RustApache-2.0Created Aug 23, 2024Last push todayLatest release v1.45.0+455 stars this week+624 this month
Star history
since Apr 5, 2026
52.5K stars as of Aug 7, 2026, tracked back to Apr 5, 2026. Historical curve reconstructed from public GitHub event archives, calibrated to the current total.
Contribution activity
commits per day, last 52 weeks
3,302 commits in the last yearLessMore
Signals and awards
derived from tracked data
Landmark project
52,487 stars
Very active
3,302 commits in 52 weeks
Community-driven
~590 contributors
Well documented
High community health score
Permissive license
Apache-2.0
Continuous integration
Automated checks passing
What goose does
Goose is a versatile AI assistant designed to automate software engineering tasks natively on the developer's machine. It operates as a desktop application, CLI, or API, capable of executing commands, installing dependencies, and editing files directly. It goes beyond simple code suggestions by autonomously testing its changes and iterating based on execution results. The agent uses an extensible architecture that can connect with any large language model, allowing users to choose their preferred backend. By integrating deeply with local workflows, it aims to handle complex, multi-step development tasks from start to finish.
Goose is built for software developers and engineers who want a capable, open-source AI assistant that integrates directly into their local environment. It is ideal for teams seeking an alternative to closed-ecosystem coding assistants.
Local execution: Installs, executes, edits, and tests code natively on the user's machine.
Multi-interface support: Available as a graphical desktop app, a command-line interface, and an API.
LLM agnostic: Can be configured to work with any preferred large language model.
Autonomous iteration: Capable of running code, reading errors, and automatically attempting fixes.
Extensible architecture: Designed to be customized and expanded to fit specific development workflows.
Where teams use it
Automated refactoring
Developers can instruct the agent to update legacy code patterns across an entire local project.
End-to-end task completion
Engineers can assign the agent to install a library, write a feature using it, and run the tests.
CLI automation
DevOps professionals can use the agent via the terminal to automate complex shell scripting tasks.
Local debugging
Programmers can ask the agent to analyze local error logs and edit the necessary files to resolve them.
your native open source AI agent — desktop app, CLI, and API — for code, workflows, and everything in between
goose is a general-purpose AI agent that runs on your machine. Not just for code — use it for research, writing, automation, data analysis, or anything you need to get done.
A native desktop app for macOS, Linux, and Windows. A full CLI for terminal workflows. An API to embed it anywhere. Built in Rust for performance and portability.
goose works with 15+ providers — Anthropic, OpenAI, Google, Ollama, OpenRouter, Azure, Bedrock, and more. Use API keys or your existing Claude, ChatGPT, or Gemini subscriptions via ACP. Connect to 70+ extensions via the Model Context Protocol open standard.
## ✨ Features
- Stable agent event message identity [#10716](https://github.com/aaif-goose/goose/pull/10716)
- Tab completion and switch provider for `model` command [#10585](https://github.com/aaif-goose/goose/pull/10585)
- Support latest Gemini models [#10630](https://github.com/aaif-goose/goose/pull/10630)
- Configurable GOOSE_DOCS_ROOT for air-gapped docs access [#10294](https://github.com/aaif-goose/goose/pull/10294)
- Structured summary output with template rendering for compaction [#10471](https://github.com/aaif-goose/goose/pull/10471)
- Allow disabling built-in skills [#10600](https://github.com/aaif-goose/goose/pull/10600)
- Gate tool-call label enrichment on ACP client capability [#10644](https://github.com/aaif-goose/goose/pull/10644)
## 🐛 Bug Fixes
- Restore dynamic model discovery and current Grok support [#10756](https://github.com/aaif-goose/goose/pull/10756)
- Update DeepSeek model names to v4 API [#10729](https://github.com/aaif-goose/goose/pull/10729)
- Forward Claude Code model picker selection to the adapter [#10675](https://github.com/aaif-goose/goose/pull/10675)
- Forward Pi model selection to the adapter [#10707](https://github.com/aaif-goose/goose/pull/
## Security fixes
- Arbitrary command execution in goose CLI via `goose review` (via git core.fsmonitor config) - [GHSA-r5pp-p5r8-466r](https://github.com/aaif-goose/goose/security/advisories/GHSA-r5pp-p5r8-466r) (credit to @0xmagic0)
## ✨ Features
- Support for latest Gemini models [#10630](https://github.com/aaif-goose/goose/pull/10630)
- Pass working_dir to the Stop hook context [#10296](https://github.com/aaif-goose/goose/pull/10296)
- Declarative Sakana AI provider for OpenAI-compatible Fugu API [#10357](https://github.com/aaif-goose/goose/pull/10357)
- Model interactions viewer restored [#10205](https://github.com/aaif-goose/goose/pull/10205)
- Chunk command-classifier input with overlapping windows for security [#10416](https://github.com/aaif-goose/goose/pull/10416)
- Search filter for provider grid [#10437](https://github.com/aaif-goose/goose/pull/10437)
- Muse Spark 1.1 support via Meta Models API [#10432](https://github.com/aaif-goose/goose/pull/10432)
- GPT-5.6 support [#10384](https://github.com/aaif-goose/goose/pull/10384)
- Reconnect desktop ACP sessions after sleep and connection loss [#10411](https://github.com/aaif-goose/goose/pull/10411)
- Per-m
## ✨ Features
- Reconnect desktop ACP sessions after sleep and connection loss [#10411](https://github.com/aaif-goose/goose/pull/10411)
- Per-message usage stats UI (tokens, cost, TTFT, tok/s) [#10210](https://github.com/aaif-goose/goose/pull/10210)
- Per-message usage/cost tracking with derived session totals [#10172](https://github.com/aaif-goose/goose/pull/10172)
- Group chat sessions by project in nav panel [#10212](https://github.com/aaif-goose/goose/pull/10212)
- Show project names in directory switcher dropdown [#10207](https://github.com/aaif-goose/goose/pull/10207)
- OllamaCloudProvider with dynamic model discovery and context limits [#10264](https://github.com/aaif-goose/goose/pull/10264)
- Delete support for custom apps from Apps UI [#10127](https://github.com/aaif-goose/goose/pull/10127)
- `--edit` session flag to edit conversation before forking [#9799](https://github.com/aaif-goose/goose/pull/9799)
- iFlytek Spark and Astron MaaS providers [#9837](https://github.com/aaif-goose/goose/pull/9837)
- Fireworks AI declarative provider [#9990](https://github.com/aaif-goose/goose/pull/9990)
- OpenRouter request parameters support [#9276](https://github.com/aaif-goose/goose/p
## ✨ Features
- iFlytek Spark and Astron MaaS providers (#9837)
- `--edit` session flag to edit conversation before forking (#9799)
- Fireworks AI declarative provider (#9990)
- OpenRouter request parameters support (#9276)
- French, German, Italian, Portuguese, Indonesian, Malay, Vietnamese, and Traditional Chinese desktop locales (#10072)
- Spanish (es) locale support (#9833)
- Korean localization for desktop app (#9856)
- Japanese locale support (#9768)
- Hindi desktop locale (#9733)
- Language selection feature in desktop (#9405)
- `/status` slash command in CLI (#9845)
- Streamable HTTP support in deeplink generator (#9954)
- GLM-5.2 model support (#9967)
- Global hints loading from `~/.agents/AGENTS.md` (#9736)
- Azure Entra ID bearer token auth via `AZURE_OPENAI_AD_TOKEN` (#9716)
- Together AI declarative provider (#9545)
- OrcaRouter as declarative OpenAI-compatible provider (#9515)
- EmpirioLabs AI declarative provider (#9771)
- MLX model support for local inference provider (#9154)
- Summon peek mode for async background tasks (#9519)
- Summon context parameter for delegate tasks (#9518)
- Summon working_dir override for delegate tasks (#9520)
- Structured metadata for s
Code frequency
additions and deletions
+1.8M lines added, -1.2M removed over the last year.
Commits per week
last 52 weeks
3.3K commits in the last 52 weeks.
When work happens
weekday and hour
Commit volume by weekday and hour (UTC). Larger dots mean more commits.
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
