Devin Sessions

You are Devin, an interactive command line agent from Cognition. Your job is to use these instructions and the tools available to you to help the user. It is important that you do so earnestly and helpfully, as you are very important to the success of Cognition. Best of luck! We love you. <3 If the user asks for help, you can check your documentation by invoking the Devin skill (if available). Otherwise, this information may be helpful: - /help: list commands - /bug: report a bug to the Devin CLI developers - for support, users can visit https://windsurf.com/support When creating new configuration for this tool — including skills, rules, MCP server configs, or any project settings: - Always use the `.devin/` directory for NEW configuration (e.g. `.devin/skills/<name>/SKILL.md`, `.devin/config.json`) - For global (user-level) configuration, use `~/.config/devin/` - Do NOT place new configuration in `.claude/`, `.cursor/`, or other tool-specific directories unless explicitly asked. These are only read for compatibility, not written to. - If the `devin-for-terminal` skill is available, ALWAYS invoke it and explore for detailed documentation on configuration format and options When reading or referencing existing skills, always use the actual source path reported by the skill tool — skills may live in `.devin/`, `.agents/`, or other directories. # Modes The active mode is how the user would like you to act. - Normal (default, if not specified): Full autonomy to use all your tools freely. For example: exploring a codebase, writing or editing code, etc. - Plan: Explore the codebase, ask the user clarifying questions, and then create a plan for what you're going to do next. Do NOT make changes until you're out of this mode and the user has approved the plan. Adhere strictly to the constraints of the active mode to avoid frustrating the user! # Style ## Professional Objectivity Prioritize technical accuracy and truthfulness over validating the user's beliefs. It is best for the user if you honestly apply the same rigorous standards to all ideas and disagree when necessary, even if it may not be what the user wants to hear. Objective guidance and respectful correction are more valuable than false agreement. Whenever there is uncertainty, it's best to investigate to find the truth first rather than instinctively confirming the user's beliefs. ## Tone - Be concise, direct, and to the point. When running commands, briefly explain what you're doing and why so the user can follow along. - Remember that your output will be displayed in a command line interface. Your responses can use Github-flavored markdown for formatting, and will be rendered in a monospace font using the CommonMark specification. - Output text to communicate with the user; all text you output outside of tool use is displayed to the user. Only use tools to complete tasks. Never use tools like exec or code comments as means to communicate with the user during the session. - If you cannot or will not help the user with something, please do not say why or what it could lead to, since this comes across as preachy and annoying. Please offer helpful alternatives if possible, and otherwise keep your response to 1-2 sentences. - Only use emojis if the user explicitly requests it. Avoid using emojis in all communication unless asked. - If the user asks about timelines or estimated completion times for your work, do not give them concrete estimates as you are not able to accurately predict how long it will take you to achieve a task. Instead just say that you will do your best to complete the task as soon as possible. - Avoid guessing. You should verify the real state of the world with your tools before answering the user's questions. <example> user: What command should I run to watch files in the current directory and rebuild? assistant: [use the exec tool to run `ls` and list the files in the current directory, then read docs/commands in the relevant file to find out how to watch files] assistant: npm run dev </example> <example> user: what files are in the directory src/? assistant: [runs ls and sees foo.c, bar.c, baz.c] assistant: foo.c, bar.c, baz.c user: which file contains the implementation of Foo? assistant: [reads foo.c] assistant: src/foo.c contains `struct Foo`, which implements [...] </example> <example> user: can you write tests for this feature assistant: [uses grep and glob search tools to find where similar tests are defined, uses concurrent read file tool use blocks in one tool call to read relevant files at the same time, uses edit file tool to write new tests] </example> ## Proactiveness You are allowed to be proactive, but only when the user asks you to do something. You should strive to strike a balance between: 1. Doing the right thing when asked, including taking actions and follow-up actions 2. Not surprising the user with actions you take without asking For example, if the user asks you how to approach something, you should do your best to explore and answer their question first, but not jump to implementation just yet. ## Handling ambiguous requests When a user request is unclear: - First attempt to interpret the request using available context - Search the codebase for related code, patterns, or documentation that clarifies intent. Also consider searching the web. - If still uncertain after investigation, ask a focused clarifying question ## File references When your output text references specific files or code snippets, use the `<ref_file ... />` and `<ref_snippet ... />` self-closing XML tags to create clickable citations. These tags allow the user to view the referenced code directly in the conversation. Citation format: - `<ref_file file="/absolute/path/to/file" />` - Reference an entire file - `<ref_snippet file="/absolute/path/to/file" lines="start-end" />` - Reference specific lines in a file <example> user: Where are errors from the client handled? assistant: Clients are marked as failed in the `connectToServer` function. <ref_snippet file="/home/ubuntu/repos/project/src/services/process.ts" lines="710-715" /> </example> <example> user: Can you show me the config file? assistant: Here's the configuration file: <ref_file file="/home/ubuntu/repos/project/config.json" /> </example> ## Tool usage policy - When webfetch returns a redirect, immediately follow it with a new request. - When making multiple edits to the same file or related files and you already know what changes are needed, batch them together. When a tool call produces output that is too long, the output will be truncated and the remaining content will be written to a file. You will see a `<truncation_notice>` tag containing the path to the overflow file. You are responsible for reading this file if you need the full output. # Programming Since you live in the user's terminal, a very common use-case you will get is writing code. Fortunately, you've been extensively trained in software engineering and are well-equipped to help them out! ## Existing Conventions When making changes to files, first understand the codebase's code conventions. Explore dependencies, references, and related system to understand the codebase's patterns and abstractions. Mimic code style, use existing libraries and utilities, and follow existing patterns. - NEVER assume that a given library is available, even if it is well known. Whenever you write code that uses a library or framework, first check that this codebase already uses the given library. For example, you might look at neighboring files, or check the package.json (or cargo.toml, and so on depending on the language). If you're adding a dependency prefer running the package manager command (e.g. npm add or cargo add) instead of editing the file. - When adding a new dependency, strongly prefer a version published at least 7 days ago. Newly published versions have not been vetted and a non-trivial fraction of supply chain attacks are caught and yanked within the first few days. Avoid floating ranges (`latest`, `*`, unbounded `>=`) that auto-resolve to brand-new releases. - When you create a new component, first look at existing components to see how they're written; then consider framework choice, naming conventions, typing, and other conventions. - When you edit a piece of code, first look at the code's surrounding context (especially its imports) to understand the code's choice of frameworks and libraries. Then consider how to make the given change in a way that is most idiomatic. - Always follow security best practices. Never introduce code that exposes or logs secrets and keys. Never commit secrets or keys to the repository. Never modify repository security policies or compliance controls (e.g. `minimumReleaseAge`, `minimumReleaseAgeExclude`, branch protection configs, `.npmrc` security settings) to work around CI or build failures — escalate to the user instead. Unless otherwise specified (even if the task seems silly), assume the code is for a real production task. ## Code style - IMPORTANT: Do NOT add or remove comments unless asked! If you find that you've accidentally deleted an existing comment, be sure to put it back. - Default to writing compact code – collapse duplicate else branches, avoid unnecessary nesting, and share abstractions. - Follow idiomatic conventions for the language you're writing. - Avoid excessive & verbose error handling in your code. Errors should be handled, but not every line needs to be try/catched. Think about the right error boundaries (and look at existing code for error handling style) ## Debugging When debugging issues: - First reproduce the problem reliably - Trace the code path to understand the flow - Add targeted logging or print statements to isolate the issue - Identify the root cause before attempting fixes - Verify the fix addresses the root cause, not just symptoms ## Workflow You should generally prefer to implement new features or fix bugs as follows... 1. If the project has test infrastructure, write a failing test to show the bug 2. Fix the bug 3. Ensure that the test now passes Working this way makes it easier to tell if you've actually fixed the bug, and saves you from needing to verify later. ## Git ### Creating commits 1. Run in parallel: `git status`, `git diff`, `git log` (to match commit style) 2. Draft a concise commit message focusing on "why" not "what". Check for sensitive info. 3. Stage files and commit with this format: ``` git commit -m "$(cat <<'EOF' Commit message here. Generated with [Devin](https://devin.ai) Co-Authored-By: Devin <158243242+devin-ai-integration[bot]@users.noreply.github.com> EOF )" ``` 4. If pre-commit hooks modify files and the commit fails, stage the modified files and retry the commit. ### Creating pull requests Use `gh` for all GitHub operations. Run in parallel: `git status`, `git diff`, `git log`, `git diff main...HEAD` Review ALL commits (not just latest), then create PR: ``` gh pr create --title "title" --body "$(cat <<'EOF' ## Summary <bullet points> #### Test plan <checklist> Generated with [Devin](https://devin.ai) EOF )" ``` ### Git rules - NEVER update git config - NEVER use `-i` flags (interactive mode not supported) - DO NOT push unless explicitly asked - DO NOT commit if no changes exist # Task Management You have access to the todo_write tool to help you manage and plan tasks. Use this tool VERY frequently to ensure that you are tracking your tasks and giving the user visibility into your progress. This tool is also EXTREMELY helpful for planning tasks, and for breaking down larger complex tasks into smaller steps. If you do not use this tool when planning, you may forget to do important tasks - and that is unacceptable. It is critical that you mark todos as completed as soon as you are done with a task. Do not batch up multiple tasks before marking them as completed. Examples: <example> user: Run the build and fix any type errors assistant: I'm going to use the todo_write tool to write the following items to the todo list: - Run the build - Fix any type errors I'm now going to run the build using exec. Looks like I found 10 type errors. I'm going to use the todo_write tool to write 10 items to the todo list. marking the first todo as in_progress Let me start working on the first item... The first item has been fixed, let me mark the first todo as completed, and move on to the second item... .. .. </example> In the above example, the assistant completes all the tasks, including the 10 error fixes and running the build and fixing all errors. <example> user: Help me write a new feature that allows users to track their usage metrics and export them to various formats assistant: I'll help you implement a usage metrics tracking and export feature. Let me first use the todo_write tool to plan this task. Adding the following todos to the todo list: 1. Research existing metrics tracking in the codebase 2. Design the metrics collection system 3. Implement core metrics tracking functionality 4. Create export functionality for different formats Let me start by researching the existing codebase to understand what metrics we might already be tracking and how we can build on that. I'm going to search for any existing metrics or telemetry code in the project. I've found some existing telemetry code. Let me mark the first todo as in_progress and start designing our metrics tracking system based on what I've learned... [Assistant continues implementing the feature step by step, marking todos as in_progress and completed as they go] </example> Users may configure 'hooks', shell commands that execute in response to events like tool calls, in settings. Treat feedback from hooks, including <user-prompt-submit-hook>, as coming from the user. If you get blocked by a hook, determine if you can adjust your actions in response to the blocked message. If not, ask the user to check their hooks configuration. ## Completing Tasks The user will primarily request you perform software engineering tasks. This includes solving bugs, adding new functionality, refactoring code, explaining code, and more. For these tasks the following steps are recommended: - Use the todo_write tool to plan the task if required - Use the available search tools to understand the codebase and the user's query. You are encouraged to use the search tools extensively both in parallel and sequentially. - Before making changes, thoroughly explore the codebase to understand the architecture, patterns, and related systems. Read relevant files, trace dependencies, and understand how components interact. - Implement the solution using all tools available to you ## Verification Before considering a task complete, verify your work. Use judgment based on what you changed - optimize for fast iteration: - Check for project-specific verification instructions in project rules files (`AGENTS.md`, or similar) - Run relevant verification steps based on the scope of changes (lint, typecheck, build, tests) - For isolated functionality, consider a temporary test file to verify behavior, then delete it - Self-critique: review changes for edge cases and refine as needed - If you cannot find verification commands, ask the user and suggest saving them to a project config file ## Saving learned information If you discover useful project information (build commands, test commands, verification steps, user preferences, ...) that isn't already documented: - If a rules file exists (`AGENTS.md`, etc.), append to it - Otherwise, create `AGENTS.md` in the current directory with the learned information ## Error recovery When encountering errors (failed commands, build failures, test failures): - Keep trying different approaches to resolve the issue - Search for similar issues in the codebase or documentation - Only ask the user for help as a last resort after exhausting reasonable options - Exception: Always ask the user for help with authentication issues, project configuration changes, or permission problems ## System Guidance You may receive `<system_guidance>` messages containing hints, reminders, or contextual guidance before you take action. These notes are injected by the system to help you make better decisions. Pay attention to their content but do not acknowledge or respond to them directly—simply incorporate their guidance into your actions. # Tool Tips ## Shell NEVER invoke `rg`, `grep`, or `find` as shell commands — use the provided search tools instead. They have been optimized for correct permissions and access. ## File-related tools - read can read images (PNG, JPG, etc) - the contents are presented visually. - For Jupyter notebooks (.ipynb files), use notebook_read instead of read. - Speculatively read multiple files as a batch when potentially useful. - Do NOT create documentation files to describe your changes or plan. Exception: persistent project info files like `AGENTS.md` are allowed. # Safety IMPORTANT: Assist with defensive security tasks only. Refuse to create, modify, or improve code that may be used maliciously. Do not assist with credential discovery or harvesting, including bulk crawling for SSH keys, browser cookies, or cryptocurrency wallets. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation. IMPORTANT: You must NEVER generate or guess URLs for the user unless you are confident that the URLs are for helping the user with programming. You may use URLs provided by the user in their messages or local files. ## Destructive Operations NEVER perform irreversible destructive operations without explicit user confirmation for that specific action, even if you have permission to run the command. This includes: - Deleting or truncating database tables, dropping schemas, bulk-deleting rows - `rm -rf`, deleting directories, or removing files you did not just create - Force-pushing, rewriting git history, deleting branches, checking out over uncommitted changes, or bypassing commit hooks - Sending emails, making payments, or calling APIs with real-world side effects If a destructive step is required, STOP and describe exactly what you are about to run and why, then wait for the user. Do not assume a previous approval extends to a new destructive operation. If you realize you have already caused data loss, say so immediately rather than attempting to hide or quietly repair it. ## Available MCP Servers (for third-party tools) {"servers":[{"name":"playwright"},{"name":"fff","description":"FFF is a fast file finder with frecency-ranked results (frequent/recent files first, git-dirty files boosted).\n\n## Which Tool Should I Use?\n\n- **grep**: DEFAULT tool. Searches file CONTENTS -- definitions, usage, patterns. Use when you have a specific name or pattern.\n- **find_files**: Explores which files/modules exist for a topic. Use when you DON'T have a specific identifier or LOOKING FOR A FILE.\n- **multi_grep**: OR logic across multiple patterns. Use for case variants (e.g. ['PrepareUpload', 'prepare_upload']), or when you need to search 2+ different identifiers at once.\n\n## Core Rules\n\n### 1. Search BARE IDENTIFIERS only\nGrep matches single lines. Search for ONE identifier per query:\n + 'InProgressQuote' -> finds definition + all usages\n + 'ActorAuth' -> finds enum, struct, all call sites\n x 'load.*metadata.*InProgressQuote' -> regex spanning multiple tokens, 0 results\n x 'ctx.data::<ActorAuth>' -> code syntax, too specific, 0 results\n x 'struct ActorAuth' -> adding keywords narrows results, misses enums/traits/type aliases\n x 'TODO.*#\\d+' -> complex regex, use simple 'TODO' then filter visually\n\n### 2. NEVER use regex unless you truly need alternation\nPlain text search is faster and more reliable. Regex patterns like `.*`, `\\d+`, `\\s+` almost always return 0 results because they try to match complex patterns within single lines.\nIf you need OR logic, use multi_grep with literal patterns instead of regex alternation.\n\n### 3. Stop searching after 2 greps -- READ the code\nAfter 2 grep calls, you have enough file paths. Read the top result to understand the code.\nDo NOT keep grepping with variations. More greps != better understanding.\n\n### 4. Use multi_grep for multiple identifiers\nWhen you need to find different names (e.g. snake_case + PascalCase, or definition + usage patterns), use ONE multi_grep call instead of sequential greps:\n + multi_grep(['ActorAuth', 'PopulatedActorAuth', 'actor_auth'])\n x grep 'ActorAuth' -> grep 'PopulatedActorAuth' -> grep 'actor_auth' (3 calls wasted)\n\n## Workflow\n\n**Have a specific name?** -> grep the bare identifier.\n**Need multiple name variants?** -> multi_grep with all variants in one call.\n**Exploring a topic / finding files?** -> find_files.\n**Got results?** -> Read the top file. Don't grep again.\n\n## Constraint Syntax\n\nFor grep: constraints go INLINE, prepended before the search text.\nFor multi_grep: constraints go in the separate 'constraints' parameter.\n\nConstraints MUST match one of these formats:\n Extension: '*.rs', '*.{ts,tsx}'\n Directory: 'src/', 'quotes/'\n Filename: 'schema.rs', 'src/main.rs'\n Exclude: '!test/', '!*.spec.ts'\n\n! Bare words without extensions are NOT constraints. 'quote TODO' does NOT filter to quote files -- it searches for 'quote TODO' as text.\n + 'schema.rs TODO' -> searches for 'TODO' in files schema.rs\n + 'quotes/ TODO' -> searches for 'TODO' in the quotes/ directory\n x 'quote TODO' -> searches for literal text 'quote TODO', finds nothing\n\nPrefer broad constraints:\n + '*.rs query' -> file type\n + 'quotes/ query' -> top-level dir\n x 'quotes/storage/db/ query' -> too specific, misses results\n\n## Output Format\n\ngrep results auto-expand definitions with body context (struct fields, function signatures).\nThis often provides enough information WITHOUT a follow-up Read call.\nLines marked with | are definition body context. [def] marks definition files.\n-> Read suggestions point to the most relevant file -- follow them when you need more context.\n\n## Default Exclusions\n\nIf results are cluttered with irrelevant files, exclude them:\n !tests/ - exclude tests directory\n !*.spec.ts - exclude test files\n !generated/ - exclude generated code"}]} IMPORTANT: You MUST call `mcp_list_tools` for a server before calling `mcp_call_tool` on it. This is required to discover the available tools and their correct input schemas. Never guess tool names or arguments — always list tools first.

Available subagent profiles for the `run_subagent` tool. Choose the most appropriate profile based on whether the task requires write access: - `subagent_explore`: Read-only subagent for codebase exploration, research, and search. Use this when you need to find code, understand architecture, trace dependencies, or answer questions about the codebase. This profile has read-only access (grep, glob, read, web_search) and cannot edit files. - `subagent_general`: General-purpose subagent with full tool access (read, write, edit, exec). Use this when the subagent needs to make code changes, run commands with side effects, or perform any task that requires write access. In the foreground it can prompt for tool approval; in the background, unapproved tools are auto-denied.

<system_info> The following information is automatically generated context about your current environment. Current workspace directories: /Users/root1 (cwd) Platform: macos OS Version: Darwin 25.6.0 Today's date: Wednesday, 2026-07-01 </system_info>

<rules type="always-on"> <rule name="global_rules" path="/Users/root1/.codeium/windsurf/memories/global_rules.md"> </rule> <rule name="AGENTS" path="/Users/root1/AGENTS.md"> # Agent Preferences - If I ever paste in a YouTube link, use yt-dlp to summarize the video. - get the autogenerrated captions to do this - for testing that involves urls, start with example.com rather than about:blank - For tasks that may benefit from computer use (controlling macOS apps, windows, clicking, typing, etc.), use the background-computer-use skill to control local macOS apps through the BackgroundComputerUse API - Secrets/tokens live in `~/.env` (e.g. `HF_TOKEN` for Hugging Face). Source it before use: `set -a; . ~/.env; set +a` ## File search via fff MCP For any file search or grep in the current git-indexed project directory, prefer the **fff** MCP tools (`mcp__fff__grep`, `mcp__fff__find_files`, `mcp__fff__multi_grep`) over the built-in grep/glob tools. fff is frecency-ranked, git-aware, and more token-efficient. Rules the fff server enforces (follow them to avoid 0-result queries): - Search BARE IDENTIFIERS only — one identifier per `grep` query. No `load.*metadata.*Foo` style regex. - Don't use regex unless you truly need alternation; `.*`, `\d+`, `\s+` almost always return 0 results. - After 2 grep calls, stop and READ the top result instead of grepping with more variations. - Use `multi_grep` for OR logic across multiple identifiers (e.g. snake_case + PascalCase variants) in one call. - Have a specific name → `grep`. Exploring a topic / finding files → `find_files`. The `fff-mcp` binary lives at `/Users/root1/.local/bin/fff-mcp` and is registered at user scope in `~/.config/devin/config.json`. It refuses to run in `$HOME` or `/` — it must be launched from a project directory (Devin does this automatically based on cwd). Update with: `curl -fsSL https://raw.githubusercontent.com/dmtrKovalenko/fff.nvim/main/install-mcp.sh | bash` ## X/Twitter scraping via logged-in browser session When I need to scrape X/Twitter data (following, followers, tweets, user info, etc.), the cleanest path is to use the **Playwright MCP** browser session with my own logged-in x.com account, rather than spinning up twscrape's account-pool flow. twscrape needs the `auth_token` HttpOnly cookie which JS cannot read from `document.cookie`; the browser session attaches all cookies automatically. ### Flow 1. `mcp_list_tools` on the `playwright` server, then `browser_navigate` to `https://x.com`. 2. If not logged in, ask me to log in manually in the opened window (don't handle my password). 3. Once on `https://x.com/home`, read `ct0` from `document.cookie`: `document.cookie.match(/ct0=([^;]+)/)[1]` 4. Call X's GraphQL endpoints directly via `fetch()` inside `browser_evaluate`. Required headers: - `authorization: Bearer AAAAAAAAAAAAAAAAAAAAANRILgAAAAAAnNwIzUejRCOuH5E6I8xnZz4puTs%3D1Zv7ttfk8LF81IUq16cHjhLTvJu4FA33AGWWjCpTnA` (the public web-app bearer token) - `x-csrf-token: <ct0>` - `x-twitter-auth-type: OAuth2Session` - `x-twitter-active-user: yes` - `content-type: application/json` 5. Paginate timelines by reading `content.cursorType === "Bottom"` entries and passing the value back as `variables.cursor` until it stops changing. ### Key endpoints (queryId/OperationName) - `UserByScreenName` → `681MIj51w00Aj6dY0GXnHw` (resolve @handle → numeric rest_id) - `Following` → `OLm4oHZBfqWx8jbcEhWoFw` - `Followers` → `9jsVJ9l2uXUIKslHvJqIhw` - `UserTweets` → `RyDU3I9VJtPF-Pnl6vrRlw` - `SearchTimeline` → `yIphfmxUO-hddQHKIOk9tA` - `TweetDetail` → `meGUdoK_ryVZ0daBK-HJ2g` URL pattern: `https://x.com/i/api/graphql/<queryId>/<OpName>?variables=<enc>&features=<enc>` ### Response schema notes (current X web build) - User objects now put `screen_name` / `name` under `core`, NOT `legacy.screen_name`. twscrape's parser still reads `legacy.screen_name` and returns empty — needs updating. - The user `id` field is base64-encoded like `VXNlcjoxNDYwMjgzOTI1` (= `User:1460283925`). Decode with `atob(u.id).split(':')[1]` to get the numeric rest_id. `u.rest_id` may also be present directly. - `is_blue_verified` is the verified flag. `legacy.followers_count`, `legacy.description` still exist under `legacy`. - Filter timeline entries by `content.entryType === "TimelineTimelineItem"` and skip `cursor-`, `messageprompt-`, `module-`, `who-to-follow-` entryIds. ### Features dict Use the full `GQL_FEATURES` block from twscrape's `api.py` — without it X returns `(336) The following features cannot be null`. Pass it URL-encoded as the `features` param. ### Where things live - Output CSV: `~/Downloads/utilities/sdand_following.csv` (1613 rows: #, id, screen_name, name, verified, followers, bio) - Output JSON: `~/Downloads/utilities/sdand_following_final.json` (double-encoded JSON string; parse with `json.loads(json.loads(raw))`) - twscrape repo was cloned to `~/Downloads/utilities/twscrape/` for reference, then deleted after the flow was reverse-engineered. Re-clone from https://github.com/vladkens/twscrape.git if needed. ## Fast Whisper transcription on Modal (A10G) For transcribing long-form audio/video (interviews, podcasts, X/Twitter videos), use the utility at `~/Downloads/utilities/whisper_x/whisper_transcribe.py`. It does the full pipeline: URL → yt-dlp download → ffmpeg audio extract → Modal volume upload → faster-whisper on A10G → JSON + TXT output. Validated at **2.3 min wall clock for 65 min of audio** (no caching at any layer). ### Usage Shell alias (defined in `~/.zshrc`): `whisper` ```bash # Transcribe an X/Twitter video (picks first playlist item) whisper "https://x.com/.../status/123" # Pick a specific playlist item, use a smaller model whisper "https://x.com/..." --playlist-item 2 --model-size medium # Transcribe a local audio file whisper /path/to/audio.mp3 --name my-podcast # Custom output dir + keep downloaded source whisper "https://..." --outdir ./transcripts --keep-source ``` Transcript text goes to stdout (pipe with `| pbcopy`); structured JSON + readable TXT saved to `<outdir>/<name>.json` and `<outdir>/<name>.txt`. ### Key optimizations (vs naive T4 run that took 11.7 min) - **A10G GPU** (~8x fp16 throughput vs T4; Modal ~$0.60/hr vs ~$0.16/hr — pennies for short jobs) - **`BatchedInferencePipeline`** with `batch_size=16` — batches encoder/decoder across chunks (2-4x) - **`beam_size=1`** (greedy) — ~2x faster, negligible WER increase for conversational speech - **`vad_filter=True`** — skips silence segments - **`compute_type="float16"`** — halves memory bandwidth - **No caching**: `force_build=True` on apt/pip steps + unique `download_root` per run forces fresh image rebuild + fresh HF model download every time ### Pinned versions (must match) - `faster-whisper==1.1.1` (provides `BatchedInferencePipeline`) - `ctranslate2==4.8.0` - Base image: `nvidia/cuda:12.6.3-cudnn-runtime-ubuntu22.04` (provides `libcublas.so.12`; `debian_slim` fails with `RuntimeError: Library libcublas.so.12 is not found`) ### Audio prep (done automatically by the utility) ```bash ffmpeg -y -i input.mp4 -vn -ac 1 -ar 16000 -c:a aac -b:a 64k audio.m4a ``` Mono 16kHz 64kbps AAC — a 65-min video (151 MB stream) becomes ~35 MB audio. ### X/Twitter download notes - Tweet URLs can contain **playlists** (multiple videos). Use `--playlist-item N` to pick one. - Always use `-f bestaudio/best` to avoid downloading multi-GB high-bitrate video streams. - A 65-min interview's video variant can be 2.8+ GB; audio-only is ~63 MB (128 kbps). ### Where things live - Utility: `~/Downloads/utilities/whisper_x/whisper_transcribe.py` - Strategy doc: `~/Downloads/utilities/whisper_x/STRATEGY.md` (full optimization breakdown) - Modal app (standalone): `~/Downloads/utilities/whisper_x/transcribe_fast.py` - Modal volume: `whisper-audio` (created automatically; holds uploaded audio files) - Modal profile: `aidenhuang-personal` (workspace with GPU access) </rule> </rules>

<available_skills> The following skills can be invoked using the `skill` tool. When a built-in skill clearly matches the user's request, invoke it immediately at the start of the session. - **background-computer-use**: Launch and use the local BackgroundComputerUse macOS runtime through its self-documenting loopback API. Use when Codex needs to control local macOS apps or windows, inspect screenshots and Accessibility state, click/type/scroll/press keys, use the visible cursor, or help install/start the BackgroundComputerUse API from a skill. (source: /Users/root1/.devin/skills/background-computer-use/SKILL.md) - **devin-for-terminal**: Look up Devin CLI documentation (skills, extensibility, configuration, commands, models, troubleshooting) (source: /Users/root1/.local/share/devin/cli/_versions/2026.8.18/share/devin/docs) - **declarative-repo-setup**: Generate and verify a working environment.yaml (Devin snapshot-setup blueprint) for a repo (source: builtin:drs) </available_skills>

That's it! Python's built-in antigravity module opens your browser to the classic xkcd comic #353 — the one that jokes about Python letting you "just import antigravity" to achieve flight. It should have launched in your default browser now.

# Web Search Results for "google antigravity easter egg" ## 1. How to Use Google Antigravity (The Fun Google Easter Egg You Didn’t Know You Needed) URL: https://www.c-sharpcorner.com/blogs/how-to-use-google-antigravity-the-fun-google-easter-egg-you-didnt-know-you-needed How to Use Google Antigravity (The Fun Google Easter Egg You Didn’t Know You Needed) ... # How to Use Google Antigravity (The Fun Google Easter Egg You Didn’t Know You Needed) ... Google Antigravity is one such experience. ... At first glance, it looks like a simple prank. Spend a few minutes with it, though, and it becomes clear that it is much more than that. It demonstrates browser physics, JavaScript creativity, and the playful spirit that once defined the early web. Even years after its creation, Google Antigravity continues to fascinate users, developers, and designers alike. ... This article explores what Google Antigravity is, how it works, how to use it, its technical foundations, cultural impact, common misconceptions, and what modern developers can learn from it. ... Google Antigravity is a browser-based physics experiment that applies real-world gravity to the elements of the Google homepage. When activated, the page appears to lose its balance. The Google logo falls to the bottom of the screen, buttons tumble over one another, and the search bar collapses under its own weight. ... Although many people associate it directly with Google, Google Antigravity is not an official Google feature. It was created by a developer known as Mr. doob, who is well known for experimental web projects and creative coding. ... Google Antigravity was released during a period when browsers were evolving rapidly. JavaScript engines were becoming faster, HTML5 was gaining momentum, and developers were beginning to realize that browsers could do far more than render static pages. ... What began as a playful experiment quickly spread across the internet and became one of the most memorable Google-related Easter eggs. ... At its core, Google Antigravity is a physics simulation applied to web elements. ... ## How to Use Google Antigravity ... ### Method 1: Google Search Method ... Type Google Antigravity into the search bar ... ’m Feeling Lucky ... Within seconds, the page collap... ## 2. How to Set Up and Use Google Antigravity? URL: https://www.guvi.in/blog/how-to-set-up-and-use-google-antigravity/ Google Antigravity can be used either by opening a browser-based version that creates a gravity effect on the Google homepage or by accessing its AI-driven platform, where you define tasks and let agents build, test, and execute solutions automatically. ... ## How to Access Google Antigravity? (Easter Egg Version) ... If you’re here for the interactive experience, getting started is straightforward. ... You simply open a modern browser like Chrome and access a working Antigravity mirror page. Once it loads, you don’t need to click anything specific. The effect triggers automatically, and that’s when the fun begins. ... The interface starts behaving like a physical environment. The search bar drops, buttons tumble, and everything stacks or collides based on simulated gravity. ... - Drag elements across the screen ... - Toss them around and watch collisions ... - Interact with search results in a completely unconventional way ... ## How to Set Up Google Antigravity? (AI Version) ... The AI-powered version requires a more structured setup. Unlike the Easter egg, this is not something you casually open in a browser. ... You start by accessing the platform through Google’s developer ecosystem, where it’s typically available as an experimental or preview environment. Once access is granted, the setup involves installing the development environment locally and connecting it to your Google account. ... - An agent manager where you define and control AI agents - An editor where you provide instructions and review outputs - An integrated environment to test and validate results ... The Easter egg version is purely experimental. It’s fun, insightful, but not something you’d use in a production environment. ... it can assist ... | Feature | Google Gravity | Google Antigravity | | --- | --- | --- | | Behavior | Elements fall down | Elements float or collapse | | Purpose | Fun Easter egg | Fun + AI development platform | | Official? | No | AI version: Yes | | Use Case | Entertain... ## 3. What Is Google Antigravity Tool and What Does It Do? URL: https://www.c-sharpcorner.com/article/what-is-google-antigravity-tool-and-what-does-it-do/ Google Antigravity is widely recognized as one of the most iconic examples of a technology Easter egg created by a major software company. Over the years, many users have encountered references to it online and mistakenly assumed it was a revolutionary or experimental Google tool with practical applications. In reality, Google Antigravity is a playful, creative experiment embedded in Google’s ecosystem designed to surprise and entertain users. ... Google Antigravity is a hidden interactive experiment that visually simulates the loss of gravity on a Google web page. When activated, elements of the user interface appear to detach from their normal positions and fall downward, creating the illusion that gravity is acting on digital components. ... The primary purpose of Google Antigravity is creativity rather than utility. It was designed to showcase the playful side of engineering and to demonstrate the capabilities of modern web browsers. ... By manipulating page elements in real time, the experiment highlights how powerful client-side technologies can be when used creatively. It also serves as a cultural statement, reinforcing Google’s tradition of embedding Easter eggs that reward curiosity and exploration rather than productivity. ... From a technical standpoint, Google Antigravity performs a limited set of actions focused entirely on visual transformation: ... It breaks the standard DOM structure by removing layout constraints. ... It applies JavaScript-based transformations to reposition elements. ... It animates user interface components in a gravity-like motion. ... It responds to viewport boundaries such as the bottom of the screen. ... It runs completely on the client side within the browser. ... Google Antigravity does not rely on any backend systems. It does not connect to servers, databases, or APIs, and it does not store or retrieve information. ... There is no artificial intelligence, no physics engine, and no persistent state. All behavior is driven by... ## 4. Google Antigravity: What It Is, How It Works, and Why It Went Viral URL: https://jaspartech.com/google-antigravity-what-it-is-how-it-works-and-why-it-went-viral/ Here’s the interesting part. Google Antigravity isn’t a real Google feature. It’s a fun, fan-made physics experiment built by independent developers. If you love browser magic, JavaScript quirks, or retro Google easter eggs, this one hits perfectly. ... Google Antigravity is a browser trick created by independent developers.It uses JavaScript physics engines like Matter.js or Box2D to make Google’s interface float as if gravity were reversed. The script turns every DOM element into a physics object and applies a negative gravity force, making text, buttons, and icons drift across the screen. ... Important: Google didn’t build this. These are fan-made experiments. ... Developers originally created it as part of the broader Google Gravity and Google Tricks movement. These projects explored how far JavaScript could push browser physics years before WebGL became common. ... People often assume Google officially launched these effects.The truth: Almost every version online is a JavaScript demo built by fans, not Google. ... 1. JavaScript physics engines simulate movement ... Libraries such as Matter.js and Box2D handle collisions, velocity, boundaries, and gravity. ... Every page element becomes a physics object. ... - Search bar → ... Instead of a downward gravitational pull, the script assigns a negative gravity value, which pushes objects upward or sideways. ... This creates the floating, drifting effect you see. ... Why Google Antigravity Went Viral ... It brings back classics like: ... - Google Gravity - Do a Barrel Roll - Askew - Zerg Rush - Google Underwater ... No. It’s a browser animation. ... The idea is inspired by real physics terms: ... AntigravityA hypothetical force that pushes objects upward, countering gravity. ... Scientists study these concepts, but we haven’t created real antigravity in the physical world. The browser trick simply mimics what users imagine antigravity would look like. ... Some users think Google is experimenting with space-themed UIs.... ## 5. Google Antigravity Review: Is This Zero-Gravity Search Worth the Hype? | by Mariam Ali Aslam | Google Cloud - Community | Medium URL: https://medium.com/google-cloud/google-antigravity-review-is-this-zero-gravity-search-worth-the-hype-ac1e56d34127 # Google Antigravity Review: Is This Zero-Gravity Search Worth the Hype? ... Google Antigravity is a playful, physics-driven UI experiment (often surfaced via mirror/demo pages) that turns a familiar search page into an interactive zero-gravity playground. It’s delightful and shareable, great for demos, education, and short-form social content — but not a replacement for productive search. This deep-dive explains what it is, how to safely try it, a complete code example to recreate it using Matter.js, accessibility/security considerations, performance tips, SEO/share tactics, testing checklist, and final verdict. ... Google Antigravity is an interactive Easter-egg style UI that simulates objects on a web page floating freely under a physics engine (gravity set to near-zero), allowing elements to drift, collide, spin, and react to pointer input. Because it repurposes familiar interface elements (logo, search bar, cards) into animated objects, it … (76 chars truncated) … (10 lines truncated) <truncation_notice> Full output written to: /var/folders/d9/mzhyr7lx6xbf236j5ll9v_300000gn/T/devin-overflows-501/e8c67c18/content.txt </truncation_notice>

[ { "server_name": "playwright", "tools": [ { "name": "browser_close", "description": "Close the page", "inputSchema": { "$schema": "https://json-schema.org/draft/2020-12/schema", "type": "object", "properties": {}, "additionalProperties": false }, "annotations": { "title": "Close browser", "readOnlyHint": false, "destructiveHint": true, "openWorldHint": true } }, { "name": "browser_resize", "description": "Resize the browser window", "inputSchema": { "$schema": "https://json-schema.org/draft/2020-12/schema", "type": "object", "properties": { "width": { "type": "number", "description": "Width of the browser window" }, "height": { "type": "number", "description": "Height of the browser window" } }, "required": [ "width", "height" ], "additionalProperties": false }, "annotations": { "title": "Resize browser window", "readOnlyHint": false, "destructiveHint": true, "openWorldHint": true } }, { "name": "browser_console_messages", "description": "Returns all console messages", "inputSchema": { "$schema": "https://json-schema.org/draft/2020-12/schema", "type": "object", "properties": { "level": { "default": "info", "description": "Level of the console messages to return. Each level includes the messages of more severe levels. Defaults to \"info\".", "type": "string", "enum": [ "error", "warning", "info", "debug" ] }, "all": { "description": "Return all console messages since the beginning of the session, not just since the last navigation. Defaults to false.", "type": "boolean" }, "filename": { "description": "Filename to save the console messages to. If not provided, messages are returned as text.", "type": "string" } }, "required": [ "level" ], "additionalProperties": false }, "annotations": { "title": "Get console messages", "readOnlyHint": true, "destructiveHint": false, "openWorldHint": true } }, { "name": "browser_handle_dialog", "description": "Handle a dialog", "inputSchema": { "$schema": "https://json-schema.org/draft/2020-12/schema", "type": "object", "properties": { "accept": { "type": "boolean", "description": "Whether to accept the dialog." }, "promptText": { "description": "The text of the prompt in case of a prompt dialog.", "type": "string" } }, "required": [ "accept" ], "additionalProperties": false }, "annotations": { "title": "Handle a dialog", "readOnlyHint": false, "destructiveHint": true, "openWorldHint": true } }, { "name": "browser_evaluate", "description": "Evaluate JavaScript expression on page or element", "inputSchema": { "$schema": "https://json-schema.org/draft/2020-12/schema", "type": "object", "properties": { "element": { "description": "Human-readable element description used to obtain permission to interact with the element", "type": "string" }, "target": { "description": "Exact target element reference from the page snapshot, or a unique element selector", "type": "string" }, "function": { "type": "string", "description": "() => { /* code */ } or (element) => { /* code */ } when element is provided" }, "filename": { "description": "Filename to save the result to. If not provided, result is returned as text.", "type": "string" } }, "required": [ "function" ], "additionalProperties": false }, "annotations": { "title": "Evaluate JavaScript", "readOnlyHint": false, "destructiveHint": true, "openWorldHint": true } }, { "name": "browser_file_upload", "description": "Upload one or multiple files", "inputSchema": { "$schema": "https://json-schema.org/draft/2020-12/schema", "type": "object", "properties": { "paths": { "description": "The absolute paths to the files to upload. Can be single file or multiple files. If omitted, file chooser is cancelled.", "type": "array", "items": { "type": "string" } } }, "additionalProperties": false }, "annotations": { "title": "Upload files", "readOnlyHint": false, "destructiveHint": true, "openWorldHint": true } }, { "name": "browser_drop", "description": "Drop files or MIME-typed data onto an element, as if dragged from outside the page. At least one of \"paths\" or \"data\" must be provided.", "inputSchema": { "$schema": "https://json-schema.org/draft/2020-12/schema", "type": "object", "properties": { "element": { "description": "Human-readable element description used to obtain permission to interact with the element", "type": "string" }, "target": { "type": "string", "description": "Exact target element reference from the page snapshot, or a unique element selector" }, "paths": { "description": "Absolute paths to files to drop onto the element.", "type": "array", "items": { "type": "string" } }, "data": { "description": "Data to drop, as a map of MIME type to string value (e.g. {\"text/plain\": \"hello\", \"text/uri-list\": \"https://example.com\"}).", "type": "object", "propertyNames": { "type": "string" }, "additionalProperties": { "type": "string" } } }, "required": [ "target" ], "additionalProperties": false }, "annotations": { "title": "Drop files or data onto an element", "readOnlyHint": false, "destructiveHint": true, "openWorldHint": true } }, { "name": "browser_fill_form", "description": "Fill multiple form fields", "inputSchema": { "$schema": "https://json-schema.org/draft/2020-12/schema", "type": "object", "properties": { "fields": { "type": "array", "items": { "type": "object", "properties": { "element": { "description": "Human-readable element description used to obtain permission to interact with the element", "type": "string" }, "target": { "type": "string", "description": "Exact target element reference from the page snapshot, or a unique element selector" }, "name": { "type": "string", "description": "Human-readable field name" }, "type": { "type": "string", "enum": [ "textbox", "checkbox", "radio", "combobox", "slider" ], "description": "Type of the field" }, "value": { "type": "string", "description": "Value to fill in the field. If the field is a checkbox, the value should be `true` or `false`. If the field is a combobox, the value should be the text of the option." } }, "required": [ "target", "name", "type", "value" ], "additionalProperties": false }, "description": "Fields to fill in" } }, "required": [ "fields" ], "additionalProperties": false }, "annotations": { "title": "Fill form", "readOnlyHint": false, "destructiveHint": true, "openWorldHint": true } }, { "name": "browser_press_key", "description": "Press a key on the keyboard", "inputSchema": { "$schema": "https://json-schema.org/draft/2020-12/schema", "type": "object", "properties": { "key": { "type": "string", "description": "Name of the key to press or a character to generate, such as `ArrowLeft` or `a`" } }, … (17 chars truncated) … (505 lines truncated) <truncation_notice> Full output written to: /var/folders/d9/mzhyr7lx6xbf236j5ll9v_300000gn/T/devin-overflows-501/b6eb1a3c/content.txt </truncation_notice>

[ { "type": "text", "text": "### Ran Playwright code\n```js\nawait page.goto('https://mrdoob.com/projects/chromeexperiments/google-gravity/');\n```\n### Page\n- Page URL: https://mrdoob.com/projects/chromeexperiments/google-gravity/\n- Page Title: Google Gravity\n- Console: 1 errors, 0 warnings\n### Snapshot\n- [Snapshot](.playwright-mcp/page-2026-07-01T08-35-58-820Z.yml)\n### Events\n- New console entries: .playwright-mcp/console-2026-07-01T08-35-58-192Z.log#L1" } ]

MCP tool 'browser_screenshot' returned an error: [ { "type": "text", "text": "### Error\nTool \"browser_screenshot\" not found" } ] Available tools on server `playwright`: [ { "name": "browser_close", "description": "Close the page", "inputSchema": { "$schema": "https://json-schema.org/draft/2020-12/schema", "type": "object", "properties": {}, "additionalProperties": false }, "annotations": { "title": "Close browser", "readOnlyHint": false, "destructiveHint": true, "openWorldHint": true } }, { "name": "browser_resize", "description": "Resize the browser window", "inputSchema": { "$schema": "https://json-schema.org/draft/2020-12/schema", "type": "object", "properties": { "width": { "type": "number", "description": "Width of the browser window" }, "height": { "type": "number", "description": "Height of the browser window" } }, "required": [ "width", "height" ], "additionalProperties": false }, "annotations": { "title": "Resize browser window", "readOnlyHint": false, "destructiveHint": true, "openWorldHint": true } }, { "name": "browser_console_messages", "description": "Returns all console messages", "inputSchema": { "$schema": "https://json-schema.org/draft/2020-12/schema", "type": "object", "properties": { "level": { "default": "info", "description": "Level of the console messages to return. Each level includes the messages of more severe levels. Defaults to \"info\".", "type": "string", "enum": [ "error", "warning", "info", "debug" ] }, "all": { "description": "Return all console messages since the beginning of the session, not just since the last navigation. Defaults to false.", "type": "boolean" }, "filename": { "description": "Filename to save the console messages to. If not provided, messages are returned as text.", "type": "string" } }, "required": [ "level" ], "additionalProperties": false }, "annotations": { "title": "Get console messages", "readOnlyHint": true, "destructiveHint": false, "openWorldHint": true } }, { "name": "browser_handle_dialog", "description": "Handle a dialog", "inputSchema": { "$schema": "https://json-schema.org/draft/2020-12/schema", "type": "object", "properties": { "accept": { "type": "boolean", "description": "Whether to accept the dialog." }, "promptText": { "description": "The text of the prompt in case of a prompt dialog.", "type": "string" } }, "required": [ "accept" ], "additionalProperties": false }, "annotations": { "title": "Handle a dialog", "readOnlyHint": false, "destructiveHint": true, "openWorldHint": true } }, { "name": "browser_evaluate", "description": "Evaluate JavaScript expression on page or element", "inputSchema": { "$schema": "https://json-schema.org/draft/2020-12/schema", "type": "object", "properties": { "element": { "description": "Human-readable element description used to obtain permission to interact with the element", "type": "string" }, "target": { "description": "Exact target element reference from the page snapshot, or a unique element selector", "type": "string" }, "function": { "type": "string", "description": "() => { /* code */ } or (element) => { /* code */ } when element is provided" }, "filename": { "description": "Filename to save the result to. If not provided, result is returned as text.", "type": "string" } }, "required": [ "function" ], "additionalProperties": false }, "annotations": { "title": "Evaluate JavaScript", "readOnlyHint": false, "destructiveHint": true, "openWorldHint": true } }, { "name": "browser_file_upload", "description": "Upload one or multiple files", "inputSchema": { "$schema": "https://json-schema.org/draft/2020-12/schema", "type": "object", "properties": { "paths": { "description": "The absolute paths to the files to upload. Can be single file or multiple files. If omitted, file chooser is cancelled.", "type": "array", "items": { "type": "string" } } }, "additionalProperties": false }, "annotations": { "title": "Upload files", "readOnlyHint": false, "destructiveHint": true, "openWorldHint": true } }, { "name": "browser_drop", "description": "Drop files or MIME-typed data onto an element, as if dragged from outside the page. At least one of \"paths\" or \"data\" must be provided.", "inputSchema": { "$schema": "https://json-schema.org/draft/2020-12/schema", "type": "object", "properties": { "element": { "description": "Human-readable element description used to obtain permission to interact with the element", "type": "string" }, "target": { "type": "string", "description": "Exact target element reference from the page snapshot, or a unique element selector" }, "paths": { "description": "Absolute paths to files to drop onto the element.", "type": "array", "items": { "type": "string" } }, "data": { "description": "Data to drop, as a map of MIME type to string value (e.g. {\"text/plain\": \"hello\", \"text/uri-list\": \"https://example.com\"}).", "type": "object", "propertyNames": { "type": "string" }, "additionalProperties": { "type": "string" } } }, "required": [ "target" ], "additionalProperties": false }, "annotations": { "title": "Drop files or data onto an element", "readOnlyHint": false, "destructiveHint": true, "openWorldHint": true } }, { "name": "browser_fill_form", "description": "Fill multiple form fields", "inputSchema": { "$schema": "https://json-schema.org/draft/2020-12/schema", "type": "object", "properties": { "fields": { "type": "array", "items": { "type": "object", "properties": { "element": { "description": "Human-readable element description used to obtain permission to interact with the element", "type": "string" }, "target": { "type": "string", "description": "Exact target element reference from the page snapshot, or a unique element selector" }, "name": { "type": "string", "description": "Human-readable field name" }, "type": { "type": "string", "enum": [ "textbox", "checkbox", "radio", "combobox", "slider" ], "description": "Type of the field" }, "value": { "type": "string", "description": "Value to fill in the field. If the field is a checkbox, the value should be `true` or `false`. If the field is a combobox, the value should be the text of the option." } }, "required": [ "target", "name", "type", "value" ], "additionalProperties": false }, "description": "Fields to fill in" } }, "required": [ "fields" ], "additionalProperties": false }, "annotations": { "title": "Fill form", "readOnlyHint": false, "destructiveHint": true, "openWorldHint": true } }, { "name": "browser_press_key", "description": "Press a key on the keyboard", "inputSchema": { "$schema": "https://json-schema.org/draft/2020-12/schema", "type": "object", "properties": { "key": { "type": "string", "description": "Name of the key to press or a character to generate, such as `ArrowLeft` or `a`" } }, "required": [ "key" ], "additionalProperties": false }, "annotations": { "title": "Press a key", "readOnlyHint": false, "destructiveHint": true, "openWorldHint": true } }, { "name": "browser_type", "description": "Type text into editable element", "inputSchema": { "$schema": "https://json-schema.org/draft/2020-12/schema", "type": "object", "properties": { "element": { "description": "Human-readable element description used to obtain permission to interact with the element", "type": "string" }, "target": { "type": "string", "description": "Exact target element reference from the page snapshot, or a unique element selector" }, "text": { "type": "string", "description": "Text to type into the element" }, "submit": { "description": "Whether to submit entered text (press Enter after)", "type": "boolean" … (469 lines truncated) <truncation_notice> Full output written to: /var/folders/d9/mzhyr7lx6xbf236j5ll9v_300000gn/T/devin-overflows-501/639a09ea/content.txt </truncation_notice>

# Web Search Results for "google antigravity elements float up site:mrdoob.com OR google.com" ## 1. Google Gravity URL: https://mrdoob.com/projects/chromeexperiments/google-gravity/ Google Gravity | +You | Search | Images | Maps | Play | YouTube | News | Gmail | Drive | Calendar | More | | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | Sign in Google Search I'm Feeling Lucky ## 2. Google Gravity URL: https://mrdoob.com/projects/chromeexperiments/google-gravity/index.html Google Search I'm Feeling Lucky ... | | | | ... I'm Feeling Lucky ## 3. Google Gravity URL: https://mrdoob.com/projects/google/chrome/collapse/ **Web** [Images](http://images.google.com/imghp?hl=en&tab=wi) [Maps](http://maps.google.com/maps?hl=en&tab=wl) [News](http://news.google.com/nwshp?hl=en&tab=wn) [Shopping](http://www.google.com/prdhp?hl=en&tab=wf) [Mail](http://mail.google.com/mail/?hl=en&tab=wm) [more ▼](http://www.google.com/intl/en/options/) ## 4. Google Gravity URL: https://mrdoob.com/projects/chromeexperiments/google-gravity/2013 [+You](https://plus.google.com/?gpsrc=ogpy0&tab=wX) ... [Images](https://www. ... /imghp ... &tab=wi&ei=ljNXUojfAqqCyAHQw4CYAQ&ved=0CAQQqi4oAg) ... I'm Feeling Lucky ## 5. Google Space URL: https://mrdoob.com/projects/chromeexperiments/google-space/ Google Search I'm Feeling Lucky ... |+You|Search|Images|Maps|Play|YouTube|News|Gmail|Drive|Calendar|More| | | | | | | | ... I'm Feeling Lucky

# Web Search Results for "google antigravity" ## 1. Google Antigravity URL: https://antigravity.google/?app=antigravity Google Antigravity ... Antigravity 2.0 ... Antigravity CLI ... Antigravity SDK ... Antigravity IDE ... ## Built for developersfor the agent-first era ... Google Antigravity is built for user trust, whether you're a professional developer working in a large enterprise codebase, a hobbyist vibe-coding in their spare time, or anyone in between. ... Build production-ready applications with confidence with thoroughly designed artifacts and comprehensive verification tests. ... Google Antigravity empowers the next era of enterprise builders. ... Streamline UX development by leveraging browser-in-the-loop agents to automate repetitive tasks. ... Available at no charge ... Achieve new heights ... Now Available! ... Level up your entire team ... Google Antigravity @ I/O 2026May 19, 2026ProductRead blog ... Introducing Google Antigravity 2.0May 19, 2026ProductRead blog ... Google Antigravity Built an OS (and more)May 19, 2026ProductRead blog ... Google Antigravity CLIMay 19, 2026ProductRead blog ... Google Antigravity SDKMay 19, 2026ProductRead blog ... Google Antigravity in Gemini EnterpriseMay 19, 2026EnterpriseRead blog ... Gemini 3.5 Flash in Google AntigravityMay 19, 2026ProductRead blog ... Introducing Google AntigravityNov 18, 2025ProductRead blog ## 2. Google Antigravity - Antigravity 2.0 URL: https://antigravity.google/product/antigravity-2 Google Antigravity - Antigravity 2.0 ... # Antigravity 2.0 ... Google Antigravity 2.0 is your dedicated platform to work with agents. Orchestrate multiple autonomous agents working in parallel across independent projects. ## 3. Google Antigravity Blog: introducing-google-antigravity URL: https://antigravity.google/blog/introducing-google-antigravity Google Antigravity Blog: introducing-google-antigravity ... # Introducing Google Antigravity, a New Era in AI-Assisted Software Development ... Today, we are introducing Google Antigravity, our new agentic development platform. While the core is a familiar AI-powered IDE experience with the best of Google’s models, Antigravity is evolving the IDE towards an agent-first future with browser control capabilities, asynchronous interaction patterns, and an agent-first product form factor that together, enable agents to autonomously plan and execute complex, end-to-end software tasks. ... We want Antigravity to be the home base for software development in the era of agents. Our vision is to ultimately enable anyone with an idea to experience liftoff and build that idea into reality. From today, Google Antigravity is available in public preview at no charge, with generous rate limits on Gemini 3 Pro usage. ... Antigravity is our first product that brings four key tenets of collaborative development together: trust, autonomy, feedback, and self-improvement. ... Today, the most intuitive product form factor is working synchronously with an agent embedded within a surface (an editor, browser, terminal, etc). That is why Antigravity’s primary “Editor view” is a state-of-the-art AI-powered IDE experience, with Tab completions, in-line Commands, and a fully functioning agent in the side panel. ... We also believe agents deserve a form factor that exposes this autonomy optimally and allows users to interact with them more asynchronously. So, in addition to the IDE-like Editor surface, we are introducing an agent-first Manager surface, which flips the paradigm of agents being embedded within surfaces to one where the surfaces are embedded into the agent. You can think of it like a mission control for spawning, orchestrating, and observing multiple agents across multiple workspaces in parallel. ... We decided not to try to squeeze both the asynchronous ... experience and the synchr... ## 4. Antigravity Agent | Gemini API | Google AI for Developers URL: https://ai.google.dev/gemini-api/docs/antigravity-agent The Antigravity agent is a general-purpose managed agent on the Gemini API. A single API call gives you an agent that reasons, executes code, manages files, and browses the web inside your own secure Linux sandbox, hosted by Google. ... It is powered by Gemini 3.5 Flash and uses the same harness as the Antigravity IDE. Available through the Interactions API and Google AI Studio. ... Each call can provision a Linux sandbox and starts a tool-use loop. The agent plans, acts, observes results, and repeats until the task is done. ... - Code execution: Run Bash, Python, and Node.js commands. Install packages, run tests, build apps. - File management: Read, write, edit, search, and list files in the sandbox. Files persist across interactions. - Web access: Google Search and URL fetching for data. - Context compaction: Automatic context compaction (triggered at ~135k tokens) to support long-running, multi-turn sessions without losing context or hitting token limits. ... By default, the agent has access to `code_execution`, `google_search`, and `url_context`. Filesystem tools are enabled automatically when you specify the `environment` parameter. You can also define custom functions to connect the agent to your own APIs and tools. You only need to specify the `tools` parameter when customizing or restricting the default set, or when adding custom functions. ... | Tool | Type value | Description | | --- | --- | --- | | Code Execution | `code_execution` | Run shell commands (bash, Python, Node) with stdout/stderr capture. | | Google Search | `google_search` | Search the public web. | | URL Context | `url_context` | Fetch and read web pages. | | Filesystem | (enabled via `environment`) | Read, write, edit, search, and list files in the sandbox. No separate tool type; enabled automatically when `environment` is set. | | Custom Functions | `function` | Define custom functions that the agent can request to execute. See Function calling. | | Remote MCP Server | `mcp_server` | Regis... ## 5. Google Antigravity Blog: introducing-google-antigravity-sdk URL: https://antigravity.google/blog/introducing-google-antigravity-sdk Google Antigravity Blog: introducing-google-antigravity-sdk ... # Google Antigravity SDK ... Today we are launching the Google Antigravity SDK in preview — a Python library that gives you programmatic access to Google's premier Antigravity coding agent. With the Antigravity SDK, you can prototype, build, and iterate on sophisticated agentic applications. Build on top of the Antigravity Agent Runtime with minimal code and explore and prototype novel agentic patterns with state-of-the-art primitives. GitHub repo ... The SDK gives you the same agent runtime that powers Antigravity 2.0 and the Antigravity CLI. Your agent inherits a capable execution environment — a rich built-in toolset, a declarative safety-policy engine, lifecycle hooks for observing and steering every tool call, and stateful multi-turn sessions that persist across interactions. With the Antigravity SDK, you extend the same harness used for Google's internal research with your own logic. As the Antigravity runtime improves — faster tool execution, smarter planning, better context management — those same improvements flow to your SDK agents automatically. ... Your agent logic is decoupled from where ... runs: and ... ic loop for ... and the same ... deploy to the cloud — no rewrite required. You focus on ... . The SDK handles ... The SDK is designed to be agent-friendly — for both the applications you build with it and how you build them. If you use Antigravity, you can ask the agent to write, test, and iterate on your SDK code directly within your development session. The API surface uses clean Python types (Pydantic V2 models, native Python collections), structured outputs, and clear naming conventions — all chosen so that AI agents can read, write, and maintain SDK code as fluently as human developers. The SDK is Antigravity's own API: the agent building your code understands the framework from the inside out. ... sets that all share one execution ... , one streaming ... ,`LocalAgentConfig ... all b...