Orkas：开源本地优先的桌面 AI 团队，统一协同 16 款专家 Agent 与 Claude Code、Codex
英文标题：🔥 Orkas-AI/Orkas
Orkas 是一款采用 MIT 协议开源、本地优先的多 Agent 桌面工作站应用，现已支持 macOS 与 Windows 平台。其核心架构由“Commander（指挥官）”统一协调 16 款覆盖投研、多媒体生成、UI 设计及电商运营的内置专家 Agent，并可深度整合 Claude Code、Codex、OpenCode 等本地 CLI 编程与个人助手工具。Orkas 引入项目上下文持久化、自动推进任务以及定时自动化工作流，所有数据默认留存于本地磁盘，支持切换自备商业模型 API 或本地端点。对于开发者与中小型团队而言，Orkas 展示了 AI 工作流从单次 Prompt 交互向多模型调度、长期记忆与持续自动化协作体系演进的全新范式。
26.0 KB
25.4 KB
33.0 KB
24.7 KB
55.0 KB
61.4 KB
29.0 KB
2.1 KB
638 B
1.2 KB
2.6 KB
1.3 KB
1.7 KB
1.3 KB
162.7 KB
中文
桌面端开源 AI Agent 团队——将你的目标转化为落地的完整成果，并持续推进。
Orkas 是一款开源（MIT 协议）、本地优先的多 Agent 桌面应用——一个以团队形式协作的 AI 助手。向 Commander（指挥官） 提出你的需求：它既能独立完成大量任务，也能针对更大规模的工作规划步骤，并引入专项 Agent 以及你现有的编程与个人 Agent——Claude Code、Codex、OpenCode、OpenClaw 和 Hermes-Agent——共同协同完成。
Orkas 专为持续推进项目而设计，而不仅是单次 Prompt 对答。一个 项目（Project） 承载着目标、规则、记忆和文件，因此每次新对话都能承接上次的进度。待办事项（To-dos） 将工作分派给人类和 Agent，自动推进（Auto-advance） 让团队能够自主接手下一个待办，而 定时自动化（Scheduled automations） 可按每小时、每天、每周或每月重复日常任务。你的所有数据均保留在你的电脑本地，完成的工作会提交给你复核——让你能够放心将业务的持续性工作交付给 Orkas。
⬇ 下载适用于 macOS 和 Windows 的 Orkas —— 免费提供，自带 500 个内置 Orkas 模型积分，无需 API 密钥即可直接上手。偏好使用自己的 Key？支持 Claude · OpenAI · Gemini · DeepSeek · Kimi · GLM · Qwen · MiniMax · 豆包，或本地 OpenAI 兼容端点。
- 视频、配音与图像 — VideoStudio、VoiceStudio、ImageStudio
- 研究报告、SEO 审计与市场分析 — DeepResearcher、SeoGeoAgent、StockAnalyser
- 帖子、文章、Newsletter 与演示文稿 — ContentWriter、PptMaker
- 网站、UI 与代码 — UIDesigner、ProductDeveloper
- Word、Excel、PowerPoint 与 PDF 文件 — OfficeWorker
- 电商业务 — 来自五位电商 Agent 的选品调研、商品详情页（Listings）、评价分析、销售分析与目录调整
- 需要多 Agent 协作的复杂工作 — Commander 会将其拆解，把各部分分配给合适的 Agent 并汇总结果；例如将市场调研转化为一份研究报告、一套 PPT 演示文稿和一段发布视频
16 款内置专家 Agent 随应用一同提供，每个都具备专属技能、记忆和工具。可在 Agent 市场 中浏览 30+ 款 Agent，或描述你需要的角色，Commander 会为你构建定制 Agent。
全部 16 款内置 Agent
| 领域 | Agent | 交付成果 |
|---|---|---|
| 研究与分析 | DeepResearcher | 基于事实依据的研究，包含已验证的来源、矛盾点标记以及可审计的报告 |
| SeoGeoAgent | 传入一个 URL —— 输出技术审计、内容质量、Core Web Vitals、AI 问答（GEO）可引用性及排序修复清单 | |
| StockAnalyser | 股票研究、因子筛选、回测与投资组合风险审查，配有可追溯的仪表盘 | |
| 内容与媒体 | ContentWriter | 根据目标、资料来源或粗略草稿，生成可直接发布的帖子、文章、Newsletter 与案例研究 |
| PptMaker | 根据主题、大纲或文档生成可编辑、可复查的 PPTX 幻灯片 | |
| ImageStudio | 海报、封面、社交媒体配图与信息图表 | |
| VideoStudio | 旁白、AI 数字人出镜、字幕与配音、高光剪辑、本地化翻译，以及结合自有内容和素材复刻参考视频 | |
| VoiceStudio | 旁白、多角色配音、转录与字幕、音频编辑与混音 | |
| UIDesigner | 基于产品目标、PRD、截图或 Figma 素材，生成可编辑、HTML 优先的 UI | |
| 开发与办公 | ProductDeveloper | 代码仓库感知的工程开发 —— 落实 PRD、修复 Bug、重构、审查，并具备可验证的成果 |
| OfficeWorker | 创建、编辑、检查并交付 Word / Excel / PowerPoint / PDF 文件，支持单文件或批量处理 | |
| 电子商务 | ECommerceResearcher | 按预算、市场和货源限制进行选品 —— 提供候选清单、淘汰理由与验证计划 |
| ECommerceWriter | 以符合品牌调性的口吻撰写标题、详情页、FAQ、图片文案与视频脚本 | |
| ECommerceReviewer | 评论与声誉分析 —— 挖掘客户核心诉求、差评根因及优化优先级 | |
| ECommerceAnalyzer | 基于导出的业务数据分析销售、利润、广告、退款与库存 —— 输出对齐指标与决策依据 | |
| ECommerceOperator | 规划商品目录、定价、促销与库存变动；仅通过你连接的工具执行操作 |
各 Agent 详细介绍 → orkas.ai/agents
结合自有内容复刻参考视频
VideoStudio 可以利用你自己的产品、脚本和素材，复刻爆款视频的叙事结构、视觉风格和剪辑节奏。只需提供一个参考视频文件和你的素材资产：该 Agent 会分析其吸睛 Hook、信息展开顺序、视觉节奏点和行动呼吁（CTA），然后在制作前提出保留哪些部分、替换哪些内容的建议方案。
这最适用于动态图形解说视频（Motion-graphic explainers）、SaaS 或应用 Demo，以及基于已有素材制作的产品广告。本地生成的文本、字幕、旁白和片段均可独立修改；若文本直接烘焙在 AI 生成的画面中，则需要重新生成该画面。
“以 reference.mp4 为参考制作一个 30 秒的垂直短视频宣传片。保留其 Hook 钩子、排版样式和节奏，将内容替换为我的产品和录屏，并先向我展示拆解结构和执行方案。”
请从 Agent 可读取的视频文件开始；应用未内置社交平台分享链接的下载功能。不保证能做到完全一致的镜头运镜、真人表演和逐帧对齐。详见 参考视频复刻工作流。
单次任务是一个好的开始，而 Orkas 是为持续性工作而构建的。
- 项目（Projects） — 目标与规则、记忆和文件，作为项目内每次对话的出发点，因此你永远不需要从零开始梳理需求。
- 待办事项与自动推进（To-dos and Auto-advance） — 每个项目都有一个供人类和 Agent 使用的待办列表；开启“自动推进”后，团队会自动处理下一个项目并将完成的工作提交给你复核。
- 定时自动化（Scheduled automations） — 按每小时、每天、每周或每月运行任意任务。Orkas 运行在你的本地电脑上。从 v1.9 起，当电脑唤醒或 Orkas 启动时，每个自动化任务都会在 12 小时内补跑最近一次错过的任务。
- 连接器（Connectors） — Gmail、Google Calendar、Google Sheets 和 Drive、Notion、Slack、Shopify、Stripe 等等。默认情况下，Orkas 在发送、发布或删除任何内容前都会先征得你的同意。
- 应用构建（Apps） — 描述你需要的工具，Orkas 会在桌面应用内部将其构建为本地 App。在打包版应用中，付费计划还可以将其发布为带有公开链接的 Web App。
- 共享项目（Shared projects） （打包版应用功能） — 邀请团队成员或虚拟助手（VA），并将每个待办事项分派给人类或 Agent。
说明
共享项目、云端同步以及 Web App 发布功能仅在打包版应用中提供——开源构建版本暂不支持。如需使用，请 下载适用于 macOS 和 Windows 的 Orkas（免费，自带 500 点初始积分）。
源码构建版本同样支持语音输入。在 设置 → 模型（Settings → Models） 中配置一个 Orkas API Key，然后点击输入框旁边的麦克风图标。系统提示时允许麦克风权限。音频将发送至 Orkas 进行语音识别，并消耗该 Key 拥有者的 Orkas 积分。再次点击可停止录音，复核识别文本后由你自行发送。如果访问权限被拒，请在系统设置中启用麦克风权限。
协同运行 Claude Code、Codex、OpenCode、OpenClaw 与 Hermes-Agent
Orkas 可以将你本地已安装的 CLI Agent 作为本地会话运行，与自身的专业 Agent 并肩协作——包括编程 Agent Claude Code、Codex 和 OpenCode，以及个人 Agent OpenClaw 和 Hermes-Agent。Commander 会将各 Agent 最擅长的部分分派给它们，并在所有 Agent 之间维护统一的规划，因此单次对话就能完成修复 Bug、审查代码变动并撰写 Release Note。像 HyperFrames 这样的开源工具也能以同样方式接入。
- 负责规划、委派并执行余下工作的 Commander（指挥官） — 它负责拆解目标，挑选合适的 Agent、技能、连接器和工具；在没有更合适的专家 Agent 时，它会亲自处理分析、写作、调研和文件处理工作。
- 设计即采用本地优先（Local-first） — 对话、文件、知识库和自定义 Agent 默认保存在你的本地磁盘中。云端同步在打包版中为可选功能。使用你自备的 API Key 时，模型调用会直接从你的设备发送到服务商；内置的 Orkas 模型则通过 Orkas 的托管模型服务运行。
- 任意模型，随时切换 — Commander 和内置 Agent 共享同一个模型配置：可以使用内置的 Orkas 模型、你自备的服务商 Key，或是本地端点。外部 CLI Agent 保留各自独立的模型设置。
- 自我进化的 Agent — 每个 Agent 都保留专属的私有技能和记忆。在应用空闲时，后台复盘会审查新的活动，从而优化自我评估机制、可复用方法及已习得的技能。
- 开源透明，绝无黑盒 — 采用 MIT 协议。Orkas 以及每个 Agent 和技能的具体逻辑完全透明可见。
⭐ 如果 Orkas 对你有帮助，点个 Star 能让更多人发现这个项目。
| 打包版应用（推荐） | 源码运行 |
|---|---|
| 平台支持 | macOS 12+（Apple Silicon & Intel）、Windows 10+ |
| 账户要求 | 需登录 — 免费提供 500 积分 |
| 支持模型 | 内置 Orkas 模型，或自备 Key |
| 包含特性 | 项目协作、App 发布、云端同步等 |
| 获取方式 | 下载 Orkas |
下载链接会自动检测你的操作系统并启动对应的安装程序。
- 营销内容 — 以你的品牌调性制作产品发布视频、详情页、社交贴文和 Newsletter。内容写作 · 视频制作
- 店铺运营 — 每周销售简报、评论回复、商品上架与竞品监测。电子商务
- 调研与报告 — 按需或每周生成带引用来源的报告和 PPT 演示文稿。研究调研 · 数据分析
- 与文档对话 — 基于你自有文件的问答，精确引用来源段落。文档对话
- 客户项目交付 — 按照你的模板制作会议纪要、月度客户报告与进度汇报幻灯片。月度客户报告模板
- 产品发布 — 落地页、带测试用例的 Bug 修复、更新日志（Changelog）与发布宣传贴。开发者专区
- 搭建应用 — 报价计算器、预订表单、内部工具等。构建应用
- 小型团队协同 — 人类与 Agent 共享同一个项目空间。小型团队
| 工具 | 定位 | Orkas 的差异化特点 |
|---|---|---|
| Claude Code | Anthropic 的 Agent 化编程工具 — 覆盖终端、IDE、桌面端与 Web 端，基于 Claude 模型构建。 | 并非二选一：Orkas 将 Claude Code 作为其可调度的 Agent 之一。在此基础上，Orkas 补充了一支模型中立的团队，用于承接代码之外的工作（研究、内容、视频等），并通过项目、待办列表与自动化机制持续推进项目。Orkas 与 Claude Code 对比 → |
| Codex | OpenAI 的编程 Agent — 处于终端与代码工作流中 |
English / 原文
An open-source team of AI agents on your desktop — it turns your goals into finished work and keeps it moving.
Orkas is an open-source (MIT), local-first multi-agent desktop app — an AI assistant that works as a team. Tell the Commander what you need: it finishes many tasks on its own, and for bigger work it plans the steps and brings in specialist agents along with the coding and personal agents you already use — Claude Code, Codex, OpenCode, OpenClaw and Hermes-Agent — to work on it together.
Orkas is built to keep a project moving, not just answer one prompt. A project holds the goal, rules, memory and files, so every new conversation picks up where the last one left off. To-dos split the work between people and agents, Auto-advance lets the team take on the next to-do by itself, and scheduled automations repeat routine work hourly, daily, weekly or monthly. All your data stays on your computer, and finished work comes back for your review — so you can trust Orkas with the ongoing work of your business.
⬇ Download Orkas for macOS& Windows — free, with 500 credits for the built-in Orkas model, so you don't need an API key to start. Prefer your own keys? Claude · OpenAI · Gemini · DeepSeek · Kimi · GLM · Qwen · MiniMax · Doubao, or a local OpenAI-compatible endpoint.
orkas-demo.mp4
- Videos, voice-overs and images — VideoStudio, VoiceStudio, ImageStudio
- Research reports, SEO audits and market analysis — DeepResearcher, SeoGeoAgent, StockAnalyser
- Posts, articles, newsletters and slide decks — ContentWriter, PptMaker
- Websites, UI and code — UIDesigner, ProductDeveloper
- Word, Excel, PowerPoint and PDF files — OfficeWorker
- E-commerce work — product research, listings, review analysis, sales analysis and catalog changes, from five e-commerce agents
- Complex work that takes several agents — the Commander splits it up, hands each part to the right agent and combines the results; for example, market research that becomes a report, a slide deck and a launch video
16 specialists ship with the app, each with its own skills, memory and tools. Browse 30+ agents in the agent marketplace, or describe the role you need and the Commander builds a custom agent for you.
| All 16 built-in agents Area | Agent | What it delivers |
|---|---|---|
| Research & analysis | DeepResearcher | Evidence-grounded research with verified sources, flagged contradictions and an auditable report |
| SeoGeoAgent | Give it a URL — technical audit, content quality, Core Web Vitals, AI-answer (GEO) citability, ranked fix list | |
| StockAnalyser | Equity research, factor screens, backtests and portfolio risk checks, with traceable dashboards | |
| Content & media | ContentWriter | Publish-ready posts, articles, newsletters and case studies from a goal, sources or a rough draft |
| PptMaker | Editable, reviewable PPTX decks from a topic, outline or document | |
| ImageStudio | Posters, covers, social images and infographics | |
| VideoStudio | Narration, AI presenters, captions and dubbing, highlight clips, localization, and reference-video recreation with your own content and footage | |
| VoiceStudio | Narration, multi-voice audio, transcripts and subtitles, audio editing and mixing | |
| UIDesigner | Editable, HTML-first UI from product goals, PRDs, screenshots or Figma material | |
| Build & office | ProductDeveloper | Repo-aware engineering — implement a PRD, fix bugs, refactor, review, with verifiable results |
| OfficeWorker | Create, edit, check and deliver Word / Excel / PowerPoint / PDF files, one at a time or in batches | |
| E-commerce | ECommerceResearcher | Product selection by budget, market and sourcing limits — candidates, rejection reasons, validation plans |
| ECommerceWriter | Titles, detail pages, FAQs, image copy and video scripts in your brand voice | |
| ECommerceReviewer | Review and reputation analysis — customer themes, root causes of bad reviews, priorities | |
| ECommerceAnalyzer | Sales, profit, ads, refunds and inventory from your exports — reconciled metrics and decisions | |
| ECommerceOperator | Plans catalog, price, promotion and inventory changes; executes only through tools you connect |
More on each agent → orkas.ai/agents
Recreate a reference video with your own content
VideoStudio can recreate a viral video's narrative structure, visual style and editing pace using your own product, script and footage. Supply a reference video file and your assets: the agent analyzes the hook, information order, visual beats and call to action, then proposes what to preserve and what to replace before production.
This works best for motion-graphic explainers, SaaS or app demos, and product ads built from your existing footage. Locally authored text, captions, narration and clips can be revised separately; text baked into AI-generated footage requires changing that footage.
"Use reference.mp4 as a reference for a 30-second vertical promo. Keep its hook, typography and pacing, replace the content with my product and screen recordings, and show me the breakdown and plan first."
Start with a video file the agent can read; social-platform share-link downloading is not built in. Exact camera moves, human performances and frame-by-frame matching are not guaranteed. See the reference-recreation workflow.
One task is a good start. Orkas is built for the work that keeps going.
- Projects — goals & rules, memory and files that every conversation in the project starts from, so you never brief from scratch.
- To-dos and Auto-advance — every project has a to-do list for people and agents; with Auto-advance on, the team picks up the next item on its own and brings finished work back for your review.
- Scheduled automations — run any task hourly, daily, weekly or monthly. Orkas runs on your computer. From v1.9, each automation catches up its most recent missed run within 12 hours when the computer wakes or Orkas starts.
- Connectors — Gmail, Google Calendar, Sheets and Drive, Notion, Slack, Shopify, Stripe and many more. By default, Orkas asks before it sends, posts or deletes anything.
- Apps — describe a tool and Orkas builds it as a local app inside the desktop app. In the packaged app, paid plans can also publish it as a web app with a public link.
- Shared projects (packaged app) — invite a teammate or VA, and give each to-do to a person or an agent.
Note
Shared projects, cloud sync and web-app publishing are only in the packaged app — the open-source build doesn't support them yet. To use them, download Orkas for macOS& Windows (free, with 500 credits to start).
Voice input also works in the source build. Configure an Orkas API Key in Settings → Models , then click the microphone beside a composer. Allow microphone access when prompted. Audio is sent to Orkas for recognition and uses the key owner’s Orkas credits. Click again to stop, review the text, and send it yourself. If access was denied, enable the microphone in your system settings.
Run Claude Code, Codex, OpenCode, OpenClaw and Hermes-Agent together
Orkas runs the CLI agents you already have installed as local sessions, next to its own specialists — the coding agents Claude Code, Codex and OpenCode , and the personal agents OpenClaw and Hermes-Agent. The Commander hands each one the part it's best at and keeps one plan across all of them, so a single chat can fix the bug, review the change and draft the release note. Open-source tools such as HyperFrames plug in the same way.
Using Claude Code and Codex together →
- A Commander that plans, delegates and does the rest — it breaks down goals, picks the right agents, skills, connectors and tools, and handles analysis, writing, research and file work itself when no specialist is a better fit.
- Local-first by design — conversations, files, knowledge bases and custom agents stay on your disk by default. Cloud sync is optional in the packaged app. With your own keys, model calls go straight from your machine to the provider; the built-in Orkas model runs through Orkas's managed model service.
- Any model, switch any time — the Commander and built-in agents share one model setting: the built-in Orkas model, your own provider, or a local endpoint. External CLI agents keep their own model settings.
- Agents that get better — each agent keeps private skills and memory. Background reviews examine new activity when the app is idle and can refine self-assessment, reusable methods and learned skills.
- Open source, no black box — MIT licensed. Read exactly what Orkas and every agent and skill do.
⭐ If Orkas is useful to you, a star helps more people find the project.
| Packaged app (recommended) | Run from source
---|---|---
Platforms | macOS 12+ (Apple Silicon & Intel), Windows 10+ | macOS, Windows, glibc 2.34+ Linux x64/arm64
Account | Sign in — 500 free credits | None
Models | Built-in Orkas model, or your own keys | Your own keys or a local endpoint
Also includes | Project collaboration, app publishing, cloud sync, and more | —
Get it | Download Orkas | Quick start
The download link detects your system and starts the right installer.
- Marketing content — launch videos, product pages, posts and newsletters in your voice. Content writing · Videos
- Store operations — weekly sales briefs, review replies, listings and competitor checks. E-commerce
- Research and reports — sourced reports and decks, on demand or every week. Research · Data analysis
- Chat with your documents — answers grounded in your own files, with citations back to the source passages. Chat with documents
- Client work — meeting briefs, monthly client reports and update decks in your template. Monthly client report template
- Product launch — landing pages, bug fixes with tests, changelogs and launch posts. Developers
- Build an app — quote calculators, booking forms, internal tools. Build apps
- Small teams — one project for people and agents. Small teams
| Tool | What it is | How Orkas differs |
|---|---|---|
| Claude Code | Anthropic's agentic coding tool — in the terminal, IDE, desktop and web, built on Claude models. | Not either-or: Orkas runs Claude Code as one of its agents. Around it, Orkas adds a model-agnostic team for the work beyond code — research, content, video and more — with projects, to-dos and automations that keep it moving. Orkas vs Claude Code → |
| Codex | OpenAI's coding agent — in the terminal, your editor and the cloud. | Not either-or: Orkas runs Codex as one of its agents, next to Claude Code and OpenCode. The Commander can hand the coding to Codex and the review to another agent, then cover the non-code half of a release — docs, launch posts and videos. Orkas vs Codex → |
| LangChain | A developer framework/library for building LLM apps and agents — code-first, embedded in your own Python/JS app. | Orkas is a desktop app you direct through chat, not by writing orchestration code. Data stays local by default. |
| 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 projects, to-dos, automations and per-agent self-improvement built in. |
| OpenClaw | A personal-agent platform with messaging integrations, multi-agent routing and sub-agents. | Orkas provides a desktop workspace for finished deliverables, with built-in specialists and coordination across Claude Code, Codex, OpenCode and other CLI agents. OpenClaw can join that workflow as a CLI agent. |
| Hermes-Agent | Nous Research's self-improving agent — one agent with memory and skills, available as a CLI, a messaging gateway and a desktop app. | Orkas coordinates a team: the Commander directs many specialists and other CLI agents, and Hermes-Agent plugs in as one of them. |
Orkas is for you if you want a team of agents rather than one assistant, work that keeps moving across days, and your data, keys and agents on your own disk.
Not for you if you just want a single all-purpose chatbot, or a pure code library to embed in your own app.
Choosing between coding agents? Codex vs OpenCode · Claude Code vs Codex vs OpenCode · Claude Code alternatives
Full side-by-side comparisons → vs Claude Code · vs Codex · vs Cline · vs LangChain · vs ChatGPT · vs OpenClaw · vs Hermes-Agent
Want a packaged installer instead? See Download above. To run from source — currently the way to run Orkas on Linux:
Requirements : Node 22.12+ · macOS / Windows 10+ / glibc 2.34+ Linux x64 or arm64. Keep Python 3 and a C/C++ build toolchain available for the uncommon native-module source-build fallback.
git clone https://github.com/Orkas-AI/Orkas.git
cd Orkas
./run.sh # macOS / Linux
run.cmd # Windows
Linux source runs require glibc 2.34+. Alpine and other musl-based distributions are not supported. Local speech transcription downloads and verifies the target-native whisper.cpp runtime and multilingual model during the first source launch.
run.sh / run.cmd installs the locked npm dependency tree and prepares the pinned Python, uv, Node, embedding model (~95 MB), OfficeCLI, FFmpeg, whisper.cpp, and multilingual speech model resources on first launch. Linux startup then verifies the platform-native modules and Whisper runtime under Electron's ABI before opening the app. OCR and Skill-specific Python packages are installed into isolated local environments when those features are first used. First launch creates a workspace under ~/.orkas/ (macOS / Linux) or <smallest non-system drive>:\.orkas\ (Windows). Then open Settings → AI Providers to add an API key or OAuth.
Native dependency errors: use Node.js 24 LTS (minimum 22.12.0), then run npm run native:repair from this checkout. This restores optional packages, repairs SQLite for Electron, prepares bundled Node for isolated image processing, and checks SQL, sqlite-vec and sharp before success. Use npm run native:check for a check without installation. See the native dependency verification script for the checks performed.
The Commander handles general work itself and delegates specialist work through three tools:
dispatch_toruns a named agent and returns its result for continued work. It can wait for the result or run asynchronously and notify the Commander when the task finishes.hand_off_totransfers the remaining work to a named agent and ends the current Commander turn. The agent delivers its own reply; an optional continuation lets the Commander resume a broader task afterward.run_workerruns an anonymous, isolated sub-task and returns a private result. It does not receive conversation history or a named agent's skills.
Named agent tasks and anonymous workers have separate concurrency controls. See the dispatch implementation and execution locks.
The runtime budgets context against the selected model's usable input capacity, accounting for prompts, tools and persistent runtime state. Completed dialogue uses a bounded recent-history window; long active tasks use checkpoints to condense earlier process messages while retaining recent work. File reads, file changes and command executions also have structured records that can survive context compaction.
See context budgets, session history and checkpoints and workspace records.
Durable notes keep user preferences, project facts and each agent's reusable knowledge in separate scopes. These notes are distinct from the Library's document index and the stored conversation history.
The Library extracts documents into passages and stores a local SQLite vector index. Its embedding model runs on your machine; the library tool can list files, search relevant passages and read source content from the global or current-project Library. Earlier conversations are retrieved separately through chat_history.
See scoped memory, document extraction, Library tools and conversation retrieval.
Execution limits and recovery
Session locks and concurrency limits bound parallel work. Tool-round budgets, progress checkpoints, repeated-call checks and phase-aware idle watchdogs help contain runs that stall or repeat work. Named agent tasks can be tracked and cancelled individually; an admitted or queued task is not treated as a completed result.
See actor budgets, the agent runtime and the desktop model adapter.
Background reviews examine new agent activity when the app is idle, subject to cooldowns and execution limits. A review may update an agent's self-assessment (COMPETENCE.md), reusable methods (LEARNING_STRATEGIES.md) or learned skills. Reviews depend on new activity rather than task count, and can conclude that there is nothing worth saving.
See the reflection scheduler and review prompt.
What is Orkas? Orkas is an open-source (MIT), local-first multi-agent desktop app. Its Commander turns your goal into to-dos and coordinates 16 built-in specialist agents — plus Claude Code, Codex, OpenCode, OpenClaw and Hermes-Agent — to deliver finished files. Not a single chatbot, not a code framework, not a hosted SaaS.
Do I need an API key? No. The packaged app comes with 500 credits for the built-in Orkas model. After that, buy credits, choose a paid plan or add your own provider keys; provider charges are separate.
Is Orkas a local LLM? No. Orkas runs on your machine and calls the models you choose — the built-in Orkas model, your own API keys, or a local model endpoint. It orchestrates agents and tools; it is not itself a model.
Can Orkas answer questions from my documents, with citations? Yes. Add PDFs and documents to your local Library; Orkas can search them and answer with citations to source passages, so you can open the original and check. The index is built on your machine.
Can I use local models like Ollama or LM Studio? Yes. Open Account settings → Models → Chat → Add model → Custom , select OpenAI-compatible or Anthropic-compatible , and enter the base URL, exact model ID, and API key. Choose the saved model from the task's model control.
Where are my API keys and data stored? On your disk by default. Your own provider keys are encrypted locally and excluded from cloud sync. With your own keys, model calls go straight from your machine to the provider; the built-in Orkas model uses Orkas's managed service. Optional cloud sync and shared projects in the packaged app store the selected data on Orkas servers. Security and data handling →
Does Orkas work offline? The source build can run fully offline against a local model endpoint. The packaged app needs to sign in, and cloud models need a network connection.
Does it keep working when my computer is off? No — Orkas runs on your computer, so Auto-advance and automations need the computer awake and Orkas running. From v1.9, each automation catches up its most recent missed run within 12 hours when the computer wakes or Orkas starts.
Can I build and publish apps? Yes. Local apps that run inside Orkas are free. Publishing a web app to a public link needs a paid plan (Lite 5, Pro 8, Max 15 apps), and published web apps don't include every capability available inside Orkas.
Do I need an Orkas account? The packaged desktop app asks you to sign in when you first launch it. The source build in this repository has no account layer at all — it boots straight into the app.
Can Orkas drive Claude Code and other CLI agents? Yes. Orkas can drive five external CLI agents as local subprocesses — the coding agents Claude Code, Codex and OpenCode, plus the personal agents OpenClaw and Hermes-Agent — and onboard open-source projects like HyperFrames, all directed from the same chat.
How is Orkas different from Claude Code / Codex / CrewAI / LangChain? Claude Code and Codex are coding agents — Orkas runs both as members of its team, so you don't have to choose between them; CrewAI and LangChain are code-first frameworks. Orkas is an open-source desktop app where a Commander coordinates a team of specialist agents and your CLI agents, with any model provider, and keeps data and keys local. See the full comparisons.
Which platforms does Orkas support? macOS 12+ (Apple Silicon and Intel) and Windows 10+ have packaged installers. glibc 2.34+ Linux x64/arm64 runs from source today, with no installer yet. Local speech transcription is supported on Linux through the pinned whisper.cpp runtime prepared on first launch. Alpine and other musl-based distributions are not supported. The source bootstrap needs Node 22.12+; Python 3 and a C/C++ build toolchain are needed only when a native npm package has no compatible prebuilt binary and must be rebuilt locally.
Is Orkas free and open source? Yes — the app is MIT licensed and free to use. The packaged app includes 500 credits for the built-in Orkas model; paid plans from $11.99/month add monthly credits, cloud sync, more shared projects and app publishing. With your own keys, model usage is billed by your provider; Orkas does not add a markup. Pricing →