{"id":51897299,"url":"https://github.com/Orkas-AI/Orkas","last_synced_at":"2026-08-01T05:00:37.119Z","repository":{"id":354656858,"uuid":"1224575142","full_name":"Orkas-AI/Orkas","owner":"Orkas-AI","description":"Open-source multi-agent AI desktop client — build and command your AI agent team through conversation. A commander LLM dispatches sub-agents in parallel or in series; agents self-evolve via reflection and skill crystallization. Local-first, BYO LLM keys (Claude · OpenAI · Gemini · DeepSeek · Kimi · GLM · Qwen). macOS / Windows / Linux.","archived":false,"fork":false,"pushed_at":"2026-07-16T18:12:24.000Z","size":51555,"stargazers_count":322,"open_issues_count":4,"forks_count":20,"subscribers_count":5,"default_branch":"main","last_synced_at":"2026-07-16T20:05:51.971Z","etag":null,"topics":["agent-collaboration","agent-orchestration","agent-team","agentic-ai","ai-agents","ai-assistant","ai-team","ai-workflow","autonomous-agents","byo-llm","cross-platform","desktop-app","electron","hermes-agent","llm","local-first","multi-agent","multi-agent-system","openclaw","self-evolving-agents"],"latest_commit_sha":null,"homepage":"https://orkas.ai?source=github","language":"TypeScript","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/Orkas-AI.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2026-04-29T12:19:08.000Z","updated_at":"2026-07-16T19:21:03.000Z","dependencies_parsed_at":"2026-07-16T20:04:09.147Z","dependency_job_id":null,"html_url":"https://github.com/Orkas-AI/Orkas","commit_stats":null,"previous_names":["orkas-ai/orkas"],"tags_count":11,"template":false,"template_full_name":null,"purl":"pkg:github/Orkas-AI/Orkas","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Orkas-AI%2FOrkas","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Orkas-AI%2FOrkas/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Orkas-AI%2FOrkas/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Orkas-AI%2FOrkas/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Orkas-AI","download_url":"https://codeload.github.com/Orkas-AI/Orkas/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Orkas-AI%2FOrkas/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":36143736,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-07-20T02:08:10.276Z","status":"online","status_checked_at":"2026-08-01T02:00:05.789Z","response_time":100,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["agent-collaboration","agent-orchestration","agent-team","agentic-ai","ai-agents","ai-assistant","ai-team","ai-workflow","autonomous-agents","byo-llm","cross-platform","desktop-app","electron","hermes-agent","llm","local-first","multi-agent","multi-agent-system","openclaw","self-evolving-agents"],"created_at":"2026-07-26T12:00:24.456Z","updated_at":"2026-08-01T05:00:37.113Z","avatar_url":"https://github.com/Orkas-AI.png","language":"TypeScript","funding_links":[],"categories":["Applications","Frameworks \u0026 Libraries","Multi-Agent \u0026 Orchestration","Multi-Agent Swarms","🌟 Core Frameworks","开源项目"],"sub_categories":["Multi-Agent Task Solver Projects","Multi-Agent Orchestration","Other IDEs"],"readme":"# Orkas\n\n**An open-source, local-first AI workforce for complex work.**\n\nOrkas is an open-source, local-first AI workforce. A super-powered **Commander** coordinates specialist agents to complete complex work together. It runs as a desktop app on macOS, Windows, and Linux; your conversations, files, agent configs, and model keys stay local, and model calls go straight to your provider.\n\n[![License: MIT](https://img.shields.io/badge/License-MIT-green.svg)](./LICENSE)\n[![Stars](https://img.shields.io/github/stars/Orkas-AI/Orkas?style=social)](https://github.com/Orkas-AI/Orkas/stargazers)\n[![Platform](https://img.shields.io/badge/platform-macOS%20%7C%20Windows%20%7C%20Linux-blue)](https://orkas.ai?source=gh-orkas)\n[![Download](https://img.shields.io/badge/download-orkas.ai-black)](https://orkas.ai?source=gh-orkas)\n[![Discord](https://img.shields.io/badge/Discord-Join-5865F2?logo=discord\u0026logoColor=white)](https://discord.gg/K8Eyvu7rD)\n[![X: @leochenpm](https://img.shields.io/badge/X-%40leochenpm-black?logo=x)](https://x.com/leochenpm)\n\n[English](./README.md) · [简体中文](./README.zh-CN.md)\n\n![Orkas demo](./resources/app-ui/demo.gif)\n\n\u003e One super-powered Commander turns your goal into an executable path, does the general work itself, and coordinates specialist agents when the job needs a team. No flowcharts, no orchestration code. Your conversations, files, and API keys never leave your machine.\n\n---\n\n## What is Orkas?\n\n- **Open-source, local-first AI workforce** — a desktop GUI where you direct a coordinated workforce of specialist AI agents through one chat. Not a single chatbot, not a code framework, not a hosted SaaS.\n- **A super-powered Commander** — the Commander understands context, breaks down goals, chooses the right agents, skills, connectors, and tools, and directly handles general analysis, writing, research, file work, and automation when no specialist is a better fit.\n- **Specialist agents that work together** — agents can run in parallel or in sequence, each with focused skills, memory, and task context, so complex work can move across coding, research, data, video, and slides.\n- **Open-source ecosystem, locally orchestrated** — plug in external CLI coding agents (Claude Code, Codex, OpenCode, Cline) and onboard open-source projects like HyperFrames as local tools, all coordinated by the same Commander.\n- **Local-first by design** — conversations, files, API keys, knowledge bases, and custom agents all stay on your disk. Model calls go straight from your machine to the provider — never through Orkas servers.\n- **Bring your own LLM keys** — plug in Claude, OpenAI, Gemini, DeepSeek, Kimi, GLM, Qwen, MiniMax, or Doubao. Mix providers across agents. No vendor lock-in.\n- **Self-evolving workforce** — each agent has its own private skills and memory, and improves through reflection after each task.\n\n\u003e ⭐ If Orkas is useful to you, a star helps more people find the project.\n\n---\n\n## What can you build with it?\n\n- **Automate recurring reports \u0026 market research** — a specialist agent gathers, summarizes, and ships a weekly report.\n- **Turn a product spec into dev tasks** — the Commander breaks a PRD into tasks and dispatches them across agents.\n- **Chat with your documents \u0026 run local data analysis** — drop files in, keep the data on your machine.\n- **Go beyond code — video, slides, and more** — the Commander drives open-source tools like HyperFrames and hands off to CLI coding agents (Claude Code, Codex, OpenCode, Cline) and other local agents, so one chat produces code, research, video, and slide decks.\n\n**Explore use cases →** [research workflows](https://orkas.ai/use/researchers?source=gh-orkas) · [data analysis](https://orkas.ai/use/data-analysis?source=gh-orkas) · [chat with documents](https://orkas.ai/use/chat-with-documents?source=gh-orkas) · [for developers](https://orkas.ai/use/developers?source=gh-orkas) · [automate your workspace](https://orkas.ai/use/automate-workspace?source=gh-orkas)\n\n---\n\n## Download\n\n- **Get the app** → [orkas.ai](https://orkas.ai?source=gh-orkas) (macOS · Windows installers)\n- **Run from source** → see [Quick start](#quick-start) below (currently required on Linux)\n\n---\n\n## How Orkas compares\n\n| Tool | What it is | How Orkas differs |\n| --- | --- | --- |\n| **LangChain** | A developer framework/library for building LLM apps and agents — code-first, embedded in your own Python/JS app. | Orkas is a local-first AI workforce you direct through chat, not by writing orchestration code. Data and keys stay local by default. |\n| **CrewAI** | A Python framework for orchestrating role-playing autonomous agents — you define crews and agents in code. | Orkas brings multi-agent orchestration into a desktop app, with **local-first storage** and per-agent self-evolution built in. |\n| **Cloud agent platforms** (SaaS orchestrators) | Server-hosted; conversations, files, and API keys live on the vendor's infrastructure. | Orkas is **local-first**: everything stays on your machine, and model API calls go straight to the provider — never archived by Orkas. |\n| **OpenClaw** | A single always-on personal assistant reaching you across messaging channels. | Orkas gives you a local-first AI workforce: the Commander coordinates specialist agents from one desktop chat, and OpenClaw plugs in as an Orkas CLI backend. |\n| **Hermes-Agent** | Nous Research's self-improving personal agent (TUI + multi-channel gateway). | Orkas is a desktop GUI for a local-first AI workforce, with per-agent private skills and meta-cognition — and Hermes-Agent plugs in as an Orkas CLI backend. |\n\n**Orkas is for you if** you want a local-first AI workforce (not one assistant), a desktop GUI with file drop-in and visual agent management, and your data, keys, and agents on your own disk rather than a vendor cloud.\n\n**Not for you if** you just want a single all-purpose chatbot, a fully hosted/cloud team where your data lives on a vendor's servers, or a pure code library to embed in your own app.\n\n**Full side-by-side comparisons →** [vs Claude Code](https://orkas.ai/compare/orkas-vs-claude-code?source=gh-orkas) · [vs Cline](https://orkas.ai/compare/orkas-vs-cline?source=gh-orkas) · [vs LangChain](https://orkas.ai/compare/orkas-vs-langchain?source=gh-orkas) · [vs ChatGPT](https://orkas.ai/compare/orkas-vs-chatgpt?source=gh-orkas) · [vs OpenClaw](https://orkas.ai/compare/orkas-vs-openclaw?source=gh-orkas)\n\n---\n\n## FAQ\n\n**What is Orkas?**\nOrkas is an open-source, local-first AI workforce. A super-powered Commander coordinates specialist agents to complete complex work together — not a single chatbot, not a code framework, not a hosted SaaS.\n\n**Is Orkas a local LLM?**\nNo. Orkas runs on your machine but calls the models you choose through your own API keys (or a local model endpoint). It orchestrates agents and tools — it is not itself a model.\n\n**Where are my API keys and data stored?**\nOn your disk. Conversations, files, knowledge bases, agents, and keys stay local; model calls go straight from your machine to the provider and are never proxied or archived by Orkas.\n\n**Does Orkas work offline?**\nThe app is fully offline-capable — only the model calls need network. Point agents at a local model endpoint and you can run without the cloud.\n\n**Can Orkas drive Claude Code and other CLI coding agents?**\nYes. Beyond its own Commander and specialist agents, Orkas can drive external CLI coding agents — Claude Code, Codex, OpenCode, Cline — as local subprocesses, and onboard open-source projects like HyperFrames, all directed from the same chat.\n\n**How is Orkas different from Claude Desktop / CrewAI / LangChain?**\nClaude Desktop is a single assistant; CrewAI and LangChain are code-first frameworks. Orkas is a local-first AI workforce: the Commander coordinates specialist agents, keeps data and keys local, and gives each agent its own private skills and memory. See the [full comparisons](https://orkas.ai/compare/orkas-vs-langchain?source=gh-orkas).\n\n**Is Orkas free and open source?**\nYes — MIT licensed. Bring your own model keys; you only ever pay your model providers.\n\n---\n\n## Quick start\n\nPackaged installers are currently available for macOS and Windows. Linux users should follow the source instructions below.\n\n- **macOS Apple Silicon** -\u003e [Orkas-mac-arm64.dmg](https://orkas.ai/download/?source=gh-orkas\u0026os=mac\u0026arch=arm64\u0026download=1)\n- **macOS Intel** -\u003e [Orkas-mac-x64.dmg](https://orkas.ai/download/?source=gh-orkas\u0026os=mac\u0026arch=x64\u0026download=1)\n- **Windows x64** -\u003e [Orkas-Setup.exe](https://orkas.ai/download/?source=gh-orkas\u0026os=win\u0026download=1)\n\nTo run from source:\n\n**Requirements**: Node 20+ · Python 3 · macOS / Windows 10+ / recent Linux\n\n```bash\ngit clone https://github.com/Orkas-AI/Orkas.git\ncd Orkas\n./run.sh           # macOS / Linux\nrun.cmd            # Windows\n```\n\n`run.sh` / `run.cmd` auto-installs dependencies and downloads the embedding model (~95 MB). First launch creates a workspace under `~/.orkas/` (macOS / Linux) or `\u003csmallest non-system drive\u003e:\\.orkas\\` (Windows). Then open **Settings → AI Providers** to add an API key or OAuth.\n\n---\n\n## Screenshots\n\n![Orkas home screen](./resources/app-ui/home-en.jpg)\n\n---\n\n## How it works (core design)\n\n\u003e Full design and hard constraints → [`CLAUDE.md`](./CLAUDE.md)\n\n### Group chat: visibility slicing + a single scheduling primitive\n\nIn one chat there's the Commander, N specialist agents, and you — but **each agent does not see the same conversation**.\n\n- **Visibility slicing** — the main conversation is one full jsonl; each agent only gets a slice (`from==me ∨ to∋me ∨ mentions∋me`). A worker never reads the full main conversation — saves tokens and prevents private context from leaking across agents.\n- **One scheduling primitive** — every dispatch (the Commander's `dispatch_to`, the user's `@`, plan steps) funnels into the same `enqueue` primitive. No parallel routing paths.\n- **Shared plan** — when agents collaborate, the Commander writes progress into one `plan.md`, visible to every member.\n\n### Agent dispatch: structured channels, not `@` in prose\n\n- **Structured dispatch** — Commander-to-agent dispatches go through the `dispatch_to({to, message})` tool call; `@` in prose is not treated as a dispatch signal (the user's `@` is still recognized — UX unchanged).\n- **Deferred wake-up** — a `dispatch_to` only stages; the recipient wakes only after the Commander's turn finishes, preventing premature execution.\n- **Turn-based safety stop** — the runaway guard counts turns (`MAX_WORKER_TURNS=100`), not wall-clock time, so a slow-but-progressing LLM isn't killed.\n\n### Self-evolution: `meta/` + self-managed skills\n\nEach agent maintains, in its own directory:\n\n- **`meta/COMPETENCE.md`** — what it's good / not good at.\n- **`meta/LEARNING_STRATEGIES.md`** — methods that have worked for it.\n\nAfter each task the agent reflects and updates these; on the next task `meta/` is fed back into the system prompt, so experience shapes the next run. Via the `skill_manage` tool an agent can also crystallize \"how I solved X\" into a **private** skill, reused directly next time.\n\n---\n\n## Acknowledgments\n\nSome core modules draw on these open-source projects — special thanks to:\n\n- [OpenClaw](https://github.com/openclaw/openclaw)\n- [Hermes-Agent](https://github.com/NousResearch/hermes-agent)\n\n---\n\n## License\n\n[MIT](./LICENSE)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FOrkas-AI%2FOrkas","html_url":"https://awesome.ecosyste.ms/projects/github.com%2FOrkas-AI%2FOrkas","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FOrkas-AI%2FOrkas/lists"}