ORG2
System of record for how agents build software: Built-in rust harness & 20+ CLIs.
Install / Use
npx skills add org2AI/ORG2Installs into whichever agent you are using.
Other
Other agent config
Quality Score
Category
Development & EngineeringSupported Platforms
Tags
Our assessment of ORG2
ORG2 scores 88/100 on our quality scale, 1797th of 4,617 Development & Engineering skills we index (top 39%).
Its Other is 14 KB long, well organised into 18 sections with 1 code example: a thorough specification that gives an agent plenty to work with.
With 2,598 GitHub stars, it is one of the more widely adopted skills in the catalogue.
Maintenance, license and trust
- The repository was last updated 2 days ago, so ORG2 is actively maintained.
- Our last check on 2026-10-20 found the source still online.
- It is released under AGPL-3.0, a copyleft license: you can use it, but modified versions you distribute must carry the same license.
- Its trust signals score 95/100, with 1 caution from licensing, adoption, age or documentation. These come from repository metadata, not a code audit — read the skill file before letting an agent act on it.
Safety scan
No issues foundOur scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful.
AI review by kimi-k2.7-code on 2026-09-24. Automated pattern scan on 2026-09-24. It catches known dangerous patterns, not every risk — read a skill before letting an agent act on it.
ORG2 compared with similar skills
All 4 of these similar skills score higher than ORG2; compare them before choosing.
| Skill | Score | Stars | Updated | Format |
|---|---|---|---|---|
| ORG2 (this skill)by org2AI | 88 | 2.6k | 2d ago | Other |
| taste-skillby Leonxlnx | 100 | 110.6k | today | CLAUDE.md |
| ai-job-searchby ai-job-search-dev | 100 | 69.8k | today | CLAUDE.md |
| claude-howtoby luongnv89 | 100 | 46.6k | 2d ago | CLAUDE.md |
| algorithmic-artby anthropics | 100 | 177.9k | 44d ago | SKILL.md |
Frequently asked questions
- How do I install ORG2?
- Run
npx skills add org2AI/ORG2. The install tabs above show the steps for each supported agent. - Which AI agents does ORG2 work with?
- It is written for Universal, as a Other file. Other agents that read the same format can often use it too.
- Is ORG2 safe to use?
- Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful. It is AGPL-3.0-licensed and scores 95/100 on trust signals. Skills are instructions an agent will follow, so read the file before installing it and do not approve commands you do not understand.
- Is ORG2 still maintained?
- The repository was last updated 2 days ago, so ORG2 is actively maintained.
Skill content
View source on GitHub<p align="center"> <a href="https://github.com/org2AI/ORG2/releases/latest/download/ORG2-latest-mac-apple-silicon.dmg"><strong>macOS Apple Silicon</strong></a> · <a href="https://github.com/org2AI/ORG2/releases/latest/download/ORG2-latest-windows-x64-setup.exe"><strong>Windows installer</strong></a> · <a href="https://github.com/org2AI/ORG2/releases/latest/download/ORG2-latest-windows-x64.msi"><strong>Windows MSI</strong></a> · <a href="https://github.com/org2AI/ORG2/releases/latest/download/ORG2-latest-linux-x64.AppImage"><strong>Linux AppImage</strong></a> · <a href="https://github.com/org2AI/ORG2/releases/latest/download/ORG2-latest-linux-x64.deb"><strong>Linux DEB</strong></a> · <a href="https://github.com/org2AI/ORG2/releases/latest"><strong>All latest release assets</strong></a> </p>
<p align="center"> <a href="README.md">English</a> · <a href="docs/readmes/README.fr.md">Français</a> · <a href="docs/readmes/README.zh.md">简体中文</a> · <a href="docs/readmes/README.zh-Hant.md">繁體中文</a> · <a href="docs/readmes/README.es.md">Español</a> · <a href="docs/readmes/README.hi.md">हिन्दी</a> · <a href="docs/readmes/README.ru.md">Русский</a> · <a href="docs/readmes/README.pt.md">Português</a> · <a href="docs/readmes/README.de.md">Deutsch</a> · <a href="docs/readmes/README.ja.md">日本語</a> · <a href="docs/readmes/README.ko.md">한국어</a> · <a href="docs/readmes/README.tr.md">Türkçe</a> · <a href="docs/readmes/README.vi.md">Tiếng Việt</a> · <a href="docs/readmes/README.id.md">Bahasa Indonesia</a> · <a href="docs/readmes/README.pl.md">Polski</a> </p> <p>Built with Rust and Tauri for local-first execution under 100MB on disk. Supports agent trajectory livestream and replay. Easy to follow and review.</p> <p align="center"> <video src="https://github.com/user-attachments/assets/bd4833d2-4cc4-4971-9805-84529b14d01a" controls width="720"></video> </p>
Answering why a piece of code exists — and whether it worked — has always meant stitching systems together by hand. Jira sees only tickets. Codex sees only its own sessions. GitHub sees only committed lines. Amplitude sees only metrics. That was survivable when humans wrote the code. At agent speed it isn't: code written on Monday is legacy by Friday.
ORG-2 is where your team runs its coding agents — a native Rust harness plus launchers for 20+ agent CLIs — and it builds that record automatically. Every session becomes a trajectory teammates replay like a video, reviewing how the work was actually built rather than just the diff and commenting in context. Sessions run in other tools are ingested and backfilled from their history, so the record covers work that never touched the app. The record links what the human asked for, what the agent understood, and what it actually did, so any shipped line traces back to the session that wrote it.
It is not just another AI coding tool; it is an experiment in human/agent organizations and org-level alignment. ORG2 treats agents as persistent, observable colleagues inside a structured organization — replayable execution, cross-session memory, AI blame, and a local-first Rust runtime so humans, agents, and teams can collaborate around shared context and aligned goals.
Features
<table> <tr> <td width="50%" valign="middle">Built-in Rust harness
Run fast, token-saving, customizable native agents with your existing API keys and agent subscriptions.
</td> <td width="50%"> <img src="docs/assets/feature-wall/rust-harness.gif" alt="Run agents with the ORG2 Rust harness" width="100%" /> </td> </tr> <tr> <td width="50%" valign="middle">Manage sessions across 10+ apps & CLIs
Load and manage agent sessions from all your tools in one place. Scan history, inspect subagents, and control each source without switching apps.
</td> <td width="50%"> <img src="docs/assets/feature-wall/session-sources.png" alt="Manage agent session sources across apps and CLIs in ORG2" width="100%" /> </td> </tr> <tr> <td width="50%" valign="middle">Team up and review trajectories, not just PRs
Form your team and share sessions across devices and teammates. Review the full agent trajectory, not only the resulting diff, and leave comments in context.
</td> <td width="50%"> <img src="docs/assets/feature-wall/team-trajectory-review.png" alt="Manage teammates and trajectory replay permissions in ORG2" width="100%" /> </td> </tr> <tr> <td width="50%" valign="middle">Tool calls, now as videos
Replay work from the native Rust harness and 15+ CLI agents. Messages, tool calls, file edits, and command output stay synchronized in one reviewable timeline.
</td> <td width="50%"> <img src="docs/assets/feature-wall/replay.gif" alt="Replay an agent session in ORG2" width="100%" /> </td> </tr> <tr> <td width="50%" valign="middle">AI blame, not just Git blame
Do not stop at who changed a line. Trace it back to the agent sessions, tool calls, and decisions that drove the change.
</td> <td width="50%"> <img src="docs/assets/feature-wall/ai-blame.gif" alt="Trace code changes back to agent sessions and decisions in ORG2" width="100%" /> </td> </tr> <tr> <td width="50%" valign="middle">Stay on track
See how your time is spent across tasks and agent sessions. A daily activity timeline keeps duration, code changes, and priorities visible.
</td> <td width="50%"> <img src="docs/assets/feature-wall/work-diary.png" alt="Review time spent across tasks and agent sessions in ORG2" width="100%" /> </td> </tr> <tr> <td width="50%" valign="middle">Full dev workspace
Use the terminal, manage source control, trace Git history, and review pull requests without leaving your agent workspace.
</td> <td width="50%"> <img src="docs/assets/feature-wall/development-workspace.gif" alt="Source control, Git history, and code review tools in ORG2" width="100%" /> </td> </tr> <tr> <td width="50%" valign="middle">Design Mode
Inspect live pages in the native WebKit browser. Select an element and send its exact page context straight to the agent for a straightforward fix.
</td> <td width="50%"> <img src="docs/assets/feature-wall/design-mode.gif" alt="Inspect a webpage element with ORG2 Design Mode" width="100%" /> </td> </tr> </table>More capabilities
- GUI, CLI, terminal, Git, browser, LSP, timeline, and database tooling.
- Cross-session memory, cross-agent knowledge sharing, and shared workspace state.
- Resource-aware execution that can react to CPU, RAM, and human attention availability.
- Agent-powered GUI end-to-end testing for supervised self-evolution.
- Scheduling and auto-started sessions so agents can run overnight or continue work when you are away.
- Org-level alignment surfaces (issues/projects management) for coordinating humans, agents, goals, and accountability (WIP).
- Session collaboration and group issue workflows via self-hosted Supabase (WIP).
Supported Agents
Use ORG2's built-in Rust harness or launch these supported coding-agent CLIs from the desktop app.
GUI + TUI
<p> <a href="#built-in-rust-harness"><kbd><img src="docs/assets/org2-icon.svg" alt="ORG-2 logo" width="22" valign="middle" /> ORG-2</kbd></a> <a href="https://cursor.com/docs/cli/overview"><kbd><img src="src/assets/modelIcons/cursor.svg" alt="Cursor CLI logo" width="16" valign="middle" /> Cursor CLI</kbd></a> <a href="https://code.claude.com/docs/en/configuration"><kbd><img src="src/assets/modelIcons/claude.svg" alt="Claude logo" width="16" valign="middle" /> Claude Code</kbd></a> <a href="https://developers.openai.com/codex/config-basic"><kbd><img src="src/assets/modelIcons/openai.svg" alt="Codex logo" width="16" valign="middle" /> Codex</kbd></a> <a href="https://kiro.dev/docs/cli/installation"><kbd><img src="src/assets/modelIcons/kiro.svg" alt="Kiro CLI logo" width="16" valign="middle" /> Kiro CLI</kbd></a> <a href="https://docs.github.com/en/copilot/how-tos/set-up/install-copilot-in-the-cli"><kbd><img src="src/assets/modelIcons/copilot.svg" alt="GitHub Copilot logo" width="16" valign="middle" /> GitHub Copilot</kbd></a> <a href="https://opencode.ai/docs/config/"><kbd><img src="src/assets/modelIcons/opencode.svg" alt="OpenCode logo" width="16" valign="middle" /> OpenCode</kbd></a> <a href="https://github.com/deepseek-ai/deepseek-harness"><kbd><img src="src/assets/modelIcons/deepseek.svg" alt="DeepSeek Harness logo" width="16" valign="middle" /> DeepSeek Harness</kbd></a> <a href="https://antigravity.google/docs/cli/getting-started"><kbd><img src="src/assets/modelIcons/antigravity.svg" alt="Antigravity logo" width="16" valign="middle" /> Antigravity</kbd></a> </p>TUI
<p> <a href="https://www.kimi.com/code/docs/en/kimi-code-cli/configuration/configuration-files.html"><kbd><img src="src/assets/modelIcons/kimi.svg" alt="Kimi Code CLI logo" width="16" valign="middle" /> Kimi Code CLI</kbd></a> <a href="https://aider.chat/docs/config.html"><kbd><img src="src/assets/modelIcons/aider.svg" alt="Aider logo" width="16" valign="middle" /> Aider</kbd></a> <a href="https://goose-docs.ai/docs/category/getting-started/"><kbd><img src="src/assets/modelIcons/goose.svg" alt="Goose logo" width="16" valign="middle" /> Goose</kbd></a> <a href="https://ampcode.com/manual"><kbd><img src="src/assets/modelIcons/amp.svg" alt="Amp logo" width="16" valign="middle" /> Amp</kbd></a> <a href="https://docs.cline.bot/cli/cli-reference"><kbd><img src="src/assets/modelIcons/cline.svg" alt="Cline logo" width="16" valign="middle" /> Cline</kbd></a> <a href="https://kilo.ai/docs/cli"><kbd><img src="src/assets/modelIcons/kilo.svg" alt="Kilo Code logo" width="16" valign="middle" /> Kilo Code</kbd></a> <a href="https://docs.x.ai/build/overview"><kbd><img src="src/assets/modelIcons/grok.svg" alt="Grok CLI logo" width="16" valign="middle" /> Grok CLI</kbd></a> <a href="https://docs.devin.ai/cli"><kbd><img src="src/assets/modelIcons/devin.svg" alt="Devin logo" width="16" valign="middle" /> Devin</kbd></a> <a href="https://hermes-agent.nousresearch.com/docs/user-guide/configuration"><kbd><img src="src/assets/modelIcons/hermes.svg" alt="Hermes logo" width="16" valign="middle" /> Hermes</kbd></a> <a href="https://docs.openclaw.ai/cli/config"><kbd><img src="src/assets/modelIcons/openclaw.svg" alt="OpenClaw logo" width="16" valign="middle" /> OpenClaw</kbd></a> <a href="https://www.codebuff.com/docs"><kbd><img src="src/assets/modelIcons/infinity-agent.svg" alt="Codebuff logo" width="16" valign="middle" /> Codebuff</kbd></a> <a href="https://qwenlm.github.io/qwen-code-docs/en/users/configuration/auth/"><kbd><img src="src/assets/modelIcons/qwen.svg" alt="Qwen Code logo" width="16" valign="middle" /> Qwen Code</kbd></a> <a href="https://mimo.xiaomi.com/mimocode/config-files"><kbd><img src="src/assets/modelIcons/xiaomimimo.svg" alt="Mimo Code logo" width="16" valign="middle" /> Mimo Code</kbd></a> <a href="https://docs.continue.dev/cli/configuration"><kbd><img src="src/assets/modelIcons/continue.svg" alt="Continue logo" width="16" valign="middle" /> Continue</kbd></a> <a href="https://docs.factory.ai/cli/byok/overview"><kbd><img src="src/assets/modelIcons/droid.svg" alt="Droid logo" width="16" valign="middle" /> Droid</kbd></a> <a href="https://docs.mistral.ai/vibe/code/cli/install-setup"><kbd><img src="src/assets/modelIcons/mistral.svg" alt="Mistral Vibe logo" width="16" valign="middle" /> Mistral Vibe</kbd></a> <a href="https://docs.autohand.ai/integrations/ai-model-providers"><kbd><img src="src/assets/modelIcons/autohand.svg" alt="Autohand logo" widthTruncated for display — read the full file on GitHub.
Related Skills
taste-skill
110.6kAgent skills that give coding agents taste: art direction, reference images and a browser check instead of generic AI pages
ai-job-search
69.8kThe job search that runs on your machine. AI job application framework built on Claude Code: evaluate postings, tailor CVs, write cover letters, prep interviews. Fork it and own it.
claude-howto
46.6kA visual, example-driven guide to Claude Code — from basic concepts to advanced agents, with copy-paste templates that bring immediate value.
algorithmic-art
177.9kCreating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems.
Languages
Trust signals
From repository metadata: license, adoption, age and documentation. Not a code audit — see the Safety scan above for what the skill file itself contains.
