diff --git a/README.md b/README.md index 9b2e555..a936bbf 100644 --- a/README.md +++ b/README.md @@ -17,29 +17,10 @@ CrewAI is Python. LangGraph makes you draw the graph by hand. `open-multi-agent` - **Goal to result in one call.** `runTeam(team, "Build a REST API")` kicks off a coordinator agent that decomposes the goal into a task DAG, resolves dependencies, runs independent tasks in parallel, and synthesizes the final output. No graph to draw, no tasks to wire up. - **TypeScript-native, three runtime dependencies.** `@anthropic-ai/sdk`, `openai`, `zod`. That is the whole runtime. Embed in Express, Next.js, serverless functions, or CI/CD pipelines. No Python runtime, no subprocess bridge, no cloud sidecar. -- **Multi-model teams.** Claude, GPT, Gemini, Grok, MiniMax, DeepSeek, Copilot, or any OpenAI-compatible local model (Ollama, vLLM, LM Studio, llama.cpp) in the same team. Run the architect on Opus 4.6, the developer on GPT-5.4, the reviewer on local Gemma 4, all in one `runTeam()` call. Gemini ships as an optional peer dependency: `npm install @google/genai` to enable. +- **Multi-model teams.** Claude, GPT, Gemini, Grok, MiniMax, DeepSeek, Copilot, or any OpenAI-compatible local model (Ollama, vLLM, LM Studio, llama.cpp) in the same team. Run the architect on Opus 4.7, the developer on GPT-5.4, the reviewer on local Gemma 4, all in one `runTeam()` call. Gemini ships as an optional peer dependency: `npm install @google/genai` to enable. Other features (MCP integration, context strategies, structured output, task retry, human-in-the-loop, lifecycle hooks, loop detection, observability) live below the fold and in [`examples/`](./examples/). -## Philosophy: what we build, what we don't - -Our goal is to be the simplest multi-agent framework for TypeScript. Simplicity does not mean closed. We believe the long-term value of a framework is the size of the network it connects to, not its feature checklist. - -**We build:** -- A coordinator that decomposes a goal into a task DAG. -- A task queue that runs independent tasks in parallel and cascades failures to dependents. -- A shared memory and message bus so agents can see each other's output. -- Multi-model teams where each agent can use a different LLM provider. - -**We don't build:** -- **Agent handoffs.** If agent A needs to transfer mid-conversation to agent B, use [OpenAI Agents SDK](https://github.com/openai/openai-agents-python). In our model, each agent owns one task end-to-end, with no mid-conversation transfers. -- **State persistence / checkpointing.** Not planned for now. Adding a storage backend would break the three-dependency promise, and our workflows run in seconds to minutes, not hours. If real usage shifts toward long-running workflows, we will revisit. - -**Tracking:** -- **A2A protocol.** Watching, will move when production adoption is real. - -See [`DECISIONS.md`](./DECISIONS.md) for the full rationale. - ## How is this different from X? **vs. [LangGraph JS](https://github.com/langchain-ai/langgraphjs).** LangGraph is declarative graph orchestration: you define nodes, edges, and conditional routing, then `compile()` and `invoke()`. `open-multi-agent` is goal-driven: you declare a team and a goal, a coordinator decomposes it into a task DAG at runtime. LangGraph gives you total control of topology (great for fixed production workflows). This gives you less typing and faster iteration (great for exploratory multi-agent work). LangGraph also has mature checkpointing; we do not. @@ -48,15 +29,29 @@ See [`DECISIONS.md`](./DECISIONS.md) for the full rationale. **vs. [Vercel AI SDK](https://github.com/vercel/ai).** AI SDK is the LLM call layer: a unified TypeScript client for 60+ providers with streaming, tool calls, and structured outputs. It does not orchestrate multi-agent teams. `open-multi-agent` sits on top when you need that. They compose: use AI SDK for single-agent work, reach for this when you need a team. -## Used by +## Ecosystem -`open-multi-agent` is a new project (launched 2026-04-01, MIT, 5,500+ stars). The ecosystem is still forming, so the list below is short and honest: +`open-multi-agent` is a new project (launched 2026-04-01, MIT). The ecosystem is still forming, so the lists below are short and honest. + +### In production - **[temodar-agent](https://github.com/xeloxa/temodar-agent)** (~50 stars). WordPress security analysis platform by [Ali Sünbül](https://github.com/xeloxa). Uses our built-in tools (`bash`, `file_*`, `grep`) directly in its Docker runtime. Confirmed production use. - **Cybersecurity SOC (home lab).** A private setup running Qwen 2.5 + DeepSeek Coder entirely offline via Ollama, building an autonomous SOC pipeline on Wazuh + Proxmox. Early user, not yet public. Using `open-multi-agent` in production or a side project? [Open a discussion](https://github.com/JackChen-me/open-multi-agent/discussions) and we will list it here. +### Integrations (free) + +- **[Engram](https://www.engram-memory.com)** — "Git for AI memory." Syncs knowledge across agents instantly and flags conflicts. ([repo](https://github.com/Agentscreator/engram-memory)) + +Built an integration? [Open a discussion](https://github.com/JackChen-me/open-multi-agent/discussions) to get listed. + +### Featured Partner ($3,000 / year) + +12 months of prominent placement: logo, 100-word description, and a maintainer endorsement quote. For products or platforms already integrated with `open-multi-agent`. + +[Inquire about Featured Partner](https://github.com/JackChen-me/open-multi-agent/issues/new?title=Featured+Partner+Inquiry&labels=featured-partner-inquiry) + ## Quick Start Requires Node.js >= 18. @@ -77,7 +72,9 @@ Set the API key for your provider. Local models via Ollama require no API key. S - `DEEPSEEK_API_KEY` (for DeepSeek) - `GITHUB_TOKEN` (for Copilot) -**CLI (`oma`).** For shell and CI, the package exposes a JSON-first binary. See [docs/cli.md](./docs/cli.md) for `oma run`, `oma task`, `oma provider`, exit codes, and file formats. +### CLI (`oma`) + +For shell and CI, the package exposes a JSON-first binary. See [docs/cli.md](./docs/cli.md) for `oma run`, `oma task`, `oma provider`, exit codes, and file formats. Three agents, one goal. The framework handles the rest: @@ -181,16 +178,17 @@ Run scripts with `npx tsx examples/basics/team-collaboration.ts`. │ └───────────────────────┘ ┌────────▼──────────┐ │ Agent │ -│ - run() │ ┌──────────────────────┐ -│ - prompt() │───►│ LLMAdapter │ -│ - stream() │ │ - AnthropicAdapter │ -└────────┬──────────┘ │ - OpenAIAdapter │ - │ │ - CopilotAdapter │ - │ │ - GeminiAdapter │ - │ │ - GrokAdapter │ - │ │ - MiniMaxAdapter │ - │ │ - DeepSeekAdapter │ - │ └──────────────────────┘ +│ - run() │ ┌────────────────────────┐ +│ - prompt() │───►│ LLMAdapter │ +│ - stream() │ │ - AnthropicAdapter │ +└────────┬──────────┘ │ - OpenAIAdapter │ + │ │ - AzureOpenAIAdapter │ + │ │ - CopilotAdapter │ + │ │ - GeminiAdapter │ + │ │ - GrokAdapter │ + │ │ - MiniMaxAdapter │ + │ │ - DeepSeekAdapter │ + │ └────────────────────────┘ ┌────────▼──────────┐ │ AgentRunner │ ┌──────────────────────┐ │ - conversation │───►│ ToolRegistry │ @@ -379,8 +377,6 @@ Pairs well with `compressToolResults` and `maxToolOutputChars` above. Gemini requires `npm install @google/genai` (optional peer dependency). -Verified local models with tool-calling: **Gemma 4** (see [`providers/gemma4-local`](examples/providers/gemma4-local.ts)). - Any OpenAI-compatible API should work via `provider: 'openai'` + `baseURL` (Mistral, Qwen, Moonshot, Doubao, etc.). Groq is now verified in [`providers/groq`](examples/providers/groq.ts). **Grok, MiniMax, and DeepSeek now have first-class support** via `provider: 'grok'`, `provider: 'minimax'`, and `provider: 'deepseek'`. ### Local Model Tool-Calling @@ -460,16 +456,16 @@ Issues, feature requests, and PRs are welcome. Some areas where contributions wo ## Contributors - + ## Star History - - - Star History Chart + + + Star History Chart diff --git a/README_zh.md b/README_zh.md index 96580a1..8384e0f 100644 --- a/README_zh.md +++ b/README_zh.md @@ -17,26 +17,10 @@ CrewAI 是 Python。LangGraph 要你自己画图。`open-multi-agent` 是你现 - `runTeam(team, "构建一个 REST API")` 下去，协调者 agent 会把目标拆成任务 DAG，独立任务并行跑，再把结果合起来。不用画图，不用手动连依赖。 - 运行时依赖就三个：`@anthropic-ai/sdk`、`openai`、`zod`。能直接塞进 Express、Next.js、Serverless 或 CI/CD，不起 Python 进程，也不跑云端 sidecar。 -- 同一个团队里的 agent 能挂不同模型：架构师用 Opus 4.6、开发用 GPT-5.4、评审跑本地 Gemma 4 都行。支持 Claude、GPT、Gemini、Grok、MiniMax、DeepSeek、Copilot，以及 OpenAI 兼容的本地模型（Ollama、vLLM、LM Studio、llama.cpp）。用 Gemini 要额外装 `@google/genai`。 +- 同一个团队里的 agent 能挂不同模型：架构师用 Opus 4.7、开发用 GPT-5.4、评审跑本地 Gemma 4 都行。支持 Claude、GPT、Gemini、Grok、MiniMax、DeepSeek、Copilot，以及 OpenAI 兼容的本地模型（Ollama、vLLM、LM Studio、llama.cpp）。用 Gemini 要额外装 `@google/genai`。 还有 MCP、上下文策略、结构化输出、任务重试、human-in-the-loop、生命周期 hook、循环检测、可观测性等，下面章节或 [`examples/`](./examples/) 里都有。 -## 做什么，不做什么 - -**做的事：** -- 一个协调者，把目标拆成任务 DAG。 -- 一个任务队列，独立任务并行跑，失败级联到下游。 -- 共享内存和消息总线，让 agent 之间能看到彼此的输出。 -- 多模型团队，每个 agent 可以挂不同的 LLM provider。 - -**不做的事：** -- **Agent handoffs**：agent A 对话中途把控制权交给 agent B 这种模式不做。要这个用 [OpenAI Agents SDK](https://github.com/openai/openai-agents-python)。我们这边一个 agent 从头到尾负责一个任务。 -- **状态持久化 / 检查点**：暂时不做。加存储后端会破坏 3 个依赖的承诺，而且我们的工作流是秒到分钟级，不是小时级。真有长时间工作流的需求再说。 - -A2A 协议在跟踪，观望中，等有人真用再跟。 - -完整理由见 [`DECISIONS.md`](./DECISIONS.md)。 - ## 和其他框架怎么选 如果你在看 [LangGraph JS](https://github.com/langchain-ai/langgraphjs)：它是声明式图编排，自己定义节点、边、路由，`compile()` + `invoke()`。`open-multi-agent` 反过来，目标驱动：给一个团队和一个目标，协调者在运行时拆 DAG。想完全控拓扑、流程定下来的用 LangGraph；想写得少、迭代快、还在探索的选这个。LangGraph 有成熟 checkpoint，我们没做。 @@ -45,15 +29,29 @@ Python 栈直接用 [CrewAI](https://github.com/crewAIInc/crewAI) 就行，编 和 [Vercel AI SDK](https://github.com/vercel/ai) 不冲突。AI SDK 是 LLM 调用层，统一的 TypeScript 客户端，60+ provider，带流式、tool call、结构化输出，但不做多智能体编排。要多 agent，把 `open-multi-agent` 叠在 AI SDK 上面就行。单 agent 用 AI SDK，多 agent 用这个。 -## 谁在用 +## 生态 -项目 2026-04-01 发布，目前 5,500+ stars，MIT 协议。目前能确认在用的： +项目 2026-04-01 发布，MIT 协议。生态还在成型，下面的列表不长，但都是真的。 + +### 生产环境在用 - **[temodar-agent](https://github.com/xeloxa/temodar-agent)**（约 50 stars）。WordPress 安全分析平台，作者 [Ali Sünbül](https://github.com/xeloxa)。在 Docker runtime 里直接用我们的内置工具（`bash`、`file_*`、`grep`）。已确认生产环境使用。 - **家用服务器 Cybersecurity SOC。** 本地完全离线跑 Qwen 2.5 + DeepSeek Coder（通过 Ollama），在 Wazuh + Proxmox 上搭自主 SOC 流水线。早期用户，未公开。 如果你在生产或 side project 里用了 `open-multi-agent`，[请开个 Discussion](https://github.com/JackChen-me/open-multi-agent/discussions)，我加上来。 +### 集成（免费） + +- **[Engram](https://www.engram-memory.com)** — "Git for AI memory." Syncs knowledge across agents instantly and flags conflicts. ([repo](https://github.com/Agentscreator/engram-memory)) + +做了 `open-multi-agent` 集成？[开个 Discussion](https://github.com/JackChen-me/open-multi-agent/discussions)，我加上来。 + +### Featured Partner（$3,000 / 年） + +12 个月显眼位置：logo、100 字介绍、maintainer 背书 quote。面向已经集成 `open-multi-agent` 的产品或平台。 + +[咨询 Featured Partner](https://github.com/JackChen-me/open-multi-agent/issues/new?title=Featured+Partner+Inquiry&labels=featured-partner-inquiry) + ## 快速开始 需要 Node.js >= 18。 @@ -74,6 +72,8 @@ npm install @jackchen_me/open-multi-agent - `DEEPSEEK_API_KEY`（DeepSeek） - `GITHUB_TOKEN`（Copilot） +### CLI（`oma`） + 包里还自带一个叫 `oma` 的命令行工具，给 shell 和 CI 场景用，输出都是 JSON。`oma run`、`oma task`、`oma provider`、退出码、文件格式都在 [docs/cli.md](./docs/cli.md) 里。 下面用三个 agent 协作做一个 REST API： @@ -178,16 +178,17 @@ Tokens: 12847 output tokens │ └───────────────────────┘ ┌────────▼──────────┐ │ Agent │ -│ - run() │ ┌──────────────────────┐ -│ - prompt() │───►│ LLMAdapter │ -│ - stream() │ │ - AnthropicAdapter │ -└────────┬──────────┘ │ - OpenAIAdapter │ - │ │ - CopilotAdapter │ - │ │ - GeminiAdapter │ - │ │ - GrokAdapter │ - │ │ - MiniMaxAdapter │ - │ │ - DeepSeekAdapter │ - │ └──────────────────────┘ +│ - run() │ ┌────────────────────────┐ +│ - prompt() │───►│ LLMAdapter │ +│ - stream() │ │ - AnthropicAdapter │ +└────────┬──────────┘ │ - OpenAIAdapter │ + │ │ - AzureOpenAIAdapter │ + │ │ - CopilotAdapter │ + │ │ - GeminiAdapter │ + │ │ - GrokAdapter │ + │ │ - MiniMaxAdapter │ + │ │ - DeepSeekAdapter │ + │ └────────────────────────┘ ┌────────▼──────────┐ │ AgentRunner │ ┌──────────────────────┐ │ - conversation │───►│ ToolRegistry │ @@ -374,8 +375,6 @@ const agent: AgentConfig = { Gemini 需要 `npm install @google/genai`（optional peer dependency）。 -已验证支持 tool-calling 的本地模型：**Gemma 4**（见 [`providers/gemma4-local`](examples/providers/gemma4-local.ts)）。 - OpenAI 兼容的 API 都能用 `provider: 'openai'` + `baseURL` 接（Mistral、Qwen、Moonshot、Doubao 等）。Groq 在 [`providers/groq`](examples/providers/groq.ts) 里验证过。Grok、MiniMax、DeepSeek 直接用 `provider: 'grok'`、`provider: 'minimax'`、`provider: 'deepseek'`，不用配 `baseURL`。 ### 本地模型 Tool-Calling @@ -455,16 +454,16 @@ Issue、feature request、PR 都欢迎。特别想要： ## 贡献者 - + ## Star 趋势 - - - Star History Chart + + + Star History Chart diff --git a/package.json b/package.json index ae96f59..06b4631 100644 --- a/package.json +++ b/package.json @@ -48,6 +48,14 @@ ], "author": "", "license": "MIT", + "repository": { + "type": "git", + "url": "git+https://github.com/JackChen-me/open-multi-agent.git" + }, + "homepage": "https://github.com/JackChen-me/open-multi-agent#readme", + "bugs": { + "url": "https://github.com/JackChen-me/open-multi-agent/issues" + }, "engines": { "node": ">=18.0.0" },