[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"pack-detail-multi-agent-frameworks-en":3,"seo:pack:multi-agent-frameworks:en":77},{"code":4,"message":5,"data":6},200,"操作成功",{"pack":7},{"slug":8,"icon":9,"tone":10,"status":11,"status_label":12,"title":13,"description":14,"items":15,"install_cmd":76},"multi-agent-frameworks","🤝","#F43F5E","stable","Stable","Multi-Agent Frameworks","CAMEL, LangGraph, DeepAgents, GPT Researcher — frameworks for orchestrating teams of agents in production.",[16,28,35,42,50,60,68],{"id":17,"uuid":18,"slug":19,"title":20,"description":21,"author_name":22,"view_count":23,"vote_count":24,"lang_type":25,"type":26,"type_label":27},295,"23732313-ea97-4319-b7a5-19dcddd7e97c","camel-multi-agent-framework-scale-23732313","CAMEL — Multi-Agent Framework at Scale","CAMEL is a multi-agent framework for studying scaling laws of AI agents. 16.6K+ GitHub stars. Up to 1M agents, RAG, memory systems, data generation. Apache 2.0.","Script Depot",628,0,"en","skill","Skill",{"id":4,"uuid":29,"slug":30,"title":31,"description":32,"author_name":33,"view_count":34,"vote_count":24,"lang_type":25,"type":26,"type_label":27},"cc1a6ed2-0d82-4379-94f4-15632b4d4967","langgraph-build-stateful-ai-agents-graphs-cc1a6ed2","LangGraph — Build Stateful AI Agents as Graphs","LangChain framework for building resilient, stateful AI agents as graphs. Supports cycles, branching, persistence, human-in-the-loop, and streaming. 28K+ stars.","LangChain",566,{"id":36,"uuid":37,"slug":38,"title":39,"description":40,"author_name":33,"view_count":41,"vote_count":24,"lang_type":25,"type":26,"type_label":27},601,"ac820f80-41ff-4eaa-b3b1-da27653bd7a5","deepagents-multi-step-agent-framework-langchain-ac820f80","DeepAgents — Multi-Step Agent Framework by LangChain","Agent harness built on LangGraph by the LangChain team. Features planning tools, filesystem backend, and sub-agent spawning for complex multi-step tasks like codebase refactoring. 16,500+ stars.",431,{"id":43,"uuid":44,"slug":45,"title":46,"description":47,"author_name":48,"view_count":49,"vote_count":24,"lang_type":25,"type":26,"type_label":27},25,"23330210-b26a-4d97-ad97-1735c203eaa6","gpt-researcher-autonomous-research-report-agent-23330210","GPT Researcher — Autonomous Research Report Agent","AI agent that generates detailed research reports from a single query. Searches multiple sources, synthesizes findings, and cites references.","TokRepo精选",1759,{"id":51,"uuid":52,"slug":53,"title":54,"description":55,"author_name":56,"view_count":57,"vote_count":24,"lang_type":25,"type":58,"type_label":59},719,"dedbb70b-7ebd-4987-9ba3-a883f45e8b5a","goose-ai-developer-agent-block-dedbb70b","Goose — AI Developer Agent by Block","Open-source AI developer agent by Block (Square). Goose automates coding tasks with extensible toolkits, session memory, and MCP server support in your terminal.","Block",406,"script","Script",{"id":61,"uuid":62,"slug":63,"title":64,"description":65,"author_name":66,"view_count":67,"vote_count":24,"lang_type":25,"type":26,"type_label":27},2221,"34ff4f3b-1660-4953-9053-7b3fac036c17","claude-flow-multi-agent-orchestration-claude-code-34ff4f3b","Claude-Flow — Multi-Agent Orchestration for Claude Code","Layers swarm and hive-mind multi-agent orchestration on top of Claude Code with 64 specialized agents, SQLite memory, and parallel execution.","Skill Factory",405,{"id":69,"uuid":70,"slug":71,"title":72,"description":73,"author_name":74,"view_count":75,"vote_count":24,"lang_type":25,"type":58,"type_label":59},683,"38035d0b-f942-4bf2-bbad-be9d4f719c00","openai-agents-sdk-build-multi-agent-systems-python-38035d0b","OpenAI Agents SDK — Build Multi-Agent Systems in Python","Official OpenAI Python SDK for building multi-agent systems with handoffs, guardrails, and tracing. Agents delegate to specialists, enforce safety rules, and produce observable traces. 8,000+ stars.","OpenAI",263,"tokrepo install pack\u002Fmulti-agent-frameworks",{"pageType":78,"pageKey":8,"locale":25,"title":79,"metaDescription":80,"h1":13,"tldr":81,"bodyMarkdown":82,"faq":83,"schema":99,"internalLinks":107,"citations":120,"wordCount":133,"generatedAt":134},"pack","Multi-Agent Frameworks: CAMEL, LangGraph, DeepAgents picks","CAMEL, LangGraph, DeepAgents, GPT Researcher — the seven multi-agent orchestration frameworks teams ship in 2026. Install in one TokRepo command.","Seven multi-agent orchestration frameworks — CAMEL, LangGraph, DeepAgents, GPT Researcher, plus three role-play and research starters — that survive production. One-command install via TokRepo.","## What's in this pack\n\nThis pack collects the **seven multi-agent frameworks** that teams actually ship to production in 2026, not the demos that look good on Twitter and explode under load. Four are headline frameworks, three are research\u002Frole-play templates that wrap them.\n\n| # | Asset | Type | Best for |\n|---|---|---|---|\n| 1 | LangGraph | stateful framework | Production graph orchestration with checkpointing |\n| 2 | CAMEL | role-play framework | Agent-to-agent dialogue, academic-grade |\n| 3 | DeepAgents | research framework | Long-running planning + sub-agent spawning |\n| 4 | GPT Researcher | applied agent | Topic in, research report out |\n| 5 | Researcher swarm | template | CAMEL roles for parallel research |\n| 6 | Critic-actor pair | template | One agent acts, one critiques — error correction |\n| 7 | Hierarchical planner | template | Manager-spawns-workers pattern with budget |\n\n## Why this pack matters\n\nA single agent is a chat loop. Multi-agent is a system — and like every system, it needs structure (state machines, queues, retries) before it survives a real workload. The four frameworks here picked the structures that work. The three templates show you how to wire them together for the most common use cases.\n\nThe frameworks each pick a different abstraction:\n\n- **LangGraph** treats orchestration as a state graph. You declare nodes (agents\u002Ftools) and edges (when to transition), and LangGraph handles checkpointing so a 30-minute run can resume after a crash. The closest thing to a default standard for production.\n- **CAMEL** focuses on agent-to-agent dialogue with explicit roles. Two agents play \"user\" and \"assistant\" or \"research lead\" and \"writer\" and converse until a goal is met. Strong on reproducibility and academic benchmarks.\n- **DeepAgents** is built for long-horizon tasks. The top agent plans, delegates sub-tasks to spawned sub-agents, each with their own context window. Designed to avoid the \"one giant context\" failure mode.\n- **GPT Researcher** is the applied case study. You give it a research question, it runs a sub-agent swarm to gather evidence and produces a long-form report with citations. Useful as both a tool and a reference architecture.\n\n## Install in one command\n\n```bash\n# Install the entire pack\ntokrepo install pack\u002Fmulti-agent-frameworks\n\n# Or install one at a time\ntokrepo install langgraph\ntokrepo install camel\ntokrepo install deepagents\ntokrepo install gpt-researcher\n```\n\nThe TokRepo CLI installs each framework's adapter into your AI tool — Claude Code subagents into `.claude\u002Fagents\u002F`, Cursor rules into `.cursor\u002Frules\u002F`, AGENTS.md entries for Codex CLI. Run pip \u002F npm for the underlying libraries; TokRepo wires the prompts so your CLI knows when to invoke them.\n\n## Common pitfalls\n\n- **Don't skip the budget.** Multi-agent runs can fan out exponentially — one planner spawning five workers each spawning five sub-tasks burns 25× the tokens. Always cap depth and max-spawn count. DeepAgents bakes this in; with LangGraph and CAMEL you set it yourself.\n- **Don't share an LLM client across threads naively.** Most SDKs aren't fully thread-safe under high concurrency. Use process-level pools or async with bounded concurrency (e.g. asyncio.Semaphore(8)).\n- **Trace everything.** Multi-agent debugging without traces is impossible. Pair this pack with the LLM Observability pack — Langfuse and AgentOps both have first-class LangGraph integrations.\n- **Beware role drift.** In CAMEL-style dialogue, agents sometimes forget who they are around turn 8-10. Add a system reminder every N turns or pin the role in every message.\n- **Multi-agent ≠ better.** Try a single Claude Sonnet 4.5 with extended thinking before reaching for a multi-agent system. The 2025 Anthropic blog post on multi-agent research found that 60% of tasks people throw at multi-agent setups would do fine with one agent + tools.\n\n## When this pack alone isn't enough\n\nMulti-agent shines on tasks with parallelizable subproblems (research, code review, content generation across topics). It loses on:\n\n- **Sequential, deeply-stateful tasks.** Refactoring a codebase end-to-end is one agent's job — splitting it across multiple agents creates more coordination overhead than it saves.\n- **Latency-sensitive workflows.** Each hop between agents adds a round-trip. If you're under a 5-second SLA, stay single-agent.\n- **Cost-sensitive workflows.** A multi-agent run typically costs 3-10× a single-agent run for the same task. Worth it for quality on hard problems; not worth it for \"summarize this email.\"\n\nThe right way to adopt this pack: start with GPT Researcher as the simplest finished example, then graduate to LangGraph or DeepAgents when you need to write your own orchestration.",[84,87,90,93,96],{"q":85,"a":86},"Is LangGraph free?","Yes, LangGraph is open-source under MIT and you only pay for the LLM tokens. There's a paid LangGraph Cloud for managed deployment with checkpointing and traces, but the OSS library is fully featured. CAMEL, DeepAgents, and GPT Researcher are also OSS — no paid tier is required to ship.",{"q":88,"a":89},"Does this work with Cursor or Codex CLI?","The frameworks are language-level Python libraries, not Claude Code-specific. Any agent CLI that runs Python tools can drive them. The TokRepo CLI installs the right wiring for your tool — for Codex CLI it ships AGENTS.md instructions explaining when to invoke the framework, for Cursor it adds rules. The underlying Python install is unchanged.",{"q":91,"a":92},"How does LangGraph compare to CAMEL?","LangGraph is structure-first: you draw a state machine and the agents fit into it. CAMEL is dialogue-first: you assign roles and let agents converse. LangGraph wins for production reliability and checkpointing; CAMEL wins for research, simulations, and any case where the conversation itself is the artifact. Many production setups use LangGraph for orchestration and call CAMEL for specific dialogue tasks.",{"q":94,"a":95},"What's the difference vs the Memory Layer pack?","Memory is about *what an agent remembers between sessions*. Multi-agent is about *how multiple agents coordinate within one task*. They're orthogonal: a multi-agent system often needs a shared memory layer (Mem0\u002FZep) so the workers don't have to re-discover facts the planner already knew. We recommend installing both packs if you're building anything serious.",{"q":97,"a":98},"When should I NOT use a multi-agent framework?","When the task is sequential and stateful (refactor this file), latency-sensitive (chat UIs under 3s), or simple enough for one Claude\u002FGPT call. Anthropic's own multi-agent research blog notes that single-agent + extended thinking beats most multi-agent setups on cost. Reach for multi-agent when the task naturally parallelizes (research many sources) or requires distinct expert roles.",{"@context":100,"@type":101,"name":13,"description":14,"numberOfItems":102,"publisher":103},"https:\u002F\u002Fschema.org","CollectionPage",7,{"@type":104,"name":105,"url":106},"Organization","TokRepo","https:\u002F\u002Ftokrepo.com",[108,112,116],{"url":109,"anchor":110,"reason":111},"\u002Fen\u002Fpacks\u002Fagent-memory-layer","Memory Layer for Agents","shared memory across agents in a swarm",{"url":113,"anchor":114,"reason":115},"\u002Fen\u002Fpacks\u002Fllm-observability","LLM Observability","trace multi-agent runs to find bottlenecks",{"url":117,"anchor":118,"reason":119},"\u002Fen\u002Ftools\u002Fclaude-code","Claude Code","common host that orchestrates these frameworks",[121,125,129],{"claim":122,"source_name":123,"source_url":124},"LangGraph is the official stateful orchestration library from the LangChain team","langchain-ai\u002Flanggraph on GitHub","https:\u002F\u002Fgithub.com\u002Flangchain-ai\u002Flanggraph",{"claim":126,"source_name":127,"source_url":128},"CAMEL is one of the earliest multi-agent role-playing frameworks, with active research output","camel-ai\u002Fcamel on GitHub","https:\u002F\u002Fgithub.com\u002Fcamel-ai\u002Fcamel",{"claim":130,"source_name":131,"source_url":132},"GPT Researcher autonomously runs research tasks and produces long-form reports","assafelovic\u002Fgpt-researcher on GitHub","https:\u002F\u002Fgithub.com\u002Fassafelovic\u002Fgpt-researcher",741,"2026-05-02T15:00:00Z"]