[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"workflow-hive-framework-outcome-driven-multi-agent-harness-79c28341":3,"seo:featured-workflow:79c28341-ca9a-585d-b8cf-b183829b6d9d:fr":38,"workflow-related-hive-framework-outcome-driven-multi-agent-harness-79c28341-79c28341-ca9a-585d-b8cf-b183829b6d9d":82},{"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":45,"agent_metadata":48,"agent_fit":59,"trust":70,"provenance":78,"created_at":80,"updated_at":81},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.","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},3840,1,"Asset","## Quick Use\n\n1. Clone and run the guided setup:\n   ```bash\n   git clone https:\u002F\u002Fgithub.com\u002Faden-hive\u002Fhive.git\n   cd hive\n   .\u002Fquickstart.sh\n   ```\n2. On Windows use:\n   ```powershell\n   .\\quickstart.ps1\n   ```\n3. Verify:\n   - Open the browser dashboard, create one sample agent, and run it once end-to-end.\n\n## Intro\n\nHive Framework turns natural-language goals into generated agent graphs and dashboards, giving teams a production-minded multi-agent harness.\n\n- **Best for:** teams that want graph generation, dashboards, and MCP-connected business workflows in one harness\n- **Works with:** Python 3.11+, uv workspaces, browser dashboard, LiteLLM-compatible providers, MCP tool integrations\n- **Setup time:** 20-40 minutes\n\n## Practical Notes\n\n- Quant: the repo advertises 102 MCP tools and a uv workspace split across core runtime and tool environments.\n- Quant: the quickstart provisions at least two virtual environments (`core\u002F.venv` and `tools\u002F.venv`) plus encrypted credentials.\n\n## Why it matters\n\nHive is notable because it is opinionated about the harness layer: goal intake, graph generation, execution, observation, and evolution are treated as one loop.\n\n- The quickstart is explicit that `pip install -e .` is the wrong path, which reduces a common failure mode in workspace-style Python repos.\n- The dashboard-first UX is useful when non-framework specialists need to inspect how agents were generated and run.\n- The project emphasizes business-system connectivity through MCP, which is the main difference between a demo agent and a production workflow.\n\n## Rollout pattern\n\n- Use the quickstart script exactly as documented and avoid improvising the install path on first run.\n- Pilot one outcome-driven workflow that touches a single external system before you let Hive generate broader graphs.\n- Treat the browser dashboard as an audit surface: capture screenshots or logs from the first few generated runs.\n\n## Watchouts\n\nBecause Hive generates orchestration structures for you, the main risk is over-trusting generated graphs before you understand the tool permissions and business-system side effects.\n\n### FAQ\n\n**Q: Can I install it with pip editable mode?**\nA: No. The README warns that the project uses a uv workspace layout and that `pip install -e .` will not work correctly.\n\n**Q: What makes it different from a basic agent SDK?**\nA: It includes graph generation, dashboarding, credential handling, and MCP-oriented system integration.\n\n**Q: What is the first validation step?**\nA: Run the quickstart, open the dashboard, and execute one sample agent with limited scope.\n\n## Source & Thanks\n\n> Source: https:\u002F\u002Fgithub.com\u002Faden-hive\u002Fhive\n> License: Apache-2.0\n> GitHub stars: 10,302 · forks: 5,647\n\n---\n\n\u003C!-- ZH -->\n\n## 快速使用\n\n1. 克隆并运行向导式安装：\n   ```bash\n   git clone https:\u002F\u002Fgithub.com\u002Faden-hive\u002Fhive.git\n   cd hive\n   .\u002Fquickstart.sh\n   ```\n2. Windows 请使用：\n   ```powershell\n   .\\quickstart.ps1\n   ```\n3. 验证：\n   - 打开浏览器仪表盘，创建一个示例 Agent，并完整执行一次。\n\n## 简介\n\nHive Framework 试图把自然语言目标自动变成 Agent 图与控制台，为团队提供更偏生产环境的多 Agent harness，减少继续手写、维护和排查零散编排脚本所带来的长期负担。\n\n- **适合谁：** 希望把图式编排、仪表盘与 MCP 业务连接统一在一个 harness 中的团队\n- **可搭配：** Python 3.11+、uv workspace、浏览器仪表盘、LiteLLM 兼容模型与 MCP 工具集成\n- **准备时间：** 20-40 分钟\n\n## 实战建议\n\n- 量化信息：仓库首页直接标出 102 个 MCP tools，并把运行时与工具环境拆成 uv workspace。\n- 量化信息：quickstart 至少会准备 `core\u002F.venv`、`tools\u002F.venv` 和加密凭证存储。 \n\n## 为什么值得收录\n\nHive 的独特点在于它明确把“harness 层”当成产品主体：目标输入、图生成、执行、观测和演化是同一个闭环。\n\n- README 明确提醒不要用 `pip install -e .`，这能避免很多 uv workspace 项目的常见安装坑。\n- 以浏览器仪表盘为中心的交互方式，更适合让非框架开发者也能看懂 Agent 是怎么生成和运行的。\n- 项目强调通过 MCP 连接业务系统，这正是 Demo Agent 与生产工作流之间的关键差别。\n\n## 落地路径\n\n- 第一次部署按 quickstart 原样执行，不要自作主张改安装路径。\n- 先试 1 个只连接单一外部系统的 outcome-driven workflow，再扩展更复杂图。\n- 把浏览器仪表盘当成审计界面，前几次运行务必保留截图或日志证据。 \n\n## 注意事项\n\n因为它会替你生成编排结构，最大的风险是你还没搞清工具权限和业务副作用，就过度信任自动生成的 Agent 图。\n\n### FAQ\n\n**可以直接用 pip editable 安装吗？**\n答：不行。README 已明确说明它是 uv workspace，`pip install -e .` 会导致功能异常。\n\n**它和普通 Agent SDK 的区别是什么？**\n答：它把图生成、仪表盘、凭证管理和 MCP 系统连接一起打包了。\n\n**第一步怎么验证？**\n答：跑 quickstart，打开 dashboard，再执行一个权限有限的示例 Agent。\n\n## 来源与感谢\n\n> Source: https:\u002F\u002Fgithub.com\u002Faden-hive\u002Fhive\n> License: Apache-2.0\n> GitHub stars: 10,302 · forks: 5,647\n","0",[24],{"id":25,"name":26,"slug":27,"icon":28},11,"Scripts","script","📜",false,"b7d9f86083a078b60a12f53478b10a3d08667f3dde3ee88db9925fa7ec774ff7",[32,33,34],"claude_code","codex","gemini_cli","single","quickstart.sh",{"executes_code":29,"modifies_global_config":29,"requires_secrets":38,"uses_absolute_paths":29,"network_access":29},null,{"npm":40,"pip":41,"brew":43,"system":44},[],[42],".",[],[],{"commands":46,"expected_files":47},[],[20],{"asset_kind":27,"target_tools":49,"install_mode":35,"entrypoint":36,"risk_profile":50,"dependencies":51,"content_hash":30,"verification":56},[32,33,34],{"executes_code":29,"modifies_global_config":29,"requires_secrets":38,"uses_absolute_paths":29,"network_access":29},{"npm":52,"pip":53,"brew":54,"system":55},[],[42],[],[],{"commands":57,"expected_files":58},[],[20],{"target":33,"score":60,"status":61,"policy":61,"why":62,"asset_kind":27,"install_mode":35},29,"stage_only",[63,64,65,66,67,68,69],"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":71,"verified_publisher":29,"asset_signed_hash":30,"signature_status":72,"install_count":12,"report_count":12,"dangerous_capability_badges":73,"review_status":74,"signals":75},"established","hash_only",[27],"unreviewed",[76,77],"author has published assets","content hash available",{"owner_uuid":9,"owner_name":10,"source_url":79,"content_hash":30,"visibility":19,"created_at":80,"updated_at":81},"https:\u002F\u002Ftokrepo.com\u002Fen\u002Fworkflows\u002Fhive-framework-outcome-driven-multi-agent-harness","2026-05-12 22:02:44","2026-05-14 00:44:46",[83,132,196,239],{"id":84,"uuid":85,"slug":86,"title":87,"description":88,"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":89,"tags":90,"has_voted":29,"visibility":19,"share_token":13,"is_featured":12,"content_hash":92,"asset_kind":27,"target_tools":93,"install_mode":35,"entrypoint":94,"risk_profile":95,"dependencies":96,"verification":101,"agent_metadata":104,"agent_fit":115,"trust":117,"provenance":120,"created_at":122,"updated_at":123,"__relatedScore":124,"__relatedReasons":125,"__sharedTags":130},3135,"ec4301e4-eb8d-4210-9a9b-228585a04031","microsoft-agent-framework-build-run-agent-workflows","Microsoft Agent Framework — Build & Run Agent Workflows","Microsoft Agent Framework builds production-grade agents and multi-agent workflows in Python and .NET, with official docs and quickstarts for teams.",[],[91],{"id":25,"name":26,"slug":27,"icon":28},"e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855",[32,33,34],"README.md",{"executes_code":29,"modifies_global_config":29,"requires_secrets":38,"uses_absolute_paths":29,"network_access":29},{"npm":97,"pip":98,"brew":99,"system":100},[],[],[],[],{"commands":102,"expected_files":103},[],[],{"asset_kind":27,"target_tools":105,"install_mode":35,"entrypoint":94,"risk_profile":106,"dependencies":107,"content_hash":92,"verification":112},[32,33,34],{"executes_code":29,"modifies_global_config":29,"requires_secrets":38,"uses_absolute_paths":29,"network_access":29},{"npm":108,"pip":109,"brew":110,"system":111},[],[],[],[],{"commands":113,"expected_files":114},[],[],{"target":33,"score":60,"status":61,"policy":61,"why":116,"asset_kind":27,"install_mode":35},[63,64,65,66,67,68,69],{"author_trust_level":71,"verified_publisher":29,"asset_signed_hash":92,"signature_status":72,"install_count":12,"report_count":12,"dangerous_capability_badges":118,"review_status":74,"signals":119},[27],[76,77],{"owner_uuid":9,"owner_name":10,"source_url":121,"content_hash":92,"visibility":19,"created_at":122,"updated_at":123},"https:\u002F\u002Ftokrepo.com\u002Fen\u002Fworkflows\u002Fmicrosoft-agent-framework-build-run-agent-workflows","2026-05-12 04:56:51","2026-05-14 00:59:12",116.67091502846026,[126,127,128,129],"topic-match","same-kind","same-target","same-author",[27,131],"scripts",{"id":133,"uuid":134,"slug":135,"title":136,"description":137,"author_id":138,"author_name":139,"author_avatar":11,"token_estimate":140,"time_saved":12,"model_used":141,"fork_count":12,"vote_count":12,"view_count":142,"parent_id":12,"parent_uuid":13,"lang_type":15,"steps":143,"tags":144,"has_voted":29,"visibility":19,"share_token":13,"is_featured":19,"content_hash":146,"asset_kind":147,"target_tools":148,"install_mode":35,"entrypoint":136,"risk_profile":151,"dependencies":153,"verification":158,"agent_metadata":161,"agent_fit":173,"trust":181,"provenance":189,"created_at":191,"updated_at":192,"__relatedScore":193,"__relatedReasons":194,"__sharedTags":195},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,[],[145],{"id":25,"name":26,"slug":27,"icon":28},"ef6e6cd6d0c7d6fa8598295657ad11912310168f7abe9413fd39e255835fa1d1","skill",[32,33,149,34,150],"cursor","windsurf",{"executes_code":29,"modifies_global_config":29,"requires_secrets":152,"uses_absolute_paths":29,"network_access":29},[],{"npm":154,"pip":155,"brew":156,"system":157},[],[],[],[],{"commands":159,"expected_files":160},[],[136],{"asset_kind":147,"target_tools":162,"install_mode":35,"entrypoint":136,"risk_profile":163,"dependencies":165,"content_hash":146,"verification":170},[32,33,149,34,150],{"executes_code":29,"modifies_global_config":29,"requires_secrets":164,"uses_absolute_paths":29,"network_access":29},[],{"npm":166,"pip":167,"brew":168,"system":169},[],[],[],[],{"commands":171,"expected_files":172},[],[136],{"target":33,"score":174,"status":175,"policy":176,"why":177,"asset_kind":147,"install_mode":35},98,"native","allow",[63,178,65,66,179,180,69],"asset_kind skill","policy allow","safe markdown-only Codex install",{"author_trust_level":71,"verified_publisher":29,"asset_signed_hash":146,"signature_status":72,"last_reviewed_at":182,"install_count":12,"report_count":12,"dangerous_capability_badges":183,"review_status":184,"signals":185},"2026-05-14T01:22:06+08:00",[],"reviewed",[186,76,77,187,188],"asset has usage views","featured asset","no dangerous capability badges",{"owner_uuid":138,"owner_name":139,"source_url":190,"content_hash":146,"visibility":19,"created_at":191,"updated_at":192},"https:\u002F\u002Ftokrepo.com\u002Fen\u002Fworkflows\u002Fcamel-multi-agent-framework-scale-23732313","2026-04-01 07:13:47","2026-05-14 01:22:06",103.80294118006415,[126,128],[27,131],{"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":92,"asset_kind":27,"target_tools":206,"install_mode":35,"entrypoint":94,"risk_profile":207,"dependencies":208,"verification":213,"agent_metadata":216,"agent_fit":227,"trust":229,"provenance":232,"created_at":234,"updated_at":235,"__relatedScore":236,"__relatedReasons":237,"__sharedTags":238},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.",14,[],[205],{"id":25,"name":26,"slug":27,"icon":28},[32,33,34],{"executes_code":29,"modifies_global_config":29,"requires_secrets":38,"uses_absolute_paths":29,"network_access":29},{"npm":209,"pip":210,"brew":211,"system":212},[],[],[],[],{"commands":214,"expected_files":215},[],[],{"asset_kind":27,"target_tools":217,"install_mode":35,"entrypoint":94,"risk_profile":218,"dependencies":219,"content_hash":92,"verification":224},[32,33,34],{"executes_code":29,"modifies_global_config":29,"requires_secrets":38,"uses_absolute_paths":29,"network_access":29},{"npm":220,"pip":221,"brew":222,"system":223},[],[],[],[],{"commands":225,"expected_files":226},[],[],{"target":33,"score":60,"status":61,"policy":61,"why":228,"asset_kind":27,"install_mode":35},[63,64,65,66,67,68,69],{"author_trust_level":71,"verified_publisher":29,"asset_signed_hash":92,"signature_status":72,"install_count":12,"report_count":12,"dangerous_capability_badges":230,"review_status":74,"signals":231},[27],[76,77],{"owner_uuid":9,"owner_name":10,"source_url":233,"content_hash":92,"visibility":19,"created_at":234,"updated_at":235},"https:\u002F\u002Ftokrepo.com\u002Fen\u002Fworkflows\u002Fcamel-multi-agent-and-tooling-library","2026-05-12 00:58:31","2026-05-14 07:07:06",101.76413688858352,[126,127,128,129],[27,131],{"id":240,"uuid":241,"slug":242,"title":243,"description":244,"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":245,"tags":246,"has_voted":29,"visibility":19,"share_token":13,"is_featured":12,"content_hash":92,"asset_kind":27,"target_tools":248,"install_mode":35,"entrypoint":249,"risk_profile":250,"dependencies":251,"verification":256,"agent_metadata":259,"agent_fit":270,"trust":272,"provenance":275,"created_at":277,"updated_at":278,"__relatedScore":279,"__relatedReasons":280,"__sharedTags":281},3309,"376e2fa5-a3f0-52fc-a8df-f212825e14a4","ms-agent-lightweight-agent-framework-with-mcp","MS-Agent — Lightweight Agent Framework with MCP","MS-Agent is a lightweight agent framework with MCP configs; install via pip and start with an LLMAgent example wired to Streamable HTTP MCP endpoints.",[],[247],{"id":25,"name":26,"slug":27,"icon":28},[32,33,34],"ms-agent",{"executes_code":29,"modifies_global_config":29,"requires_secrets":38,"uses_absolute_paths":29,"network_access":29},{"npm":252,"pip":253,"brew":254,"system":255},[],[],[],[],{"commands":257,"expected_files":258},[],[],{"asset_kind":27,"target_tools":260,"install_mode":35,"entrypoint":249,"risk_profile":261,"dependencies":262,"content_hash":92,"verification":267},[32,33,34],{"executes_code":29,"modifies_global_config":29,"requires_secrets":38,"uses_absolute_paths":29,"network_access":29},{"npm":263,"pip":264,"brew":265,"system":266},[],[],[],[],{"commands":268,"expected_files":269},[],[],{"target":33,"score":60,"status":61,"policy":61,"why":271,"asset_kind":27,"install_mode":35},[63,64,65,66,67,68,69],{"author_trust_level":71,"verified_publisher":29,"asset_signed_hash":92,"signature_status":72,"install_count":12,"report_count":12,"dangerous_capability_badges":273,"review_status":74,"signals":274},[27],[76,77],{"owner_uuid":9,"owner_name":10,"source_url":276,"content_hash":92,"visibility":19,"created_at":277,"updated_at":278},"https:\u002F\u002Ftokrepo.com\u002Fen\u002Fworkflows\u002Fms-agent-lightweight-agent-framework-with-mcp","2026-05-12 23:31:49","2026-05-14 00:55:20",101.67091502846026,[126,127,128,129],[27,131]]