[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"workflow-asset-51e958c5":3,"seo:featured-workflow:51e958c5-4ea4-11f1-9bc6-00163e2b0d79:zh":84,"workflow-related-asset-51e958c5-51e958c5-4ea4-11f1-9bc6-00163e2b0d79":85},{"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":12,"parent_id":12,"parent_uuid":13,"lang_type":14,"steps":15,"tags":22,"has_voted":28,"visibility":18,"share_token":13,"is_featured":12,"content_hash":29,"asset_kind":30,"target_tools":31,"install_mode":35,"entrypoint":19,"risk_profile":36,"dependencies":38,"verification":44,"agent_metadata":47,"agent_fit":60,"trust":72,"provenance":81,"created_at":83,"updated_at":83},3577,"51e958c5-4ea4-11f1-9bc6-00163e2b0d79","asset-51e958c5","XAgent — Autonomous AI Agent for Complex Task Solving","XAgent is an open-source autonomous agent framework that decomposes complex tasks into subtasks, plans execution strategies, and uses tool calling to complete multi-step workflows with minimal human intervention.","8a911193-3180-11f1-9bc6-00163e2b0d79","AI Open Source","https:\u002F\u002Ftokrepo.com\u002Fapple-touch-icon.png",0,"","en",[16],{"id":17,"step_order":18,"title":19,"description":13,"prompt_template":20,"variables":13,"depends_on":21,"expected_output":13},4137,1,"XAgent Overview","# XAgent — Autonomous AI Agent for Complex Task Solving\n\n## Quick Use\n```bash\ngit clone https:\u002F\u002Fgithub.com\u002FOpenBMB\u002FXAgent.git\ncd XAgent\npip install -r requirements.txt\npython run.py --task \"Analyze the top 10 Python packages by downloads\"\n```\n\n## Introduction\nXAgent is an autonomous AI agent framework developed by OpenBMB that breaks down complex tasks into manageable subtasks, creates execution plans, and carries them out using a combination of LLM reasoning and tool use. It supports human-in-the-loop interaction and provides a web interface for monitoring agent progress.\n\n## What XAgent Does\n- Decomposes user goals into structured subtask trees\n- Plans and executes multi-step workflows autonomously\n- Uses tool calling (web search, code execution, file operations)\n- Supports human-in-the-loop mode for guidance at decision points\n- Provides a web-based UI for real-time task monitoring\n\n## Architecture Overview\nXAgent uses a dual-loop architecture. The outer loop manages high-level planning and task decomposition, while the inner loop handles individual subtask execution with tool dispatch. A ToolServer component runs tools in sandboxed Docker containers for safety. The dispatcher routes between planning and execution phases, maintaining a persistent task state that enables recovery from failures.\n\n## Self-Hosting & Configuration\n- Clone the repository and install Python dependencies\n- Configure API keys for the LLM backend (supports OpenAI and compatible APIs)\n- Start the ToolServer via Docker for sandboxed tool execution\n- Launch the web UI for interactive monitoring\n- Adjust planning depth and tool permissions in the config file\n\n## Key Features\n- Hierarchical task decomposition with plan-then-execute strategy\n- Sandboxed tool execution via Docker-based ToolServer\n- Human-in-the-loop mode for supervised autonomous operation\n- Web UI with real-time task tree visualization\n- Supports multiple LLM backends through OpenAI-compatible API\n\n## Comparison with Similar Tools\n- **AutoGPT** — loop-based autonomous agent; XAgent uses structured planning with subtask trees\n- **CrewAI** — multi-agent role-based framework; XAgent is a single-agent planner-executor\n- **LangChain Agents** — tool-calling agents within a chain; XAgent provides deeper task decomposition\n- **MetaGPT** — multi-agent software engineering; XAgent targets general-purpose task solving\n\n## FAQ\n**Q: What LLMs does XAgent support?**\nA: It works with GPT-4, GPT-3.5, and any model accessible through an OpenAI-compatible API.\n\n**Q: Is XAgent safe to run?**\nA: Tool execution happens in sandboxed Docker containers. Human-in-the-loop mode adds an additional safety layer.\n\n**Q: Can it handle coding tasks?**\nA: Yes, it can write, execute, and debug code as part of its task-solving workflow.\n\n**Q: How does it differ from simple ReAct agents?**\nA: XAgent creates a full task tree before execution, enabling more structured and recoverable workflows than single-loop ReAct patterns.\n\n## Sources\n- https:\u002F\u002Fgithub.com\u002FOpenBMB\u002FXAgent\n- https:\u002F\u002Fblog.openbmb.org\u002Fxagent\u002F","0",[23],{"id":24,"name":25,"slug":26,"icon":27},12,"Configs","config","⚙️",false,"7407b3ccc8fefeeac7f562bb7f8c81ade008f360947afa4e167bfc8a9659020d","skill",[32,33,34],"claude_code","codex","gemini_cli","single",{"executes_code":28,"modifies_global_config":28,"requires_secrets":37,"uses_absolute_paths":28,"network_access":28},[],{"npm":39,"pip":40,"brew":42,"system":43},[],[41],"requirements.txt",[],[],{"commands":45,"expected_files":46},[],[19],{"asset_kind":30,"target_tools":48,"install_mode":35,"entrypoint":19,"risk_profile":49,"dependencies":51,"content_hash":29,"verification":56,"inferred":59},[32,33,34],{"executes_code":28,"modifies_global_config":28,"requires_secrets":50,"uses_absolute_paths":28,"network_access":28},[],{"npm":52,"pip":53,"brew":54,"system":55},[],[41],[],[],{"commands":57,"expected_files":58},[],[19],true,{"target":33,"score":61,"status":62,"policy":63,"why":64,"asset_kind":30,"install_mode":35},98,"native","allow",[65,66,67,68,69,70,71],"target_tools includes codex","asset_kind skill","install_mode single","markdown-only","policy allow","safe markdown-only Codex install","trust established",{"author_trust_level":73,"verified_publisher":28,"asset_signed_hash":29,"signature_status":74,"install_count":12,"report_count":12,"dangerous_capability_badges":75,"review_status":76,"signals":77},"established","hash_only",[],"unreviewed",[78,79,80],"author has published assets","content hash available","no dangerous capability badges",{"owner_uuid":9,"owner_name":10,"source_url":82,"content_hash":29,"visibility":18,"created_at":83,"updated_at":83},"https:\u002F\u002Ftokrepo.com\u002Fen\u002Fworkflows\u002Fasset-51e958c5","2026-05-13 16:18:28",null,[86,139,186,247],{"id":87,"uuid":88,"slug":89,"title":90,"description":91,"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":92,"parent_id":12,"parent_uuid":13,"lang_type":14,"steps":93,"tags":94,"has_voted":28,"visibility":18,"share_token":13,"is_featured":12,"content_hash":96,"asset_kind":30,"target_tools":97,"install_mode":35,"entrypoint":98,"risk_profile":99,"dependencies":101,"verification":106,"agent_metadata":109,"agent_fit":121,"trust":123,"provenance":127,"created_at":129,"updated_at":130,"__relatedScore":131,"__relatedReasons":132,"__sharedTags":137},1977,"0cff6cf4-3e8c-11f1-9bc6-00163e2b0d79","superagi-dev-first-autonomous-ai-agent-platform-0cff6cf4","SuperAGI — Dev-First Autonomous AI Agent Platform","Open-source framework for building, managing, and running autonomous AI agents with a web-based management console and tool marketplace.",100,[],[95],{"id":24,"name":25,"slug":26,"icon":27},"836b7a0394c11d100569371d4187616aa9df50d595e0d21e26501b6387052001",[32,33,34],"SuperAGI Overview",{"executes_code":28,"modifies_global_config":28,"requires_secrets":100,"uses_absolute_paths":28,"network_access":28},[],{"npm":102,"pip":103,"brew":104,"system":105},[],[],[],[],{"commands":107,"expected_files":108},[],[98],{"asset_kind":30,"target_tools":110,"install_mode":35,"entrypoint":98,"risk_profile":111,"dependencies":113,"content_hash":96,"verification":118},[32,33,34],{"executes_code":28,"modifies_global_config":28,"requires_secrets":112,"uses_absolute_paths":28,"network_access":28},[],{"npm":114,"pip":115,"brew":116,"system":117},[],[],[],[],{"commands":119,"expected_files":120},[],[98],{"target":33,"score":61,"status":62,"policy":63,"why":122,"asset_kind":30,"install_mode":35},[65,66,67,68,69,70,71],{"author_trust_level":73,"verified_publisher":28,"asset_signed_hash":96,"signature_status":74,"install_count":12,"report_count":12,"dangerous_capability_badges":124,"review_status":76,"signals":125},[],[126,78,79,80],"asset has usage views",{"owner_uuid":9,"owner_name":10,"source_url":128,"content_hash":96,"visibility":18,"created_at":129,"updated_at":130},"https:\u002F\u002Ftokrepo.com\u002Fen\u002Fworkflows\u002Fsuperagi-dev-first-autonomous-ai-agent-platform-0cff6cf4","2026-04-23 04:44:25","2026-05-13 17:02:49",106.00648206067396,[133,134,135,136],"topic-match","same-kind","same-target","same-author",[26,138],"configs",{"id":140,"uuid":141,"slug":142,"title":143,"description":144,"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":145,"parent_id":12,"parent_uuid":13,"lang_type":14,"steps":146,"tags":147,"has_voted":28,"visibility":18,"share_token":13,"is_featured":12,"content_hash":149,"asset_kind":30,"target_tools":150,"install_mode":35,"entrypoint":151,"risk_profile":152,"dependencies":154,"verification":159,"agent_metadata":162,"agent_fit":174,"trust":176,"provenance":179,"created_at":181,"updated_at":182,"__relatedScore":183,"__relatedReasons":184,"__sharedTags":185},2636,"3b971897-47b5-11f1-9bc6-00163e2b0d79","asset-3b971897","Agent Squad — Multi-Agent Orchestration for Complex Conversations","A flexible open-source framework for managing multiple AI agents that intelligently routes conversations to specialized agents based on context, supporting both Python and TypeScript.",89,[],[148],{"id":24,"name":25,"slug":26,"icon":27},"7692828c97ea51b76e4c0a6cc0fb41a3f399fea9ea9d7121f41d122fa4c60aff",[32,33,34],"Agent Squad",{"executes_code":28,"modifies_global_config":28,"requires_secrets":153,"uses_absolute_paths":28,"network_access":28},[],{"npm":155,"pip":156,"brew":157,"system":158},[],[],[],[],{"commands":160,"expected_files":161},[],[151],{"asset_kind":30,"target_tools":163,"install_mode":35,"entrypoint":151,"risk_profile":164,"dependencies":166,"content_hash":149,"verification":171},[32,33,34],{"executes_code":28,"modifies_global_config":28,"requires_secrets":165,"uses_absolute_paths":28,"network_access":28},[],{"npm":167,"pip":168,"brew":169,"system":170},[],[],[],[],{"commands":172,"expected_files":173},[],[151],{"target":33,"score":61,"status":62,"policy":63,"why":175,"asset_kind":30,"install_mode":35},[65,66,67,68,69,70,71],{"author_trust_level":73,"verified_publisher":28,"asset_signed_hash":149,"signature_status":74,"install_count":12,"report_count":12,"dangerous_capability_badges":177,"review_status":76,"signals":178},[],[78,79,80],{"owner_uuid":9,"owner_name":10,"source_url":180,"content_hash":149,"visibility":18,"created_at":181,"updated_at":182},"https:\u002F\u002Ftokrepo.com\u002Fen\u002Fworkflows\u002Fasset-3b971897","2026-05-04 20:31:53","2026-05-13 00:01:03",102.93136376415899,[133,134,135,136],[26,138],{"id":187,"uuid":188,"slug":189,"title":190,"description":191,"author_id":192,"author_name":193,"author_avatar":11,"token_estimate":12,"time_saved":12,"model_used":13,"fork_count":12,"vote_count":12,"view_count":194,"parent_id":12,"parent_uuid":13,"lang_type":14,"steps":195,"tags":196,"has_voted":28,"visibility":18,"share_token":13,"is_featured":12,"content_hash":202,"asset_kind":30,"target_tools":203,"install_mode":204,"entrypoint":205,"risk_profile":206,"dependencies":209,"verification":214,"agent_metadata":217,"agent_fit":229,"trust":236,"provenance":240,"created_at":242,"updated_at":243,"__relatedScore":244,"__relatedReasons":245,"__sharedTags":246},1976,"f3ff673a-3e8b-11f1-9bc6-00163e2b0d79","babyagi-task-driven-autonomous-agent-framework-f3ff673a","BabyAGI — Task-Driven Autonomous Agent Framework","Lightweight autonomous agent that creates, prioritizes, and executes tasks using LLMs in a continuous loop.","8a910e34-3180-11f1-9bc6-00163e2b0d79","Script Depot",117,[],[197],{"id":198,"name":199,"slug":200,"icon":201},11,"Scripts","script","📜","6179fa81eb0920907fd5ebc0611aa49dfe487e2f499350b41f4f17c8c514305a",[32,33,34],"stage_only","BabyAGI Overview",{"executes_code":28,"modifies_global_config":28,"requires_secrets":207,"uses_absolute_paths":28,"network_access":28},[208],"OPENAI_API_KEY",{"npm":210,"pip":211,"brew":212,"system":213},[],[],[],[],{"commands":215,"expected_files":216},[],[205],{"asset_kind":30,"target_tools":218,"install_mode":204,"entrypoint":205,"risk_profile":219,"dependencies":221,"content_hash":202,"verification":226},[32,33,34],{"executes_code":28,"modifies_global_config":28,"requires_secrets":220,"uses_absolute_paths":28,"network_access":28},[208],{"npm":222,"pip":223,"brew":224,"system":225},[],[],[],[],{"commands":227,"expected_files":228},[],[205],{"target":33,"score":230,"status":204,"policy":204,"why":231,"asset_kind":30,"install_mode":204},29,[65,66,232,233,234,235,71],"install_mode stage_only","policy stage_only","install_mode is stage_only","risk_profile.requires_secrets is not empty",{"author_trust_level":73,"verified_publisher":28,"asset_signed_hash":202,"signature_status":74,"install_count":12,"report_count":12,"dangerous_capability_badges":237,"review_status":76,"signals":239},[238,204],"requires_secrets",[126,78,79],{"owner_uuid":192,"owner_name":193,"source_url":241,"content_hash":202,"visibility":18,"created_at":242,"updated_at":243},"https:\u002F\u002Ftokrepo.com\u002Fen\u002Fworkflows\u002Fbabyagi-task-driven-autonomous-agent-framework-f3ff673a","2026-04-23 04:43:44","2026-05-13 12:56:33",99.1078230109592,[133,134,135],[],{"id":248,"uuid":249,"slug":250,"title":251,"description":252,"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":253,"parent_id":12,"parent_uuid":13,"lang_type":14,"steps":254,"tags":255,"has_voted":28,"visibility":18,"share_token":13,"is_featured":12,"content_hash":257,"asset_kind":30,"target_tools":258,"install_mode":204,"entrypoint":259,"risk_profile":260,"dependencies":262,"verification":267,"agent_metadata":270,"agent_fit":282,"trust":284,"provenance":287,"created_at":289,"updated_at":290,"__relatedScore":291,"__relatedReasons":292,"__sharedTags":293},2059,"76372082-3fda-11f1-9bc6-00163e2b0d79","agentgpt-autonomous-ai-agent-your-browser-76372082","AgentGPT — Autonomous AI Agent in Your Browser","AgentGPT lets you deploy autonomous AI agents directly in a web browser. Give it a goal and it will create tasks, execute them, and iterate until the objective is reached.",67,[],[256],{"id":24,"name":25,"slug":26,"icon":27},"b200a7c9f3455322a725e50e71958db335bab1acdae79c2780d0c13c45ce6f00",[32,33,34],"AgentGPT Overview",{"executes_code":28,"modifies_global_config":28,"requires_secrets":261,"uses_absolute_paths":28,"network_access":28},[208],{"npm":263,"pip":264,"brew":265,"system":266},[],[],[],[],{"commands":268,"expected_files":269},[],[259],{"asset_kind":30,"target_tools":271,"install_mode":204,"entrypoint":259,"risk_profile":272,"dependencies":274,"content_hash":257,"verification":279},[32,33,34],{"executes_code":28,"modifies_global_config":28,"requires_secrets":273,"uses_absolute_paths":28,"network_access":28},[208],{"npm":275,"pip":276,"brew":277,"system":278},[],[],[],[],{"commands":280,"expected_files":281},[],[259],{"target":33,"score":230,"status":204,"policy":204,"why":283,"asset_kind":30,"install_mode":204},[65,66,232,233,234,235,71],{"author_trust_level":73,"verified_publisher":28,"asset_signed_hash":257,"signature_status":74,"install_count":12,"report_count":12,"dangerous_capability_badges":285,"review_status":76,"signals":286},[238,204],[78,79],{"owner_uuid":9,"owner_name":10,"source_url":288,"content_hash":257,"visibility":18,"created_at":289,"updated_at":290},"https:\u002F\u002Ftokrepo.com\u002Fen\u002Fworkflows\u002Fagentgpt-autonomous-ai-agent-your-browser-76372082","2026-04-24 20:38:14","2026-05-13 17:04:20",95.74876336905936,[133,134,135,136],[26,138]]