[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"workflow-gpt-researcher-autonomous-research-report-agent-23330210":3,"seo:featured-workflow:23330210-b26a-4d97-ad97-1735c203eaa6:en":93,"workflow-related-gpt-researcher-autonomous-research-report-agent-23330210-23330210-b26a-4d97-ad97-1735c203eaa6":153},{"id":4,"uuid":5,"slug":6,"title":7,"description":8,"author_id":9,"author_name":10,"author_avatar":11,"token_estimate":12,"time_saved":13,"model_used":14,"fork_count":13,"vote_count":13,"view_count":15,"parent_id":13,"parent_uuid":16,"lang_type":17,"steps":18,"files":27,"tags":32,"has_voted":38,"visibility":21,"share_token":16,"is_featured":13,"content_hash":39,"asset_kind":40,"target_tools":41,"install_mode":44,"entrypoint":29,"risk_profile":45,"dependencies":47,"verification":52,"agent_metadata":55,"agent_fit":67,"trust":79,"provenance":89,"created_at":91,"updated_at":92},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.","81b6b4dc-2ab8-11f1-9bc6-00163e2b0d79","TokRepo精选","https:\u002F\u002Ftokrepo.com\u002Fapple-touch-icon.png",493,0,"Claude Code \u002F Codex \u002F OpenCode",448,"","en",[19],{"id":20,"step_order":21,"title":22,"description":23,"prompt_template":24,"variables":25,"depends_on":26,"expected_output":16},195,1,"GPT Researcher Autonomous Research Agent","Automated deep-research agent. Supports server-side execution, Python package usage, Docker deployment, and Claude Skill integration.","## Quick Use\n\n```bash\npip install gpt-researcher\n```\n\n```python\nfrom gpt_researcher import GPTResearcher\nimport asyncio\n\nasync def research():\n    researcher = GPTResearcher(query=\"your research topic here\")\n    await researcher.conduct_research()\n    report = await researcher.write_report()\n    print(report)\n\nasyncio.run(research())\n```\n\n**Required API keys** (set as environment variables):\n```bash\nexport OPENAI_API_KEY=your_key\nexport TAVILY_API_KEY=your_key  # for web search\n```\n\n---\n\n## Intro\n\nGPT Researcher is an autonomous research agent that generates detailed, citation-backed research reports from a single query. It crawls 20+ web sources in parallel, cross-references information to reduce bias, and produces reports exceeding 2,000 words — complete with source citations. Think of it as a research assistant that does hours of googling and reading in minutes.\n\n**Works with**: GitHub Copilot, Gemini CLI, OpenAI Codex, Ollama\n---\n\n## Architecture\n\nThe system uses a **planner + execution** agent pattern:\n\n1. **Task agent** created based on your research query\n2. **Planner** generates focused sub-questions for objectivity\n3. **Crawler agents** gather information per question (parallelized)\n4. **Summarizer** tracks sources and extracts key findings\n5. **Publisher** aggregates everything into a structured report\n\n## Key Features\n\n- 📝 Detailed research reports from web and local documents\n- 🖼️ Smart image scraping and AI-generated inline images (via Gemini)\n- 📜 Reports exceeding 2,000 words with citations\n- 🌐 Aggregates 20+ sources for balanced conclusions\n- 🔍 JavaScript-enabled web scraping\n- 📂 Persistent memory and context throughout research\n- 📄 Export to PDF, Word, Markdown\n- 🌳 Deep Research mode with tree-like recursive exploration\n- 🤖 MCP Client integration for specialized data sources\n\n## Installation Options\n\n### Via pip\n```bash\npip install gpt-researcher\n```\n\n### From source\n```bash\ngit clone https:\u002F\u002Fgithub.com\u002Fassafelovic\u002Fgpt-researcher.git\ncd gpt-researcher\npip install -r requirements.txt\npython -m uvicorn main:app --reload\n# Visit http:\u002F\u002Flocalhost:8000\n```\n\n### Docker\n```bash\ndocker-compose up --build\n# React app at localhost:3000, API at localhost:8000\n```\n\n## Usage Examples\n\n### Basic research\n```python\nresearcher = GPTResearcher(query=\"why is Nvidia stock going up?\")\nawait researcher.conduct_research()\nreport = await researcher.write_report()\n```\n\n### Research local documents\n```bash\nexport DOC_PATH=\".\u002Fmy-docs\"\n```\n```python\nresearcher = GPTResearcher(query=\"analyze these docs\", report_source=\"local\")\n```\nSupports: PDF, plain text, CSV, Excel, Markdown, PowerPoint, Word.\n\n### MCP integration\n```python\nresearcher = GPTResearcher(\n    query=\"top open source research agents\",\n    mcp_configs=[{\n        \"name\": \"github\",\n        \"command\": \"npx\",\n        \"args\": [\"-y\", \"@modelcontextprotocol\u002Fserver-github\"],\n        \"env\": {\"GITHUB_TOKEN\": os.getenv(\"GITHUB_TOKEN\")}\n    }]\n)\n```\n\n### Deep Research\nTree-like recursive exploration with configurable depth\u002Fbreadth. Takes ~5 minutes, costs ~$0.40 with o3-mini.\n\n---\n\n\n\n### FAQ\n\n**Q: What is GPT Researcher?**\nA: AI agent that generates detailed research reports from a single query. Searches multiple sources, synthesizes findings, and cites references.\n\n**Q: How do I install GPT Researcher?**\nA: Check the Quick Use section above for step-by-step installation instructions. Most assets can be set up in under 2 minutes.\n\n## Source & Thanks\n\n> Created by [Assaf Elovic](https:\u002F\u002Fgithub.com\u002Fassafelovic). Licensed under Apache 2.0.\n> [gpt-researcher](https:\u002F\u002Fgithub.com\u002Fassafelovic\u002Fgpt-researcher) — ⭐ 26,000+\n> Docs: [docs.gptr.dev](https:\u002F\u002Fdocs.gptr.dev)\n\nThanks to Assaf Elovic for building an open alternative to deep research tools. Active development with regular updates.","{}","0",[28],{"name":29,"content":30,"type":31},"Claude-Skills-A-Deep-Dive-From-Internals-to-Claude-Code-CodeX-OpenCode-in-Practice.md","---\nname: Claude Skills — A Deep Dive From Internals to Claude Code, CodeX, and OpenCode in Practice\ndescription: A cross-runtime walkthrough of Claude Skills, covering how the format works and how the same skill can be reused across Claude Code, Codex, and OpenCode.\ntype: other\n---\n\n# Claude Skills — A Deep Dive From Internals to Claude Code, CodeX, and OpenCode in Practice\n\n- Original Author: Java Tech Stack\n- Source: https:\u002F\u002Fwww.cnblogs.com\u002Fjavastack\u002Fp\u002F19531825\n- Discovery Team Verdict: pass, 5\u002F6 signals\n- Review Team Score: 86\u002F100, A\n- Email Status: not-found\n\n## Goal\n\nExplain what Skills are, why they save context and tokens, and how one Skill structure can be reused across multiple AI coding runtimes.\n\n## Tools\n\n- Claude Code\n- Codex \u002F CodeX\n- OpenCode\n- Agent Skills standard\n- SKILL.md\n\n## Method\n\n1. Define Skills as modular folders containing instructions, metadata, and resources.\n2. Show how on-demand loading keeps the main context smaller than always-on prompting.\n3. Demonstrate the same Skill pattern across Claude Code, CodeX, and OpenCode instead of treating each runtime as a separate one-off workflow.\n\n## Result\n\n- The source positions Skills as a reusable format rather than a product-specific hack.\n- It explicitly frames on-demand Skill loading as a token-saving and compatibility advantage.\n\n## Lessons\n\n- A strong Skill format is more valuable than platform-specific prompt clutter.\n- Cross-runtime compatibility increases the long-term value of a Skill investment.\n- Modular capability files are easier to maintain than giant instruction blocks.\n\n## Reusable Assets\n\n- Skill folder structure examples\n- Cross-runtime Skills adaptation pattern\n- A practical explanation of why Skills reduce token overhead\n\n## Why TokRepo\n\nTokRepo needs content that helps users treat Skills as portable AI assets. This piece is especially useful because it connects format design, runtime reuse, and token efficiency in one place.\n","other",[33],{"id":34,"name":35,"slug":36,"icon":37},11,"Scripts","script","📜",false,"5a75a9c8d528bc8963430159a28a71173ed1e855d9dfe6d4f82fbd4c4ff7422e","skill",[42,43],"claude_code","codex","single",{"executes_code":38,"modifies_global_config":38,"requires_secrets":46,"uses_absolute_paths":38,"network_access":38},[],{"npm":48,"pip":49,"brew":50,"system":51},[],[],[],[],{"commands":53,"expected_files":54},[],[29],{"asset_kind":40,"target_tools":56,"install_mode":44,"entrypoint":29,"risk_profile":57,"dependencies":59,"content_hash":39,"verification":64},[42,43],{"executes_code":38,"modifies_global_config":38,"requires_secrets":58,"uses_absolute_paths":38,"network_access":38},[],{"npm":60,"pip":61,"brew":62,"system":63},[],[],[],[],{"commands":65,"expected_files":66},[],[29],{"target":43,"score":68,"status":69,"policy":70,"why":71,"asset_kind":40,"install_mode":44},98,"native","allow",[72,73,74,75,76,77,78],"target_tools includes codex","asset_kind skill","install_mode single","markdown-only","policy allow","safe markdown-only Codex install","trust established",{"author_trust_level":80,"verified_publisher":38,"asset_signed_hash":39,"signature_status":81,"install_count":13,"report_count":13,"dangerous_capability_badges":82,"review_status":83,"signals":84},"established","hash_only",[],"unreviewed",[85,86,87,88],"asset has usage views","author has published assets","content hash available","no dangerous capability badges",{"owner_uuid":9,"owner_name":10,"source_url":90,"content_hash":39,"visibility":21,"created_at":91,"updated_at":92},"https:\u002F\u002Ftokrepo.com\u002Fen\u002Fworkflows\u002Fgpt-researcher-autonomous-research-report-agent-23330210","2026-03-28 14:36:26","2026-05-13 04:51:01",{"pageType":94,"pageKey":5,"locale":17,"title":95,"metaDescription":96,"h1":7,"tldr":97,"bodyMarkdown":98,"faq":99,"schema":115,"internalLinks":125,"citations":138,"wordCount":151,"generatedAt":152},"featured-workflow","GPT Researcher: Autonomous Research Report Agent (2026)","GPT Researcher is an AI agent that generates detailed research reports from a single query. Searches multiple sources, synthesizes findings, and cites references.","GPT Researcher generates detailed, cited research reports from a single query automatically.","## What it is\n\nGPT Researcher is an open-source autonomous AI agent that produces comprehensive research reports from a single query. Given a topic, it plans sub-questions, searches multiple web sources, scrapes and summarizes relevant content, and synthesizes everything into a structured report with citations. The agent handles the entire research workflow that would otherwise require manual searching, reading, and writing.\n\nGPT Researcher targets professionals, analysts, and teams who need well-researched reports without spending hours on manual web research. It works with OpenAI, Anthropic, and other LLM providers.\n\n## How it saves time or tokens\n\nManual research involves iterating between search engines, reading articles, taking notes, and synthesizing findings. GPT Researcher automates this entire loop. It generates 3-5 sub-questions from your main query, searches each one across multiple sources, extracts relevant passages, and compiles a coherent report. A research task that takes hours manually completes in minutes.\n\nThe agent uses focused sub-queries rather than one broad search, which produces more relevant results and reduces the need for follow-up searches.\n\n## How to use\n\n1. Install GPT Researcher: `pip install gpt-researcher`. Set your `OPENAI_API_KEY` and optionally a search API key (Tavily, Serper, or Bing).\n2. Define your research query as a plain text string. Optionally specify the report type (research_report, detailed_report, outline_report).\n3. Run the researcher. It plans, searches, scrapes, and writes the report autonomously. The output is a Markdown document with inline citations.\n\n## Example\n\n```python\nfrom gpt_researcher import GPTResearcher\nimport asyncio\n\nasync def main():\n    researcher = GPTResearcher(\n        query='What are the best practices for LLM evaluation in production?',\n        report_type='research_report'\n    )\n    report = await researcher.conduct_research()\n    print(report)\n\nasyncio.run(main())\n```\n\nThe agent autonomously breaks the query into sub-questions, searches the web, reads relevant pages, and produces a multi-section report with source URLs.\n\n## Related on TokRepo\n\n- [AI tools for research](\u002Fen\u002Fai-tools-for\u002Fresearch) — Research automation and analysis tools\n- [AI tools for content](\u002Fen\u002Fai-tools-for\u002Fcontent) — Content generation and writing tools\n\n## Common pitfalls\n\n- GPT Researcher makes multiple LLM calls and web searches per report. A single detailed report can use significant tokens and API credits. Monitor costs for production use.\n- Report quality depends heavily on search result quality. Configure a reliable search API (Tavily is recommended) for best results. Free search APIs may return lower-quality results.\n- The agent scrapes web pages to extract content. Some websites block automated scraping. If key sources are behind paywalls or CAPTCHAs, those sources will be missing from the report.",[100,103,106,109,112],{"q":101,"a":102},"Which LLM providers does GPT Researcher support?","GPT Researcher works with OpenAI (GPT-4o, GPT-4), Anthropic (Claude), Google (Gemini), and other providers. The default configuration uses OpenAI. You can switch providers by setting the appropriate API key and model name.",{"q":104,"a":105},"How long does a research report take to generate?","A standard research report typically takes 2-5 minutes depending on the complexity of the query, the number of sub-questions generated, and the speed of web scraping. Detailed reports with more sources take longer.",{"q":107,"a":108},"Can I customize the research process?","Yes. You can specify the report type, maximum number of sources, search depth, and which search API to use. Advanced configurations let you provide custom source URLs, restrict search domains, and adjust the report structure.",{"q":110,"a":111},"Does GPT Researcher include citations?","Yes. Every claim in the report includes an inline citation with the source URL. The report ends with a full bibliography of all sources consulted. This makes the output suitable for professional use where source verification matters.",{"q":113,"a":114},"Can GPT Researcher work with private data sources?","GPT Researcher primarily searches the public web. For private data sources, you can provide custom URLs or documents as supplementary sources. Some configurations support local document search alongside web search.",{"@context":116,"@type":117,"name":118,"description":119,"applicationCategory":120,"operatingSystem":121,"offers":122},"https:\u002F\u002Fschema.org","SoftwareApplication","GPT Researcher","Autonomous AI agent that generates comprehensive research reports with citations from web sources","DeveloperApplication","Cross-platform",{"@type":123,"price":26,"priceCurrency":124},"Offer","USD",[126,130,134],{"url":127,"anchor":128,"reason":129},"\u002Fen\u002Fai-tools-for\u002Fresearch","Research tools","GPT Researcher is a research agent",{"url":131,"anchor":132,"reason":133},"\u002Fen\u002Fai-tools-for\u002Fcontent","Content tools","Produces written reports",{"url":135,"anchor":136,"reason":137},"\u002Fen\u002Fai-tools-for\u002Fagents","AI agent tools","Autonomous agent architecture",[139,143,147],{"claim":140,"source_name":141,"source_url":142},"GPT Researcher generates research reports autonomously","GPT Researcher GitHub","https:\u002F\u002Fgithub.com\u002Fassafelovic\u002Fgpt-researcher",{"claim":144,"source_name":145,"source_url":146},"Plans sub-questions and searches multiple sources","GPT Researcher Documentation","https:\u002F\u002Fdocs.gptr.dev\u002F",{"claim":148,"source_name":149,"source_url":150},"Supports multiple LLM providers and search APIs","GPT Researcher README","https:\u002F\u002Fgithub.com\u002Fassafelovic\u002Fgpt-researcher\u002Fblob\u002Fmaster\u002FREADME.md",478,"2026-04-15T00:00:00Z",[154,209,264,318],{"id":155,"uuid":156,"slug":157,"title":158,"description":159,"author_id":160,"author_name":161,"author_avatar":11,"token_estimate":162,"time_saved":13,"model_used":163,"fork_count":13,"vote_count":13,"view_count":164,"parent_id":13,"parent_uuid":16,"lang_type":17,"steps":165,"tags":166,"has_voted":38,"visibility":21,"share_token":16,"is_featured":13,"content_hash":168,"asset_kind":40,"target_tools":169,"install_mode":44,"entrypoint":158,"risk_profile":171,"dependencies":173,"verification":178,"agent_metadata":181,"agent_fit":193,"trust":195,"provenance":198,"created_at":200,"updated_at":201,"__relatedScore":202,"__relatedReasons":203,"__sharedTags":207},221,"6764deda-6349-4f2e-a9a0-0f867ac9d5e6","autogpt-autonomous-ai-agent-platform-6764deda","AutoGPT — Autonomous AI Agent Platform","Build and deploy autonomous AI agents that accomplish goals with minimal human input. Visual builder, marketplace, and API. The original autonomous agent. 183K+ stars.","8a910e34-3180-11f1-9bc6-00163e2b0d79","Script Depot",500,"Claude Code",146,[],[167],{"id":34,"name":35,"slug":36,"icon":37},"0fce1419671503c7435f237d60b1ae2b0ca6ebc99114c00b8b1e6d01307390e6",[42,43,170],"gemini_cli",{"executes_code":38,"modifies_global_config":38,"requires_secrets":172,"uses_absolute_paths":38,"network_access":38},[],{"npm":174,"pip":175,"brew":176,"system":177},[],[],[],[],{"commands":179,"expected_files":180},[],[158],{"asset_kind":40,"target_tools":182,"install_mode":44,"entrypoint":158,"risk_profile":183,"dependencies":185,"content_hash":168,"verification":190},[42,43,170],{"executes_code":38,"modifies_global_config":38,"requires_secrets":184,"uses_absolute_paths":38,"network_access":38},[],{"npm":186,"pip":187,"brew":188,"system":189},[],[],[],[],{"commands":191,"expected_files":192},[],[158],{"target":43,"score":68,"status":69,"policy":70,"why":194,"asset_kind":40,"install_mode":44},[72,73,74,75,76,77,78],{"author_trust_level":80,"verified_publisher":38,"asset_signed_hash":168,"signature_status":81,"install_count":13,"report_count":13,"dangerous_capability_badges":196,"review_status":83,"signals":197},[],[85,86,87,88],{"owner_uuid":160,"owner_name":161,"source_url":199,"content_hash":168,"visibility":21,"created_at":200,"updated_at":201},"https:\u002F\u002Ftokrepo.com\u002Fen\u002Fworkflows\u002Fautogpt-autonomous-ai-agent-platform-6764deda","2026-03-31 08:36:29","2026-05-13 02:31:11",95.25097600212226,[204,205,206],"topic-match","same-kind","same-target",[36,208],"scripts",{"id":210,"uuid":211,"slug":212,"title":213,"description":214,"author_id":160,"author_name":161,"author_avatar":11,"token_estimate":13,"time_saved":13,"model_used":16,"fork_count":13,"vote_count":13,"view_count":215,"parent_id":13,"parent_uuid":16,"lang_type":17,"steps":216,"tags":217,"has_voted":38,"visibility":21,"share_token":16,"is_featured":13,"content_hash":219,"asset_kind":40,"target_tools":220,"install_mode":221,"entrypoint":222,"risk_profile":223,"dependencies":226,"verification":231,"agent_metadata":234,"agent_fit":246,"trust":253,"provenance":257,"created_at":259,"updated_at":260,"__relatedScore":261,"__relatedReasons":262,"__sharedTags":263},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.",114,[],[218],{"id":34,"name":35,"slug":36,"icon":37},"6179fa81eb0920907fd5ebc0611aa49dfe487e2f499350b41f4f17c8c514305a",[42,43,170],"stage_only","BabyAGI Overview",{"executes_code":38,"modifies_global_config":38,"requires_secrets":224,"uses_absolute_paths":38,"network_access":38},[225],"OPENAI_API_KEY",{"npm":227,"pip":228,"brew":229,"system":230},[],[],[],[],{"commands":232,"expected_files":233},[],[222],{"asset_kind":40,"target_tools":235,"install_mode":221,"entrypoint":222,"risk_profile":236,"dependencies":238,"content_hash":219,"verification":243},[42,43,170],{"executes_code":38,"modifies_global_config":38,"requires_secrets":237,"uses_absolute_paths":38,"network_access":38},[225],{"npm":239,"pip":240,"brew":241,"system":242},[],[],[],[],{"commands":244,"expected_files":245},[],[222],{"target":43,"score":247,"status":221,"policy":221,"why":248,"asset_kind":40,"install_mode":221},29,[72,73,249,250,251,252,78],"install_mode stage_only","policy stage_only","install_mode is stage_only","risk_profile.requires_secrets is not empty",{"author_trust_level":80,"verified_publisher":38,"asset_signed_hash":219,"signature_status":81,"install_count":13,"report_count":13,"dangerous_capability_badges":254,"review_status":83,"signals":256},[255,221],"requires_secrets",[85,86,87],{"owner_uuid":160,"owner_name":161,"source_url":258,"content_hash":219,"visibility":21,"created_at":259,"updated_at":260},"https:\u002F\u002Ftokrepo.com\u002Fen\u002Fworkflows\u002Fbabyagi-task-driven-autonomous-agent-framework-f3ff673a","2026-04-23 04:43:44","2026-05-13 02:31:10",91.09104676053042,[204,205,206],[36,208],{"id":265,"uuid":266,"slug":267,"title":268,"description":269,"author_id":160,"author_name":161,"author_avatar":11,"token_estimate":13,"time_saved":13,"model_used":16,"fork_count":13,"vote_count":13,"view_count":270,"parent_id":13,"parent_uuid":16,"lang_type":17,"steps":271,"tags":272,"has_voted":38,"visibility":21,"share_token":16,"is_featured":13,"content_hash":274,"asset_kind":40,"target_tools":275,"install_mode":44,"entrypoint":277,"risk_profile":278,"dependencies":280,"verification":285,"agent_metadata":288,"agent_fit":300,"trust":308,"provenance":311,"created_at":313,"updated_at":314,"__relatedScore":315,"__relatedReasons":316,"__sharedTags":317},2601,"6cc2b583-4771-11f1-9bc6-00163e2b0d79","asset-6cc2b583","GPT-Pilot — AI Developer Agent That Writes Full Apps","GPT-Pilot is an AI coding agent that builds complete applications from a natural language description, working iteratively with the developer through planning, coding, debugging, and testing phases like a collaborative pair programmer.",49,[],[273],{"id":34,"name":35,"slug":36,"icon":37},"87921b6a915426339a7cfe818a11423d2b8fdd85e6b6d84dced6d6c3ef69b54f",[42,276],"cursor","GPT-Pilot AI Agent",{"executes_code":38,"modifies_global_config":38,"requires_secrets":279,"uses_absolute_paths":38,"network_access":38},[],{"npm":281,"pip":282,"brew":283,"system":284},[],[],[],[],{"commands":286,"expected_files":287},[],[277],{"asset_kind":40,"target_tools":289,"install_mode":44,"entrypoint":277,"risk_profile":290,"dependencies":292,"content_hash":274,"verification":297},[42,276],{"executes_code":38,"modifies_global_config":38,"requires_secrets":291,"uses_absolute_paths":38,"network_access":38},[],{"npm":293,"pip":294,"brew":295,"system":296},[],[],[],[],{"commands":298,"expected_files":299},[],[277],{"target":43,"score":301,"status":302,"policy":303,"why":304,"asset_kind":40,"install_mode":44},66,"needs_confirmation","confirm",[305,73,74,75,306,307,78],"target_tools does not include codex","policy confirm","metadata target_tools does not include codex",{"author_trust_level":80,"verified_publisher":38,"asset_signed_hash":274,"signature_status":81,"install_count":13,"report_count":13,"dangerous_capability_badges":309,"review_status":83,"signals":310},[],[86,87,88],{"owner_uuid":160,"owner_name":161,"source_url":312,"content_hash":274,"visibility":21,"created_at":313,"updated_at":314},"https:\u002F\u002Ftokrepo.com\u002Fen\u002Fworkflows\u002Fasset-6cc2b583","2026-05-04 12:26:30","2026-05-13 02:31:14",82.54845500650403,[204,205,206],[36,208],{"id":319,"uuid":320,"slug":321,"title":322,"description":323,"author_id":324,"author_name":325,"author_avatar":11,"token_estimate":13,"time_saved":13,"model_used":16,"fork_count":13,"vote_count":13,"view_count":326,"parent_id":13,"parent_uuid":16,"lang_type":17,"steps":327,"tags":328,"has_voted":38,"visibility":21,"share_token":16,"is_featured":13,"content_hash":334,"asset_kind":40,"target_tools":335,"install_mode":44,"entrypoint":336,"risk_profile":337,"dependencies":339,"verification":344,"agent_metadata":347,"agent_fit":359,"trust":361,"provenance":364,"created_at":366,"updated_at":367,"__relatedScore":368,"__relatedReasons":369,"__sharedTags":370},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.","8a911193-3180-11f1-9bc6-00163e2b0d79","AI Open Source",96,[],[329],{"id":330,"name":331,"slug":332,"icon":333},12,"Configs","config","⚙️","836b7a0394c11d100569371d4187616aa9df50d595e0d21e26501b6387052001",[42,43,170],"SuperAGI Overview",{"executes_code":38,"modifies_global_config":38,"requires_secrets":338,"uses_absolute_paths":38,"network_access":38},[],{"npm":340,"pip":341,"brew":342,"system":343},[],[],[],[],{"commands":345,"expected_files":346},[],[336],{"asset_kind":40,"target_tools":348,"install_mode":44,"entrypoint":336,"risk_profile":349,"dependencies":351,"content_hash":334,"verification":356},[42,43,170],{"executes_code":38,"modifies_global_config":38,"requires_secrets":350,"uses_absolute_paths":38,"network_access":38},[],{"npm":352,"pip":353,"brew":354,"system":355},[],[],[],[],{"commands":357,"expected_files":358},[],[336],{"target":43,"score":68,"status":69,"policy":70,"why":360,"asset_kind":40,"install_mode":44},[72,73,74,75,76,77,78],{"author_trust_level":80,"verified_publisher":38,"asset_signed_hash":334,"signature_status":81,"install_count":13,"report_count":13,"dangerous_capability_badges":362,"review_status":83,"signals":363},[],[86,87,88],{"owner_uuid":324,"owner_name":325,"source_url":365,"content_hash":334,"visibility":21,"created_at":366,"updated_at":367},"https:\u002F\u002Ftokrepo.com\u002Fen\u002Fworkflows\u002Fsuperagi-dev-first-autonomous-ai-agent-platform-0cff6cf4","2026-04-23 04:44:25","2026-05-11 21:09:23",76.98015760139937,[204,205,206],[]]