Orkas is an open-source (MIT), local-first AI team for your desktop: a Commander turns your goal into to-dos and coordinates 16 built-in specialist agents plus Claude Code, Codex, OpenCode, OpenClaw and Hermes, with projects, scheduled automations and connectors. Free app for macOS & Windows; built-in models or your own keys.
JavaScript agent-collaborationagent-harnessagent-orchestrationagent-teamagent-workflowai-assistantai-automationai-employeeai-productivityai-teamai-workflowautonomous-agentsclaude-code-guiclaude-coworkdesktop-agentlocal-firstmulti-agentmulti-agent-systemself-evolving-agentstask-automation
docs: align README positioning
wyt1463c1ac07fa
diff --git a/README.md b/README.mdindex f96073af..24102431 100644--- a/README.md+++ b/README.md@@ -1,8 +1,8 @@# Orkas-**Command a team of AI agents from one chat — not a single chatbot.**+**An open-source, local-first AI workforce for complex work.**-Orkas is an open-source, local-first desktop app: a capable **commander agent** does the work itself and directs specialized sub-agents, all with your own LLM keys. Fully offline-capable. macOS · Windows · Linux.+Orkas 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.[](./LICENSE)[](https://github.com/Orkas-AI/Orkas/stargazers)@@ -15,18 +15,19 @@ Orkas is an open-source, local-first desktop app: a capable **commander agent**-> One capable commander agent — with the strengths of a coding agent — does the work itself and directs a team of specialized sub-agents, all by conversation. No flowcharts, no orchestration code. Your conversations, files, and API keys never leave your machine.+> 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.---## What is Orkas?-- **What it is** — a desktop GUI app where you command a *team* of specialized AI agents through one chat. Not a single chatbot, not a code framework, not a hosted SaaS.-- **A commander that does, not just delegates** — the lead agent brings coding-agent strengths (precise file edits, careful tool use, engineering discipline, multi-step and long-horizon reasoning) and does the work itself; when a job needs a team, it assembles sub-agents to run in parallel or in series.-- **Drives the open-source ecosystem** — plug in external CLI coding agents (Claude Code, Codex, OpenCode, Cline) and onboard open-source projects like HyperFrames as local tools — so one commander can deliver code, research, data, video, and slides.-- **Local-first** — 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.+- **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.+- **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.+- **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.+- **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.+- **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.- **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.-- **Self-evolving** — each agent has its own private skills and memory, and improves through reflection after each task.+- **Self-evolving workforce** — each agent has its own private skills and memory, and improves through reflection after each task.> ⭐ If Orkas is useful to you, a star helps more people find the project.@@ -34,10 +35,10 @@ Orkas is an open-source, local-first desktop app: a capable **commander agent**## What can you build with it?-- **Automate recurring reports & market research** — a sub-agent that gathers, summarizes, and ships a weekly report.-- **Turn a product spec into dev tasks** — the commander breaks a PRD into tasks and dispatches them across agents.+- **Automate recurring reports & market research** — a specialist agent gathers, summarizes, and ships a weekly report.+- **Turn a product spec into dev tasks** — the Commander breaks a PRD into tasks and dispatches them across agents.- **Chat with your documents & run local data analysis** — drop files in, keep the data on your machine.-- **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.+- **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.**Explore use cases →** [research workflows](https://orkas.ai/use/researchers?source=github) · [data analysis](https://orkas.ai/use/data-analysis?source=github) · [chat with documents](https://orkas.ai/use/chat-with-documents?source=github) · [for developers](https://orkas.ai/use/developers?source=github) · [automate your workspace](https://orkas.ai/use/automate-workspace?source=github)@@ -54,13 +55,13 @@ Orkas is an open-source, local-first desktop app: a capable **commander agent**| Tool | What it is | How Orkas differs || --- | --- | --- |-| **LangChain** | A developer framework/library for building LLM apps and agents — code-first, embedded in your own Python/JS app. | Orkas is a **no-code desktop GUI**: you assemble and command a team of agents through chat, not by writing orchestration code. Data and keys stay local by default. |-| **CrewAI** | A Python framework for orchestrating role-playing autonomous agents — you define crews and agents in code. | Orkas gives you the same multi-agent orchestration **without code**, in a desktop app, with **local-first storage** and per-agent self-evolution built in. |+| **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. |+| **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. || **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. |-| **OpenClaw** | A single always-on personal assistant reaching you across messaging channels. | Orkas builds a *team* of specialized agents directed from one desktop chat — and OpenClaw plugs in as an Orkas CLI backend. |-| **Hermes-Agent** | Nous Research's self-improving personal agent (TUI + multi-channel gateway). | Orkas is desktop-GUI and team-shaped, with per-agent private skills and meta-cognition — and Hermes-Agent plugs in as an Orkas CLI backend. |+| **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. |+| **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. |-**Orkas is for you if** you want a *team* of agents (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.+**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.**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.@@ -71,7 +72,7 @@ Orkas is an open-source, local-first desktop app: a capable **commander agent**## FAQ**What is Orkas?**-A local-first desktop app where you command a team of AI agents from one chat. A capable commander agent does the work itself and directs specialized sub-agents — not a single chatbot, not a code framework, not a hosted SaaS.+Orkas 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.**Is Orkas a local LLM?**No. 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.@@ -83,10 +84,10 @@ On your disk. Conversations, files, knowledge bases, agents, and keys stay localThe 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.**Can Orkas drive Claude Code and other CLI coding agents?**-Yes. Beyond its own commander and sub-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.+Yes. 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.**How is Orkas different from Claude Desktop / CrewAI / LangChain?**-Claude Desktop is a single assistant; CrewAI and LangChain are code-first frameworks. Orkas is a no-code desktop app that commands a *team* of 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=github).+Claude 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=github).**Is Orkas free and open source?**Yes — MIT licensed. Bring your own model keys; you only ever pay your model providers.@@ -128,16 +129,16 @@ run.cmd # Windows### Group chat: visibility slicing + a single scheduling primitive-In one chat there's a commander, N agents, and you — but **each agent does not see the same conversation**.+In one chat there's the Commander, N specialist agents, and you — but **each agent does not see the same conversation**.- **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.-- **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.-- **Shared plan** — when agents collaborate, the commander writes progress into one `plan.md`, visible to every member.+- **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.+- **Shared plan** — when agents collaborate, the Commander writes progress into one `plan.md`, visible to every member.### Agent dispatch: structured channels, not `@` in prose-- **Structured dispatch** — commander↔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).-- **Deferred wake-up** — a `dispatch_to` only stages; the recipient wakes only after the commander's turn finishes, preventing premature execution.+- **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).+- **Deferred wake-up** — a `dispatch_to` only stages; the recipient wakes only after the Commander's turn finishes, preventing premature execution.- **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.### Self-evolution: `meta/` + self-managed skillsdiff --git a/README.zh-CN.md b/README.zh-CN.mdindex 36e61c6f..39e1bbb7 100644--- a/README.zh-CN.md+++ b/README.zh-CN.md@@ -1,8 +1,8 @@# Orkas-**在一个对话里指挥一支 AI agent 团队 —— 而不是单个聊天机器人。**+**开源、本地优先的 AI 工作团队,用来协同完成复杂工作。**-Orkas 是一个开源、本地优先的桌面应用:一个能力强的**指挥官 agent** 亲自干活,并调度专精的 sub-agent,全程用你自己的大模型 key,可完全离线运行。支持 macOS · Windows · Linux。+Orkas 是一个开源、本地优先的 AI 工作团队。一个超强**指挥官**会协调多个专业智能体,共同完成复杂工作。它是运行在 macOS、Windows、Linux 上的桌面应用;你的对话、文件、智能体配置和模型 key 默认留在本机,模型调用直连你选择的服务商。[](./LICENSE)[](https://github.com/Orkas-AI/Orkas/stargazers)@@ -15,18 +15,19 @@ Orkas 是一个开源、本地优先的桌面应用:一个能力强的**指挥-> 一个能力强的指挥官 agent —— 具备 coding agent 的强项 —— 亲自完成硬核工作,并通过对话调度一支专精的 sub-agent 团队。无需流程图、无需编排代码。你的对话、文件和 API key 始终不离开本机。+> 一个超强指挥官会把你的目标转成可执行路径,亲自处理通用工作,并在任务需要团队时协调专业智能体。无需流程图、无需编排代码。你的对话、文件和 API key 始终不离开本机。---## Orkas 是什么?-- **它是什么** —— 一个桌面 GUI 应用,让你在同一个对话里指挥一支专精的 AI agent *团队*。不是单个聊天机器人,不是代码框架,也不是托管 SaaS。-- **指挥官亲自干,而不只是派活** —— 主 agent 具备 coding agent 的强项(精细的文件读写、稳健的工具操作、工程纪律、多步与长程推理),能亲自完成工作;当任务需要一支团队时,它再调度 sub-agent 并行或串行执行。-- **驱动开源生态** —— 接入外部 CLI coding agent(Claude Code、Codex、OpenCode、Cline),并把 HyperFrames 等开源项目作为本地工具接入 —— 于是一个指挥官就能产出代码、研究、数据、视频和幻灯片。-- **本地优先** —— 对话、文件、API key、知识库、自定义 agent 全部留在你的硬盘上。模型调用从你的机器直连服务商,绝不经过 Orkas 服务器。-- **自带大模型 key** —— 接入 Claude、OpenAI、Gemini、DeepSeek、Kimi、GLM、Qwen、MiniMax、Doubao,不同 agent 可混用不同服务商,无厂商锁定。-- **自我进化** —— 每个 agent 拥有自己私有的技能与记忆,并在每次任务后通过复盘自我改进。+- **开源、本地优先的 AI 工作团队** —— 一个桌面 GUI,让你在同一个对话里指挥多个协同工作的专业智能体。不是单个聊天机器人,不是代码框架,也不是托管 SaaS。+- **超强指挥官** —— 指挥官理解上下文、拆解目标、选择合适的智能体、技能、连接器和工具;当没有更合适的专家时,也能直接处理分析、写作、调研、文件处理和自动化。+- **专业智能体共同完成复杂工作** —— 智能体可以并行或串行执行,每个智能体都有自己的技能、记忆和任务上下文,复杂工作可以跨代码、研究、数据、视频和幻灯片推进。+- **本地编排开源生态** —— 接入外部 CLI 编程智能体(Claude Code、Codex、OpenCode、Cline),并把 HyperFrames 等开源项目作为本地工具接入,全部由同一个指挥官协调。+- **本地优先设计** —— 对话、文件、API key、知识库、自定义智能体全部留在你的硬盘上。模型调用从你的机器直连服务商,绝不经过 Orkas 服务器。+- **自带大模型 key** —— 接入 Claude、OpenAI、Gemini、DeepSeek、Kimi、GLM、Qwen、MiniMax、Doubao,不同智能体可混用不同服务商,无厂商锁定。+- **自我进化的工作团队** —— 每个智能体拥有自己私有的技能与记忆,并在每次任务后通过复盘自我改进。> ⭐ 如果 Orkas 对你有用,点个 star 能帮助更多人发现这个项目。@@ -34,10 +35,10 @@ Orkas 是一个开源、本地优先的桌面应用:一个能力强的**指挥## 你能用它做什么?-- **自动化周期性报告与市场调研** —— 一个 sub-agent 负责收集、汇总并产出每周报告。-- **把产品需求拆成开发任务** —— 指挥官把 PRD 拆成任务,分派给多个 agent。+- **自动化周期性报告与市场调研** —— 一个专业智能体负责收集、汇总并产出每周报告。+- **把产品需求拆成开发任务** —— 指挥官把 PRD 拆成任务,分派给多个智能体。- **与你的文档对话、做本地数据分析** —— 拖入文件,数据全程留在本机。-- **不止于代码 —— 视频、幻灯片等** —— 指挥官可驱动 HyperFrames 等开源工具,并把任务交接给 CLI coding agent(Claude Code、Codex、OpenCode、Cline)及其他本地 agent,于是一个对话就能产出代码、研究、视频与幻灯片。+- **不止于代码 —— 视频、幻灯片等** —— 指挥官可驱动 HyperFrames 等开源工具,并把任务交接给 CLI 编程智能体(Claude Code、Codex、OpenCode、Cline)及其他本地智能体,于是一个对话就能产出代码、研究、视频与幻灯片。**查看使用场景 →** [研究工作流](https://orkas.ai/use/researchers?source=github) · [数据分析](https://orkas.ai/use/data-analysis?source=github) · [与文档对话](https://orkas.ai/use/chat-with-documents?source=github) · [面向开发者](https://orkas.ai/use/developers?source=github) · [自动化你的工作区](https://orkas.ai/use/automate-workspace?source=github)@@ -54,13 +55,13 @@ Orkas 是一个开源、本地优先的桌面应用:一个能力强的**指挥| 工具 | 它是什么 | Orkas 的不同之处 || --- | --- | --- |-| **LangChain** | 面向开发者的框架/库,用于构建 LLM 应用与 agent —— 代码优先,嵌入你自己的 Python/JS 应用中。 | Orkas 是 **无代码的桌面 GUI**:通过对话组建并指挥一支 agent 团队,而不是写编排代码。数据与 key 默认留在本地。 |-| **CrewAI** | 一个 Python 框架,用于编排扮演角色的自治 agent —— 你用代码定义 crew 和 agent。 | Orkas 提供同样的多 agent 编排,但**无需写代码**,运行在桌面应用里,内置**本地优先存储**与每个 agent 的自我进化。 |-| **云端 agent 平台**(SaaS 编排器) | 服务器托管;对话、文件、API key 都存在厂商的基础设施上。 | Orkas **本地优先**:一切留在你的机器上,模型 API 调用直连服务商 —— 绝不被 Orkas 归档。 |-| **OpenClaw** | 一个常驻的单一个人助理,跨即时通讯渠道触达你。 | Orkas 在一个桌面对话里组建并指挥一支专精 agent *团队* —— 且 OpenClaw 可作为 Orkas 的 CLI 后端接入。 |-| **Hermes-Agent** | Nous Research 的自我改进个人 agent(TUI + 多渠道网关)。 | Orkas 是桌面 GUI、团队化形态,每个 agent 拥有私有技能与元认知 —— 且 Hermes-Agent 可作为 Orkas 的 CLI 后端接入。 |+| **LangChain** | 面向开发者的框架/库,用于构建 LLM 应用与智能体 —— 代码优先,嵌入你自己的 Python/JS 应用中。 | Orkas 是一个通过对话指挥的本地优先 AI 工作团队,而不是靠你写编排代码。数据与 key 默认留在本地。 |+| **CrewAI** | 一个 Python 框架,用于编排扮演角色的自治智能体 —— 你用代码定义 crew 和智能体。 | Orkas 把多智能体编排带进桌面应用,内置**本地优先存储**与每个智能体的自我进化。 |+| **云端智能体平台**(SaaS 编排器) | 服务器托管;对话、文件、API key 都存在厂商的基础设施上。 | Orkas **本地优先**:一切留在你的机器上,模型 API 调用直连服务商 —— 绝不被 Orkas 归档。 |+| **OpenClaw** | 一个常驻的单一个人助理,跨即时通讯渠道触达你。 | Orkas 提供本地优先的 AI 工作团队:指挥官在一个桌面对话里协调多个专业智能体,且 OpenClaw 可作为 Orkas 的 CLI 后端接入。 |+| **Hermes-Agent** | Nous Research 的自我改进个人智能体(TUI + 多渠道网关)。 | Orkas 是面向本地优先 AI 工作团队的桌面 GUI,每个智能体拥有私有技能与元认知 —— 且 Hermes-Agent 可作为 Orkas 的 CLI 后端接入。 |-**如果你想要的是:**一支 agent *团队*(而非单个助理)、一个支持拖入文件与可视化管理 agent 的桌面 GUI、并希望数据/key/agent 都在自己的硬盘上而非厂商云端 —— 那么 Orkas 适合你。+**如果你想要的是:**一个本地优先的 AI 工作团队(而非单个助理)、一个支持拖入文件与可视化管理智能体的桌面 GUI、并希望数据/key/智能体都在自己的硬盘上而非厂商云端 —— 那么 Orkas 适合你。**以下情况 Orkas 不适合你:**只想要一个万能单点聊天机器人、想要一个数据托管在厂商服务器上的全云端团队、或想要一个嵌入自己应用的纯代码库。@@ -71,22 +72,22 @@ Orkas 是一个开源、本地优先的桌面应用:一个能力强的**指挥## 常见问题(FAQ)**Orkas 是什么?**-一个本地优先的桌面应用,让你在一个对话里指挥一支 AI agent 团队。一个能力强的指挥官 agent 亲自干活并调度专精的 sub-agent —— 不是单个聊天机器人,不是代码框架,也不是托管 SaaS。+Orkas 是一个开源、本地优先的 AI 工作团队。一个超强指挥官会协调多个专业智能体,共同完成复杂工作 —— 不是单个聊天机器人,不是代码框架,也不是托管 SaaS。**Orkas 是本地大模型吗?**-不是。Orkas 运行在你的机器上,但通过你自己的 API key(或本地模型端点)调用你选择的模型。它编排 agent 与工具,本身不是模型。+不是。Orkas 运行在你的机器上,但通过你自己的 API key(或本地模型端点)调用你选择的模型。它编排智能体与工具,本身不是模型。**我的 API key 和数据存在哪里?**-在你的硬盘上。对话、文件、知识库、agent 和 key 都留在本地;模型调用从你的机器直连服务商,绝不被 Orkas 代理或归档。+在你的硬盘上。对话、文件、知识库、智能体和 key 都留在本地;模型调用从你的机器直连服务商,绝不被 Orkas 代理或归档。**Orkas 能离线用吗?**-应用本身可完全离线运行 —— 只有模型调用需要网络。把 agent 指向本地模型端点,就能脱离云端运行。+应用本身可完全离线运行 —— 只有模型调用需要网络。把智能体指向本地模型端点,就能脱离云端运行。-**Orkas 能驱动 Claude Code 等 CLI coding agent 吗?**-能。除了自己的指挥官与 sub-agent,Orkas 还能把外部 CLI coding agent(Claude Code、Codex、OpenCode、Cline)作为本地子进程驱动,并接入 HyperFrames 等开源项目,全部在同一个对话里指挥。+**Orkas 能驱动 Claude Code 等 CLI 编程智能体吗?**+能。除了自己的指挥官与专业智能体,Orkas 还能把外部 CLI 编程智能体(Claude Code、Codex、OpenCode、Cline)作为本地子进程驱动,并接入 HyperFrames 等开源项目,全部在同一个对话里指挥。**Orkas 和 Claude Desktop / CrewAI / LangChain 有什么不同?**-Claude Desktop 是单个助理;CrewAI 和 LangChain 是代码优先的框架。Orkas 是无代码桌面应用,指挥一支 agent *团队*,数据与 key 留在本地,每个 agent 拥有私有技能与记忆。见[逐项对比](https://orkas.ai/compare/orkas-vs-langchain?source=github)。+Claude Desktop 是单个助理;CrewAI 和 LangChain 是代码优先的框架。Orkas 是一个本地优先 AI 工作团队:指挥官协调多个专业智能体,数据与 key 留在本地,每个智能体拥有私有技能与记忆。见[逐项对比](https://orkas.ai/compare/orkas-vs-langchain?source=github)。**Orkas 免费且开源吗?**是的 —— MIT 许可证。自带模型 key,你只需为你的模型服务商付费。@@ -128,26 +129,26 @@ run.cmd # Windows### 群聊:可见性切片 + 单一调度原语-一个对话里有指挥官、N 个 agent 和你 —— 但**每个 agent 看到的对话并不相同**。+一个对话里有指挥官、N 个专业智能体和你 —— 但**每个智能体看到的对话并不相同**。-- **可见性切片** —— 主对话是一份完整 jsonl;每个 agent 只拿到属于自己的切片(`from==me ∨ to∋me ∨ mentions∋me`)。worker 永远读不到完整主对话 —— 既省 token,又防止私有上下文在 agent 间泄漏。+- **可见性切片** —— 主对话是一份完整 jsonl;每个智能体只拿到属于自己的切片(`from==me ∨ to∋me ∨ mentions∋me`)。worker 永远读不到完整主对话 —— 既省 token,又防止私有上下文在智能体间泄漏。- **单一调度原语** —— 每一次分派(指挥官的 `dispatch_to`、用户的 `@`、计划拆出的步骤)都汇入同一个 `enqueue` 原语,没有并行的路由路径。-- **共享计划** —— 多 agent 协作时,指挥官把进度写进同一份 `plan.md`,对每个成员可见。+- **共享计划** —— 多智能体协作时,指挥官把进度写进同一份 `plan.md`,对每个成员可见。-### Agent 分派:结构化通道,而非散文里的 `@`+### 智能体分派:结构化通道,而非散文里的 `@`-- **结构化分派** —— 指挥官与 agent 之间的分派必须走 `dispatch_to({to, message})` 工具调用;散文里的 `@` 不被识别为分派信号(用户的 `@` 仍按文本识别 —— 用户体验不变)。+- **结构化分派** —— 指挥官与智能体之间的分派必须走 `dispatch_to({to, message})` 工具调用;散文里的 `@` 不被识别为分派信号(用户的 `@` 仍按文本识别 —— 用户体验不变)。- **延迟唤醒** —— 一次 `dispatch_to` 只做暂存;接收方 worker 要等指挥官当前回合结束后才被唤醒,避免过早执行。- **基于回合的安全停止** —— 失控保护计的是回合数(`MAX_WORKER_TURNS=100`)而非墙钟时间,因此一个慢但在推进的 LLM 不会被误杀。### 自我进化:`meta/` + 自管理技能-每个 agent 在自己的目录里维护:+每个智能体在自己的目录里维护:- **`meta/COMPETENCE.md`** —— 我擅长什么 / 不擅长什么。- **`meta/LEARNING_STRATEGIES.md`** —— 对我有效的方法。-每次任务后 agent 复盘并更新它们;下次任务时 `meta/` 会作为系统提示的一部分回喂进去,让经验真正影响下一次运行。通过 `skill_manage` 工具,agent 还能把"我是如何解决 X 的"结晶成一个**私有**技能,下次直接复用。+每次任务后智能体复盘并更新它们;下次任务时 `meta/` 会作为系统提示的一部分回喂进去,让经验真正影响下一次运行。通过 `skill_manage` 工具,智能体还能把"我是如何解决 X 的"结晶成一个**私有**技能,下次直接复用。---