[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"workflow-openfang-open-source-agent-operating-system-e6513dd2":3,"seo:featured-workflow:e6513dd2-0683-4cb0-b111-1734977daae4:fr":38,"workflow-related-openfang-open-source-agent-operating-system-e6513dd2-e6513dd2-0683-4cb0-b111-1734977daae4":81},{"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":28,"visibility":19,"share_token":13,"is_featured":12,"content_hash":29,"asset_kind":30,"target_tools":31,"install_mode":35,"entrypoint":36,"risk_profile":37,"dependencies":39,"verification":44,"agent_metadata":47,"agent_fit":58,"trust":69,"provenance":77,"created_at":79,"updated_at":80},3139,"e6513dd2-0683-4cb0-b111-1734977daae4","openfang-open-source-agent-operating-system","OpenFang — Open-Source Agent Operating System","OpenFang is an open-source Agent Operating System in Rust that runs autonomous agents as one binary with built-in sandboxing and gateways.","8a911193-3180-11f1-9bc6-00163e2b0d79","AI Open Source","https:\u002F\u002Ftokrepo.com\u002Fapple-touch-icon.png",0,"",14,"en",[17],{"id":18,"step_order":19,"title":20,"description":13,"prompt_template":21,"variables":13,"depends_on":22,"expected_output":13},3702,1,"Asset","## Quick Use\n\n1. Install \u002F run:\n   ```bash\n   curl -fsSL https:\u002F\u002Fopenfang.sh\u002Finstall | sh\n   ```\n2. Start \u002F smoke test:\n   ```bash\n   openfang init\n   ```\n3. Verify:\n   - Complete the Getting Started flow from the docs and run one tiny autonomous workflow end-to-end before opening network or write permissions.\n\n## Intro\n\nOpenFang is an open-source Agent Operating System in Rust that runs autonomous agents as one binary with built-in sandboxing and gateways.\n\n- **Best for:** Developers who want a single-binary, deployable Agent OS approach (not just a chat framework) for long-running autonomous work\n- **Works with:** Rust-based runtime; installs via the project install script and uses official docs for getting started\n- **Setup time:** 20 minutes\n\n## How to Use It Well\n\n- Setup time ~20 minutes (install + `openfang init` + smallest quickstart)\n- The README calls out quantitative engineering signals (LOC\u002Ftests\u002Fversion) you can use as a maturity check\n- GitHub stars + forks (verified): see Source & Thanks\n\nAgent OS thinking shifts focus from “prompting” to “operations”: installation, sandboxing, gateways, and reproducible long-running jobs. Adopt it when you’re ready to treat agents like services with guardrails.\n\n### FAQ\n\n**Q: Is it “just another agent framework”?**\nA: The README positions it as an Agent Operating System with a single-binary runtime and system-level concerns.\n\n**Q: How do I keep autonomy safe?**\nA: Start in a sandboxed, least-privilege mode and add capabilities gradually with explicit approvals.\n\n**Q: What’s the first integration step?**\nA: Follow the official Getting Started docs and validate one minimal workflow before customizing gateways\u002Ftools.\n\n## Source & Thanks\n\n> Source: https:\u002F\u002Fgithub.com\u002FRightNow-AI\u002Fopenfang\n> License: Apache-2.0\n> GitHub stars: 17,421 · forks: 2,224\n\n---\n\n\u003C!-- ZH -->\n\n## 快速使用\n\n1. 安装 \u002F 运行：\n   ```bash\n   curl -fsSL https:\u002F\u002Fopenfang.sh\u002Finstall | sh\n   ```\n2. 启动 \u002F 冒烟测试：\n   ```bash\n   openfang init\n   ```\n3. 验证：\n   - Complete the Getting Started flow from the docs and run one tiny autonomous workflow end-to-end before opening network or write permissions.\n\n## 简介\n\nOpenFang 是用 Rust 构建的开源 Agent OS：单二进制安装运行，主打可部署与可审计的自治代理。它提供内置 gateway 与 sandbox 思路，适合把“长期自主执行”做成稳定服务并逐步加权限边界。\n\n- **适合谁：** 希望用“可部署、单二进制”的 Agent OS 思路做长期自治任务的开发者（而不是只做聊天框架）\n- **可搭配：** Rust 运行时；可通过项目安装脚本安装，并按官方文档入门\n- **准备时间：** 20 分钟\n\n## 实战建议\n\n- 上手约 20 分钟（安装 + `openfang init` + 跑通最小 quickstart）\n- README 给出了 LOC\u002F测试数\u002F版本等量化信号，可作为成熟度参考\n- GitHub stars + forks（已核验）：见「来源与感谢」\n\nAgent OS 思路把重心从“提示词”转向“运维与边界”：安装、sandbox、gateway、可复现的长期任务。当你准备把 agent 当服务来治理时，它会更合适。\n\n### FAQ\n\n**它只是另一个框架吗？**\nA: README 的定位更接近 Agent Operating System：强调单二进制运行时与系统级能力边界。\n\n**自治怎么做安全？**\nA: 先用 sandbox + 最小权限模式起步，再用明确审批逐步放开能力。\n\n**第一步怎么接入？**\nA: 按官方 Getting Started 文档跑通一个最小工作流，再开始定制 gateway\u002F工具。\n\n## 来源与感谢\n\n> Source: https:\u002F\u002Fgithub.com\u002FRightNow-AI\u002Fopenfang\n> License: Apache-2.0\n> GitHub stars: 17,421 · forks: 2,224\n","0",[24],{"id":14,"name":25,"slug":26,"icon":27},"CLI Tools","cli","🖥️",false,"0c28d1ef7d5a20773fd76d6bf4ba22238c0fe427bde2c86fe2feb969a09cc109","cli_tool",[32,33,34],"claude_code","codex","gemini_cli","single","README.md",{"executes_code":28,"modifies_global_config":28,"requires_secrets":38,"uses_absolute_paths":28,"network_access":28},null,{"npm":40,"pip":41,"brew":42,"system":43},[],[],[],[],{"commands":45,"expected_files":46},[],[20],{"asset_kind":30,"target_tools":48,"install_mode":35,"entrypoint":36,"risk_profile":49,"dependencies":50,"content_hash":29,"verification":55},[32,33,34],{"executes_code":28,"modifies_global_config":28,"requires_secrets":38,"uses_absolute_paths":28,"network_access":28},{"npm":51,"pip":52,"brew":53,"system":54},[],[],[],[],{"commands":56,"expected_files":57},[],[20],{"target":33,"score":59,"status":60,"policy":60,"why":61,"asset_kind":30,"install_mode":35},29,"stage_only",[62,63,64,65,66,67,68],"target_tools includes codex","asset_kind cli_tool","install_mode single","markdown-only","policy stage_only","asset_kind cli_tool is not activated directly for Codex","trust established",{"author_trust_level":70,"verified_publisher":28,"asset_signed_hash":29,"signature_status":71,"install_count":12,"report_count":12,"dangerous_capability_badges":72,"review_status":73,"signals":74},"established","hash_only",[30],"unreviewed",[75,76],"author has published assets","content hash available",{"owner_uuid":9,"owner_name":10,"source_url":78,"content_hash":29,"visibility":19,"created_at":79,"updated_at":80},"https:\u002F\u002Ftokrepo.com\u002Fen\u002Fworkflows\u002Fopenfang-open-source-agent-operating-system","2026-05-12 04:56:52","2026-05-14 06:19:54",[82,132,177,222],{"id":83,"uuid":84,"slug":85,"title":86,"description":87,"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":88,"parent_id":12,"parent_uuid":13,"lang_type":15,"steps":89,"tags":90,"has_voted":28,"visibility":19,"share_token":13,"is_featured":12,"content_hash":92,"asset_kind":30,"target_tools":93,"install_mode":35,"entrypoint":36,"risk_profile":94,"dependencies":95,"verification":100,"agent_metadata":103,"agent_fit":114,"trust":116,"provenance":119,"created_at":121,"updated_at":122,"__relatedScore":123,"__relatedReasons":124,"__sharedTags":130},3108,"25799792-379e-4d8c-a8c7-85034a2129d9","openllm-serve-open-source-llms","OpenLLM — Serve Open-Source LLMs","Serve open-source LLMs with a unified CLI, multiple backends, and production deployment paths. Start with `openllm hello`, then serve a real model.",12,[],[91],{"id":14,"name":25,"slug":26,"icon":27},"e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855",[32,33,34],{"executes_code":28,"modifies_global_config":28,"requires_secrets":38,"uses_absolute_paths":28,"network_access":28},{"npm":96,"pip":97,"brew":98,"system":99},[],[],[],[],{"commands":101,"expected_files":102},[],[],{"asset_kind":30,"target_tools":104,"install_mode":35,"entrypoint":36,"risk_profile":105,"dependencies":106,"content_hash":92,"verification":111},[32,33,34],{"executes_code":28,"modifies_global_config":28,"requires_secrets":38,"uses_absolute_paths":28,"network_access":28},{"npm":107,"pip":108,"brew":109,"system":110},[],[],[],[],{"commands":112,"expected_files":113},[],[],{"target":33,"score":59,"status":60,"policy":60,"why":115,"asset_kind":30,"install_mode":35},[62,63,64,65,66,67,68],{"author_trust_level":70,"verified_publisher":28,"asset_signed_hash":92,"signature_status":71,"install_count":12,"report_count":12,"dangerous_capability_badges":117,"review_status":73,"signals":118},[30],[75,76],{"owner_uuid":9,"owner_name":10,"source_url":120,"content_hash":92,"visibility":19,"created_at":121,"updated_at":122},"https:\u002F\u002Ftokrepo.com\u002Fen\u002Fworkflows\u002Fopenllm-serve-open-source-llms","2026-05-12 03:00:18","2026-05-14 00:55:40",145.67091502846026,[125,126,127,128,129],"shared-tag","topic-match","same-kind","same-target","same-author",[26,131],"cli-tools",{"id":133,"uuid":134,"slug":135,"title":136,"description":137,"author_id":138,"author_name":139,"author_avatar":11,"token_estimate":12,"time_saved":12,"model_used":13,"fork_count":12,"vote_count":12,"view_count":140,"parent_id":12,"parent_uuid":13,"lang_type":15,"steps":141,"tags":142,"has_voted":28,"visibility":19,"share_token":13,"is_featured":12,"content_hash":92,"asset_kind":30,"target_tools":144,"install_mode":35,"entrypoint":36,"risk_profile":145,"dependencies":146,"verification":151,"agent_metadata":154,"agent_fit":165,"trust":167,"provenance":170,"created_at":172,"updated_at":173,"__relatedScore":174,"__relatedReasons":175,"__sharedTags":176},3102,"4a6bad3c-a22a-49b3-868a-5999b9a5db2c","hector-self-hosted-agent-runtime-binary","Hector — Self-Hosted Agent Runtime Binary","Run Hector as a self-hosted agent runtime: a single Go binary that serves an agent API and studio UI, keeping execution on your own infrastructure.","8a910fec-3180-11f1-9bc6-00163e2b0d79","Agent Toolkit",11,[],[143],{"id":14,"name":25,"slug":26,"icon":27},[32,33,34],{"executes_code":28,"modifies_global_config":28,"requires_secrets":38,"uses_absolute_paths":28,"network_access":28},{"npm":147,"pip":148,"brew":149,"system":150},[],[],[],[],{"commands":152,"expected_files":153},[],[],{"asset_kind":30,"target_tools":155,"install_mode":35,"entrypoint":36,"risk_profile":156,"dependencies":157,"content_hash":92,"verification":162},[32,33,34],{"executes_code":28,"modifies_global_config":28,"requires_secrets":38,"uses_absolute_paths":28,"network_access":28},{"npm":158,"pip":159,"brew":160,"system":161},[],[],[],[],{"commands":163,"expected_files":164},[],[],{"target":33,"score":59,"status":60,"policy":60,"why":166,"asset_kind":30,"install_mode":35},[62,63,64,65,66,67,68],{"author_trust_level":70,"verified_publisher":28,"asset_signed_hash":92,"signature_status":71,"install_count":12,"report_count":12,"dangerous_capability_badges":168,"review_status":73,"signals":169},[30],[75,76],{"owner_uuid":138,"owner_name":139,"source_url":171,"content_hash":92,"visibility":19,"created_at":172,"updated_at":173},"https:\u002F\u002Ftokrepo.com\u002Fen\u002Fworkflows\u002Fhector-self-hosted-agent-runtime-binary","2026-05-12 01:55:11","2026-05-14 00:28:01",120.61877186907144,[125,126,127,128],[26,131],{"id":178,"uuid":179,"slug":180,"title":181,"description":182,"author_id":183,"author_name":184,"author_avatar":11,"token_estimate":12,"time_saved":12,"model_used":13,"fork_count":12,"vote_count":12,"view_count":185,"parent_id":12,"parent_uuid":13,"lang_type":15,"steps":186,"tags":187,"has_voted":28,"visibility":19,"share_token":13,"is_featured":12,"content_hash":92,"asset_kind":30,"target_tools":189,"install_mode":35,"entrypoint":36,"risk_profile":190,"dependencies":191,"verification":196,"agent_metadata":199,"agent_fit":210,"trust":212,"provenance":215,"created_at":217,"updated_at":218,"__relatedScore":219,"__relatedReasons":220,"__sharedTags":221},3088,"405e1e05-5c75-4703-9659-e65e181d3a2e","open-interpreter-local-code-interpreter-cli","Open Interpreter — Local Code Interpreter CLI","Open Interpreter runs a local code interpreter in your terminal. Install from GitHub, run `interpreter`, then write files and run commands with approvals.","8a910e34-3180-11f1-9bc6-00163e2b0d79","Script Depot",10,[],[188],{"id":14,"name":25,"slug":26,"icon":27},[32,33,34],{"executes_code":28,"modifies_global_config":28,"requires_secrets":38,"uses_absolute_paths":28,"network_access":28},{"npm":192,"pip":193,"brew":194,"system":195},[],[],[],[],{"commands":197,"expected_files":198},[],[],{"asset_kind":30,"target_tools":200,"install_mode":35,"entrypoint":36,"risk_profile":201,"dependencies":202,"content_hash":92,"verification":207},[32,33,34],{"executes_code":28,"modifies_global_config":28,"requires_secrets":38,"uses_absolute_paths":28,"network_access":28},{"npm":203,"pip":204,"brew":205,"system":206},[],[],[],[],{"commands":208,"expected_files":209},[],[],{"target":33,"score":59,"status":60,"policy":60,"why":211,"asset_kind":30,"install_mode":35},[62,63,64,65,66,67,68],{"author_trust_level":70,"verified_publisher":28,"asset_signed_hash":92,"signature_status":71,"install_count":12,"report_count":12,"dangerous_capability_badges":213,"review_status":73,"signals":214},[30],[75,76],{"owner_uuid":183,"owner_name":184,"source_url":216,"content_hash":92,"visibility":19,"created_at":217,"updated_at":218},"https:\u002F\u002Ftokrepo.com\u002Fen\u002Fworkflows\u002Fopen-interpreter-local-code-interpreter-cli","2026-05-12 00:58:30","2026-05-14 00:59:56",120.56208902773734,[125,126,127,128],[26,131],{"id":223,"uuid":224,"slug":225,"title":226,"description":227,"author_id":183,"author_name":184,"author_avatar":11,"token_estimate":12,"time_saved":12,"model_used":13,"fork_count":12,"vote_count":12,"view_count":140,"parent_id":12,"parent_uuid":13,"lang_type":15,"steps":228,"tags":229,"has_voted":28,"visibility":19,"share_token":13,"is_featured":12,"content_hash":92,"asset_kind":30,"target_tools":231,"install_mode":35,"entrypoint":36,"risk_profile":232,"dependencies":233,"verification":238,"agent_metadata":241,"agent_fit":252,"trust":254,"provenance":257,"created_at":259,"updated_at":260,"__relatedScore":261,"__relatedReasons":262,"__sharedTags":263},3101,"8029d015-2365-4580-8fe6-56cc52b5f612","pipelock-mcp-firewall-for-agent-egress","Pipelock — MCP Firewall for Agent Egress","Run Pipelock as an agent firewall\u002Fproxy to scan MCP traffic for injection, secrets, SSRF, and risky tool chains; integrate with Claude Code fast.",[],[230],{"id":14,"name":25,"slug":26,"icon":27},[32,33,34],{"executes_code":28,"modifies_global_config":28,"requires_secrets":38,"uses_absolute_paths":28,"network_access":28},{"npm":234,"pip":235,"brew":236,"system":237},[],[],[],[],{"commands":239,"expected_files":240},[],[],{"asset_kind":30,"target_tools":242,"install_mode":35,"entrypoint":36,"risk_profile":243,"dependencies":244,"content_hash":92,"verification":249},[32,33,34],{"executes_code":28,"modifies_global_config":28,"requires_secrets":38,"uses_absolute_paths":28,"network_access":28},{"npm":245,"pip":246,"brew":247,"system":248},[],[],[],[],{"commands":250,"expected_files":251},[],[],{"target":33,"score":59,"status":60,"policy":60,"why":253,"asset_kind":30,"install_mode":35},[62,63,64,65,66,67,68],{"author_trust_level":70,"verified_publisher":28,"asset_signed_hash":92,"signature_status":71,"install_count":12,"report_count":12,"dangerous_capability_badges":255,"review_status":73,"signals":256},[30],[75,76],{"owner_uuid":183,"owner_name":184,"source_url":258,"content_hash":92,"visibility":19,"created_at":259,"updated_at":260},"https:\u002F\u002Ftokrepo.com\u002Fen\u002Fworkflows\u002Fpipelock-mcp-firewall-for-agent-egress","2026-05-12 01:55:10","2026-05-14 00:25:00",117.61877186907144,[125,126,127,128],[26,131]]