[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"workflow-camel-multi-agent-and-tooling-library-716fc1ad":3,"seo:featured-workflow:716fc1ad-c3a2-49ab-a810-3a139949e377:fr":38,"workflow-related-camel-multi-agent-and-tooling-library-716fc1ad-716fc1ad-c3a2-49ab-a810-3a139949e377":83},{"id":4,"uuid":5,"slug":6,"title":7,"description":8,"author_id":9,"author_name":10,"author_avatar":11,"token_estimate":12,"time_saved":12,"model_used":13,"fork_count":12,"vote_count":12,"view_count":14,"parent_id":12,"parent_uuid":13,"lang_type":15,"steps":16,"tags":23,"has_voted":29,"visibility":19,"share_token":13,"is_featured":12,"content_hash":30,"asset_kind":27,"target_tools":31,"install_mode":35,"entrypoint":36,"risk_profile":37,"dependencies":39,"verification":46,"agent_metadata":49,"agent_fit":60,"trust":71,"provenance":79,"created_at":81,"updated_at":82},3092,"716fc1ad-c3a2-49ab-a810-3a139949e377","camel-multi-agent-and-tooling-library","CAMEL — Multi-Agent and Tooling Library","CAMEL is an open-source library for multi-agent systems and tools. Install `camel-ai`, then compose agents, tools, and optional web helpers in Python.","8a910fec-3180-11f1-9bc6-00163e2b0d79","Agent Toolkit","https:\u002F\u002Ftokrepo.com\u002Fapple-touch-icon.png",0,"",12,"en",[17],{"id":18,"step_order":19,"title":20,"description":13,"prompt_template":21,"variables":13,"depends_on":22,"expected_output":13},3655,1,"Asset","# CAMEL — Multi-Agent and Tooling Library\n\n> CAMEL is an open-source library for multi-agent systems and tools. Install `camel-ai`, then compose agents, tools, and optional web helpers in Python.\n\n## Quick Use\n\n1. Install:\n   ```bash\n   pip install camel-ai\n   ```\n2. Run:\n   ```bash\n   python -c \"import camel; print('camel-ai import ok')\"\n   ```\n3. Verify:\n   - Follow one README example end-to-end and confirm the agent\u002Ftool pipeline runs without manual parsing\n\n\n---\n\n## Intro\n\nCAMEL is an open-source library for multi-agent systems and tools. Install `camel-ai`, then compose agents, tools, and optional web helpers in Python.\n\n- **Best for:** Python teams exploring multi-agent patterns who want a batteries-included library with tools, examples, and extensible building blocks\n- **Works with:** Python, `pip install camel-ai`, optional extras like `camel-ai[web_tools]` (repo), agent composition and tools\n- **Setup time:** 13 minutes\n\n\n### Quantitative Notes\n\n- Install: `pip install camel-ai` (repo)\n- Optional tools extra: `pip install 'camel-ai[web_tools]'` (repo)\n- Setup time ~13 minutes\n\n\n---\n\n## Practical Notes\n\nUse CAMEL when you need a practical playground for multi-agent patterns: role-based collaboration, tool augmentation, and reusable components. Start small: one agent + one tool + one success metric. Once the loop is stable, add a second agent for critique\u002Fverification. In production, keep tool interfaces strict and log everything needed to reproduce failures.\n\n**Safety note:** Multi-agent systems amplify mistakes—use verification agents and strict tool schemas to limit blast radius.\n\n### FAQ\n\n**Q: Is CAMEL an agent framework or a toolbox?**\nA: Both. It provides agent primitives and a growing set of tools\u002Fintegrations with examples to compose systems.\n\n**Q: Do I need all extras?**\nA: No. Start with the base install and add extras (like web tools) only when your workflow needs them.\n\n**Q: How do I keep runs deterministic?**\nA: Fix models and temperatures, log prompts\u002Foutputs, and wrap tool calls with explicit schemas and validators.\n\n---\n\n## Source & Thanks\n\n> GitHub: https:\u002F\u002Fgithub.com\u002Fcamel-ai\u002Fcamel\n> Owner avatar: https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F134388954?v=4\n> License (SPDX): Apache-2.0\n> GitHub stars (verified via `api.github.com\u002Frepos\u002Fcamel-ai\u002Fcamel`): 16,917\n\n\n---\n\n\u003C!-- ZH -->\n\n# CAMEL——多 Agent 与工具调用 Python 库\n\n> CAMEL 是开源的多 Agent 与工具调用库，提供丰富的 agent 组合与工具集成。安装 `camel-ai`（可选 extras）后，即可在 Python 中搭建多 agent 协作与 web 工具能力。\n\n## 快速使用\n\n1. 安装：\n   ```bash\n   pip install camel-ai\n   ```\n2. 运行：\n   ```bash\n   python -c \"import camel; print('camel-ai import ok')\"\n   ```\n3. 验证：\n   - Follow one README example end-to-end and confirm the agent\u002Ftool pipeline runs without manual parsing\n\n\n---\n\n## 简介\n\nCAMEL 是开源的多 Agent 与工具调用库，提供丰富的 agent 组合与工具集成。安装 `camel-ai`（可选 extras）后，即可在 Python 中搭建多 agent 协作与 web 工具能力。\n\n- **适合谁（Best for）:** 在探索多 agent 模式的 Python 团队，希望用一个“电池齐全”的库快速试验并可扩展落地\n- **兼容工具（Works with）:** Python、`pip install camel-ai`、可选 extras（如 `camel-ai[web_tools]`，仓库）、agent 组合与工具能力\n- **安装时间（Setup time）:** 13 分钟\n\n\n### 量化信息\n\n- 安装：`pip install camel-ai`（仓库）\n- 工具扩展：`pip install 'camel-ai[web_tools]'`（仓库）\n- 装机约 13 分钟\n\n\n---\n\n## 实战要点\n\n当你想要一个可落地的多 agent 试验场时，CAMEL 很合适：角色协作、工具增强、可复用组件都在一个库里。先从小闭环开始：一个 agent + 一个工具 + 一个成功指标；闭环稳定后再加第二个 agent 做复核\u002F验证。上生产要把工具接口收紧，并记录复现失败所需的全部信息。\n\n**安全提示：** 多 agent 会放大错误影响——用验证\u002F复核 agent + 严格工具 schema 控制爆炸半径。\n\n### FAQ\n\n**Q: CAMEL 是框架还是工具箱？**\nA: 两者都有：既提供 agent 原语，也提供不断扩展的工具\u002F集成与示例，便于组合系统。\n\n**Q: 需要装所有 extras 吗？**\nA: 不需要。先装基础包，等工作流确实需要再加 extras（例如 web 工具）。\n\n**Q: 怎样让运行更可复现？**\nA: 固定模型与 temperature，记录 prompt\u002F输出，并给工具调用加明确 schema 与校验器。\n\n---\n\n## 来源与感谢\n\n> GitHub：https:\u002F\u002Fgithub.com\u002Fcamel-ai\u002Fcamel\n> Owner avatar：https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F134388954?v=4\n> 许可证（SPDX）：Apache-2.0\n> GitHub stars（已通过 `api.github.com\u002Frepos\u002Fcamel-ai\u002Fcamel` 核验）：16,917\n","0",[24],{"id":25,"name":26,"slug":27,"icon":28},11,"Scripts","script","📜",false,"2ae2e394f3bd44a57e5a584e37559971070e88eeeae1ac417ff1fbc99d713945",[32,33,34],"claude_code","codex","gemini_cli","single","README.md",{"executes_code":29,"modifies_global_config":29,"requires_secrets":38,"uses_absolute_paths":29,"network_access":29},null,{"npm":40,"pip":41,"brew":44,"system":45},[],[42,43],"camel-ai","camel-ai[web_tools]",[],[],{"commands":47,"expected_files":48},[],[20],{"asset_kind":27,"target_tools":50,"install_mode":35,"entrypoint":36,"risk_profile":51,"dependencies":52,"content_hash":30,"verification":57},[32,33,34],{"executes_code":29,"modifies_global_config":29,"requires_secrets":38,"uses_absolute_paths":29,"network_access":29},{"npm":53,"pip":54,"brew":55,"system":56},[],[42,43],[],[],{"commands":58,"expected_files":59},[],[20],{"target":33,"score":61,"status":62,"policy":62,"why":63,"asset_kind":27,"install_mode":35},29,"stage_only",[64,65,66,67,68,69,70],"target_tools includes codex","asset_kind script","install_mode single","markdown-only","policy stage_only","asset_kind script is not activated directly for Codex","trust established",{"author_trust_level":72,"verified_publisher":29,"asset_signed_hash":30,"signature_status":73,"install_count":12,"report_count":12,"dangerous_capability_badges":74,"review_status":75,"signals":76},"established","hash_only",[27],"unreviewed",[77,78],"author has published assets","content hash available",{"owner_uuid":9,"owner_name":10,"source_url":80,"content_hash":30,"visibility":19,"created_at":81,"updated_at":82},"https:\u002F\u002Ftokrepo.com\u002Fen\u002Fworkflows\u002Fcamel-multi-agent-and-tooling-library","2026-05-12 00:58:31","2026-05-14 00:43:43",[84,151,196,240],{"id":85,"uuid":86,"slug":87,"title":88,"description":89,"author_id":90,"author_name":91,"author_avatar":11,"token_estimate":92,"time_saved":12,"model_used":93,"fork_count":12,"vote_count":12,"view_count":94,"parent_id":12,"parent_uuid":13,"lang_type":15,"steps":95,"tags":96,"has_voted":29,"visibility":19,"share_token":13,"is_featured":19,"content_hash":98,"asset_kind":99,"target_tools":100,"install_mode":35,"entrypoint":88,"risk_profile":103,"dependencies":105,"verification":110,"agent_metadata":113,"agent_fit":125,"trust":133,"provenance":141,"created_at":143,"updated_at":144,"__relatedScore":145,"__relatedReasons":146,"__sharedTags":149},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.","8a910e34-3180-11f1-9bc6-00163e2b0d79","Script Depot",500,"Claude Code",342,[],[97],{"id":25,"name":26,"slug":27,"icon":28},"ef6e6cd6d0c7d6fa8598295657ad11912310168f7abe9413fd39e255835fa1d1","skill",[32,33,101,34,102],"cursor","windsurf",{"executes_code":29,"modifies_global_config":29,"requires_secrets":104,"uses_absolute_paths":29,"network_access":29},[],{"npm":106,"pip":107,"brew":108,"system":109},[],[],[],[],{"commands":111,"expected_files":112},[],[88],{"asset_kind":99,"target_tools":114,"install_mode":35,"entrypoint":88,"risk_profile":115,"dependencies":117,"content_hash":98,"verification":122},[32,33,101,34,102],{"executes_code":29,"modifies_global_config":29,"requires_secrets":116,"uses_absolute_paths":29,"network_access":29},[],{"npm":118,"pip":119,"brew":120,"system":121},[],[],[],[],{"commands":123,"expected_files":124},[],[88],{"target":33,"score":126,"status":127,"policy":128,"why":129,"asset_kind":99,"install_mode":35},98,"native","allow",[64,130,66,67,131,132,70],"asset_kind skill","policy allow","safe markdown-only Codex install",{"author_trust_level":72,"verified_publisher":29,"asset_signed_hash":98,"signature_status":73,"last_reviewed_at":134,"install_count":12,"report_count":12,"dangerous_capability_badges":135,"review_status":136,"signals":137},"2026-05-14T01:22:06+08:00",[],"reviewed",[138,77,78,139,140],"asset has usage views","featured asset","no dangerous capability badges",{"owner_uuid":90,"owner_name":91,"source_url":142,"content_hash":98,"visibility":19,"created_at":143,"updated_at":144},"https:\u002F\u002Ftokrepo.com\u002Fen\u002Fworkflows\u002Fcamel-multi-agent-framework-scale-23732313","2026-04-01 07:13:47","2026-05-14 01:22:06",107.80294118006415,[147,148],"topic-match","same-target",[27,150],"scripts",{"id":152,"uuid":153,"slug":154,"title":155,"description":156,"author_id":9,"author_name":10,"author_avatar":11,"token_estimate":12,"time_saved":12,"model_used":13,"fork_count":12,"vote_count":12,"view_count":14,"parent_id":12,"parent_uuid":13,"lang_type":15,"steps":157,"tags":158,"has_voted":29,"visibility":19,"share_token":13,"is_featured":12,"content_hash":160,"asset_kind":27,"target_tools":161,"install_mode":35,"entrypoint":36,"risk_profile":162,"dependencies":163,"verification":168,"agent_metadata":171,"agent_fit":182,"trust":184,"provenance":187,"created_at":189,"updated_at":190,"__relatedScore":191,"__relatedReasons":192,"__sharedTags":195},3137,"02e02d27-cc74-447b-a7cf-587d5fa638cd","open-multi-agent-task-dag-orchestration-with-mcp","open-multi-agent — Task DAG Orchestration with MCP","open-multi-agent turns a goal into a task DAG and orchestrates multiple agents in TypeScript, with MCP support and runnable example scripts.",[],[159],{"id":25,"name":26,"slug":27,"icon":28},"e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855",[32,33,34],{"executes_code":29,"modifies_global_config":29,"requires_secrets":38,"uses_absolute_paths":29,"network_access":29},{"npm":164,"pip":165,"brew":166,"system":167},[],[],[],[],{"commands":169,"expected_files":170},[],[],{"asset_kind":27,"target_tools":172,"install_mode":35,"entrypoint":36,"risk_profile":173,"dependencies":174,"content_hash":160,"verification":179},[32,33,34],{"executes_code":29,"modifies_global_config":29,"requires_secrets":38,"uses_absolute_paths":29,"network_access":29},{"npm":175,"pip":176,"brew":177,"system":178},[],[],[],[],{"commands":180,"expected_files":181},[],[],{"target":33,"score":61,"status":62,"policy":62,"why":183,"asset_kind":27,"install_mode":35},[64,65,66,67,68,69,70],{"author_trust_level":72,"verified_publisher":29,"asset_signed_hash":160,"signature_status":73,"install_count":12,"report_count":12,"dangerous_capability_badges":185,"review_status":75,"signals":186},[27],[77,78],{"owner_uuid":9,"owner_name":10,"source_url":188,"content_hash":160,"visibility":19,"created_at":189,"updated_at":190},"https:\u002F\u002Ftokrepo.com\u002Fen\u002Fworkflows\u002Fopen-multi-agent-task-dag-orchestration-with-mcp","2026-05-12 04:56:51","2026-05-14 00:41:53",107.67091502846026,[147,193,148,194],"same-kind","same-author",[27,150],{"id":197,"uuid":198,"slug":199,"title":200,"description":201,"author_id":9,"author_name":10,"author_avatar":11,"token_estimate":12,"time_saved":12,"model_used":13,"fork_count":12,"vote_count":12,"view_count":202,"parent_id":12,"parent_uuid":13,"lang_type":15,"steps":203,"tags":204,"has_voted":29,"visibility":19,"share_token":13,"is_featured":12,"content_hash":160,"asset_kind":27,"target_tools":206,"install_mode":35,"entrypoint":207,"risk_profile":208,"dependencies":209,"verification":214,"agent_metadata":217,"agent_fit":228,"trust":230,"provenance":233,"created_at":235,"updated_at":236,"__relatedScore":237,"__relatedReasons":238,"__sharedTags":239},3277,"79c28341-ca9a-585d-b8cf-b183829b6d9d","hive-framework-outcome-driven-multi-agent-harness","Hive Framework — Outcome-Driven Multi-Agent Harness","Hive Framework turns natural-language goals into generated agent graphs and dashboards, giving teams a production-minded multi-agent harness.",13,[],[205],{"id":25,"name":26,"slug":27,"icon":28},[32,33,34],"quickstart.sh",{"executes_code":29,"modifies_global_config":29,"requires_secrets":38,"uses_absolute_paths":29,"network_access":29},{"npm":210,"pip":211,"brew":212,"system":213},[],[],[],[],{"commands":215,"expected_files":216},[],[],{"asset_kind":27,"target_tools":218,"install_mode":35,"entrypoint":207,"risk_profile":219,"dependencies":220,"content_hash":160,"verification":225},[32,33,34],{"executes_code":29,"modifies_global_config":29,"requires_secrets":38,"uses_absolute_paths":29,"network_access":29},{"npm":221,"pip":222,"brew":223,"system":224},[],[],[],[],{"commands":226,"expected_files":227},[],[],{"target":33,"score":61,"status":62,"policy":62,"why":229,"asset_kind":27,"install_mode":35},[64,65,66,67,68,69,70],{"author_trust_level":72,"verified_publisher":29,"asset_signed_hash":160,"signature_status":73,"install_count":12,"report_count":12,"dangerous_capability_badges":231,"review_status":75,"signals":232},[27],[77,78],{"owner_uuid":9,"owner_name":10,"source_url":234,"content_hash":160,"visibility":19,"created_at":235,"updated_at":236},"https:\u002F\u002Ftokrepo.com\u002Fen\u002Fworkflows\u002Fhive-framework-outcome-driven-multi-agent-harness","2026-05-12 22:02:44","2026-05-14 07:06:53",101.71919205351736,[147,193,148,194],[27,150],{"id":241,"uuid":242,"slug":243,"title":244,"description":245,"author_id":9,"author_name":10,"author_avatar":11,"token_estimate":246,"time_saved":12,"model_used":247,"fork_count":12,"vote_count":12,"view_count":248,"parent_id":12,"parent_uuid":13,"lang_type":15,"steps":249,"tags":250,"has_voted":29,"visibility":19,"share_token":13,"is_featured":12,"content_hash":256,"asset_kind":99,"target_tools":257,"install_mode":35,"entrypoint":244,"risk_profile":258,"dependencies":260,"verification":265,"agent_metadata":268,"agent_fit":280,"trust":288,"provenance":291,"created_at":293,"updated_at":294,"__relatedScore":295,"__relatedReasons":296,"__sharedTags":297},794,"b532d25b-6aa6-4eaf-9718-7fa025786f2b","camel-ai-multi-agent-role-playing-framework-b532d25b","Camel AI — Multi-Agent Role-Playing Framework","Build multi-agent systems where AI agents collaborate through role-playing. CAMEL enables autonomous cooperation between agents with structured communication protocols.",3800,"mixed",201,[],[251],{"id":252,"name":253,"slug":254,"icon":255},9,"Workflows","workflow","⚡","c32d331224fff8766eeced0f66ff5669bf1c6cce6659e76ee48d0129040430b4",[32],{"executes_code":29,"modifies_global_config":29,"requires_secrets":259,"uses_absolute_paths":29,"network_access":29},[],{"npm":261,"pip":262,"brew":263,"system":264},[],[],[],[],{"commands":266,"expected_files":267},[],[244],{"asset_kind":99,"target_tools":269,"install_mode":35,"entrypoint":244,"risk_profile":270,"dependencies":272,"content_hash":256,"verification":277},[32],{"executes_code":29,"modifies_global_config":29,"requires_secrets":271,"uses_absolute_paths":29,"network_access":29},[],{"npm":273,"pip":274,"brew":275,"system":276},[],[],[],[],{"commands":278,"expected_files":279},[],[244],{"target":33,"score":281,"status":282,"policy":283,"why":284,"asset_kind":99,"install_mode":35},66,"needs_confirmation","confirm",[285,130,66,67,286,287,70],"target_tools does not include codex","policy confirm","metadata target_tools does not include codex",{"author_trust_level":72,"verified_publisher":29,"asset_signed_hash":256,"signature_status":73,"install_count":12,"report_count":12,"dangerous_capability_badges":289,"review_status":75,"signals":290},[],[138,77,78,140],{"owner_uuid":9,"owner_name":10,"source_url":292,"content_hash":256,"visibility":19,"created_at":293,"updated_at":294},"https:\u002F\u002Ftokrepo.com\u002Fen\u002Fworkflows\u002Fcamel-ai-multi-agent-role-playing-framework-b532d25b","2026-04-08 14:13:15","2026-05-14 02:26:22",91.45802705416993,[147,148,194],[]]