[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"workflow-hermes-agent-self-improving-multi-channel-ai-agent-504d0a00":3,"seo:featured-workflow:504d0a00-03fe-59a3-8de7-ae5c3f3ae206:zh":39,"workflow-related-hermes-agent-self-improving-multi-channel-ai-agent-504d0a00-504d0a00-03fe-59a3-8de7-ae5c3f3ae206":84},{"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,"files":23,"tags":24,"has_voted":30,"visibility":19,"share_token":13,"is_featured":12,"content_hash":31,"asset_kind":28,"target_tools":32,"install_mode":36,"entrypoint":37,"risk_profile":38,"dependencies":40,"verification":45,"agent_metadata":48,"agent_fit":59,"trust":71,"provenance":80,"created_at":82,"updated_at":83},3273,"504d0a00-03fe-59a3-8de7-ae5c3f3ae206","hermes-agent-self-improving-multi-channel-ai-agent","Hermes Agent — Self-Improving Multi-Channel AI Agent","Hermes Agent is a self-improving CLI and gateway agent with memory, skills, cron, and multi-provider support for shared terminal and chat workflows.","8a910fec-3180-11f1-9bc6-00163e2b0d79","Agent Toolkit","https:\u002F\u002Ftokrepo.com\u002Fapple-touch-icon.png",0,"",15,"en",[17],{"id":18,"step_order":19,"title":20,"description":13,"prompt_template":21,"variables":13,"depends_on":22,"expected_output":13},3836,1,"Asset","## Quick Use\n\n1. Install on Linux\u002FmacOS\u002FWSL2:\n   ```bash\n   curl -fsSL https:\u002F\u002Fraw.githubusercontent.com\u002FNousResearch\u002Fhermes-agent\u002Fmain\u002Fscripts\u002Finstall.sh | bash\n   source ~\u002F.zshrc\n   ```\n2. Start the CLI and run guided setup:\n   ```bash\n   hermes\n   hermes setup\n   ```\n3. Verify:\n   - Run `hermes model` and `hermes tools`, then finish one conversation from the terminal.\n\n## Intro\n\nHermes Agent is a self-improving CLI and gateway agent with memory, skills, cron, and multi-provider support for shared terminal and chat workflows.\n\n- **Best for:** operators who want one open agent to span CLI, cron, and messaging channels\n- **Works with:** Python 3.11, Node.js, ripgrep, ffmpeg, Telegram\u002FSlack\u002FDiscord gateways, MCP servers\n- **Setup time:** 15-30 minutes\n\n## Practical Notes\n\n- Quant: the installer wires Python 3.11, Node.js, ripgrep, ffmpeg, and a portable Git Bash on native Windows.\n- Quant: the docs call out 40+ tools and 7 terminal backends, useful when you need a remote-first agent footprint.\n\n## Why it matters\n\nHermes is interesting because it treats agent memory and channel delivery as first-class runtime features instead of add-on scripts.\n\n- The same agent can live in terminal, Telegram, Discord, Slack, WhatsApp, Signal, and email without forcing a separate automation stack.\n- It exposes operational commands such as `hermes model`, `hermes tools`, `hermes gateway`, and `hermes doctor`, which lowers day-2 maintenance cost.\n- The README explicitly positions skills, memory search, and scheduled automations as part of the core loop, not optional demos.\n\n## Rollout pattern\n\n- Start with the CLI only and pin one provider + one toolset before you expose any gateway channel.\n- Add cron or gateway delivery only after you can replay the same task three times from the terminal with consistent evidence.\n- Use separate environments for experiments versus production because the agent can execute tools and accumulate long-lived memory.\n\n## Watchouts\n\nThe project is powerful enough to touch local systems and remote chats, so approval gates and environment separation matter more here than in a prompt-only assistant.\n\n### FAQ\n\n**Q: Does it lock me to one model vendor?**\nA: No. The README lists OpenAI, OpenRouter, NVIDIA NIM, GLM, Kimi, MiniMax, Hugging Face, and custom endpoints.\n\n**Q: Can I start from chat instead of the terminal?**\nA: Yes, but the terminal path is the cleanest first verification route before enabling gateways.\n\n**Q: What is the fastest smoke test?**\nA: Install, run `hermes setup`, pick a model, and complete one tool-free CLI conversation before enabling extra tools.\n\n## Source & Thanks\n\n> Source: https:\u002F\u002Fgithub.com\u002FNousResearch\u002Fhermes-agent\n> License: MIT\n> GitHub stars: 146,285 · forks: 22,902\n\n---\n\n\u003C!-- ZH -->\n\n## 快速使用\n\n1. 在 Linux\u002FmacOS\u002FWSL2 安装：\n   ```bash\n   curl -fsSL https:\u002F\u002Fraw.githubusercontent.com\u002FNousResearch\u002Fhermes-agent\u002Fmain\u002Fscripts\u002Finstall.sh | bash\n   source ~\u002F.zshrc\n   ```\n2. 启动 CLI 并完成向导：\n   ```bash\n   hermes\n   hermes setup\n   ```\n3. 验证：\n   - 运行 `hermes model` 与 `hermes tools`，并在终端完成一次完整对话。\n\n## 简介\n\nHermes Agent 把 CLI、消息网关、长期记忆、技能系统与定时任务放进同一套开源代理里，并支持多模型切换，适合希望把终端工作流与聊天入口统一到一个可持续运行的 AI Agent 的团队。\n\n- **适合谁：** 希望用一套开源 Agent 同时覆盖 CLI、定时任务与消息通道的团队\n- **可搭配：** Python 3.11、Node.js、ripgrep、ffmpeg、Telegram\u002FSlack\u002FDiscord 网关与 MCP servers\n- **准备时间：** 15-30 分钟\n\n## 实战建议\n\n- 量化信息：安装脚本会处理 Python 3.11、Node.js、ripgrep、ffmpeg，Windows 还会带上便携 Git Bash。\n- 量化信息：文档列出了 40+ 工具与 7 种终端后端，适合要把 Agent 跑在远端环境的团队。\n\n## 为什么值得收录\n\nHermes 的价值在于它把记忆、技能、通道接入和定时执行都做成了运行时原生能力，而不是让你再拼一层胶水脚本。\n\n- 同一个 Agent 能在终端、Telegram、Discord、Slack、WhatsApp、Signal 与邮件之间复用，减少多入口维护成本。\n- 像 `hermes model`、`hermes tools`、`hermes gateway`、`hermes doctor` 这样的运维命令已经内建，便于长期管理。\n- README 明确把技能、历史检索和定时自动化当成核心能力，而不是只给一个演示型聊天壳子。\n\n## 落地路径\n\n- 先只开 CLI，固定 1 个模型 provider 与 1 套工具集，再考虑开放消息通道。\n- 当你能在终端把同一任务稳定复现 3 次之后，再接入 cron 或外部网关。\n- 测试环境与生产环境分开，因为它既能执行工具，也会累积长期记忆。\n\n## 注意事项\n\n这类“可执行 + 可跨通道”的 Agent 比普通提示词系统风险更高，权限闸门、日志证据和环境隔离都应该更严格。\n\n### FAQ\n\n**会绑定某一家模型厂商吗？**\n答：不会。README 列出了 OpenAI、OpenRouter、NVIDIA NIM、GLM、Kimi、MiniMax、Hugging Face 和自定义端点。\n\n**能直接从聊天端开始吗？**\n答：可以，但第一次验证更建议从 CLI 开始，问题更容易定位。\n\n**最快的冒烟验证是什么？**\n答：安装后跑 `hermes setup`，选好模型，再完成一次不带外部工具的 CLI 对话。\n\n## 来源与感谢\n\n> Source: https:\u002F\u002Fgithub.com\u002FNousResearch\u002Fhermes-agent\n> License: MIT\n> GitHub stars: 146,285 · forks: 22,902\n","0",[],[25],{"id":26,"name":27,"slug":28,"icon":29},14,"CLI Tools","cli","🖥️",false,"c29fa9b0561c2a800787754276606314b7f43e493985276a4a63231d67619086",[33,34,35],"claude_code","codex","gemini_cli","single","hermes",{"executes_code":30,"modifies_global_config":30,"requires_secrets":39,"uses_absolute_paths":30,"network_access":30},null,{"npm":41,"pip":42,"brew":43,"system":44},[],[],[],[],{"commands":46,"expected_files":47},[],[20],{"asset_kind":28,"target_tools":49,"install_mode":36,"entrypoint":37,"risk_profile":50,"dependencies":51,"content_hash":31,"verification":56},[33,34,35],{"executes_code":30,"modifies_global_config":30,"requires_secrets":39,"uses_absolute_paths":30,"network_access":30},{"npm":52,"pip":53,"brew":54,"system":55},[],[],[],[],{"commands":57,"expected_files":58},[],[20],{"target":34,"score":60,"status":61,"policy":62,"why":63,"asset_kind":28,"install_mode":36},94,"native","allow",[64,65,66,67,68,69,70],"target_tools includes codex","asset_kind cli","install_mode single","markdown-only","policy allow","safe markdown-only Codex install","trust established",{"author_trust_level":72,"verified_publisher":30,"asset_signed_hash":31,"signature_status":73,"install_count":12,"report_count":12,"dangerous_capability_badges":74,"review_status":75,"signals":76},"established","hash_only",[],"unreviewed",[77,78,79],"author has published assets","content hash available","no dangerous capability badges",{"owner_uuid":9,"owner_name":10,"source_url":81,"content_hash":31,"visibility":19,"created_at":82,"updated_at":83},"https:\u002F\u002Ftokrepo.com\u002Fen\u002Fworkflows\u002Fhermes-agent-self-improving-multi-channel-ai-agent","2026-05-12 22:02:43","2026-05-14 09:30:08",[85,139,184,234],{"id":86,"uuid":87,"slug":88,"title":89,"description":90,"author_id":91,"author_name":92,"author_avatar":11,"token_estimate":12,"time_saved":12,"model_used":13,"fork_count":12,"vote_count":12,"view_count":93,"parent_id":12,"parent_uuid":13,"lang_type":15,"steps":94,"files":39,"tags":95,"has_voted":30,"visibility":19,"share_token":13,"is_featured":12,"content_hash":97,"asset_kind":28,"target_tools":98,"install_mode":99,"entrypoint":100,"risk_profile":101,"dependencies":102,"verification":107,"agent_metadata":110,"agent_fit":121,"trust":124,"provenance":127,"created_at":129,"updated_at":130,"__relatedScore":131,"__relatedReasons":132,"__sharedTags":137},3554,"c270d7b6-f7bd-50ee-9b36-a95e11417c7b","zhikuncode-self-hosted-multi-agent-coding-suite","ZhikunCode — Self-Hosted Multi-Agent Coding Suite","ZhikunCode is a self-hosted AI coding suite with browser-first control and Docker deployment; README notes the first build can take 15–30 minutes.","8a911193-3180-11f1-9bc6-00163e2b0d79","AI Open Source",18,[],[96],{"id":26,"name":27,"slug":28,"icon":29},"e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855",[33,34,35],"docker|compose","pip install -r requirements.txt",{"executes_code":30,"modifies_global_config":30,"requires_secrets":39,"uses_absolute_paths":30,"network_access":30},{"npm":103,"pip":104,"brew":105,"system":106},[],[],[],[],{"commands":108,"expected_files":109},[],[],{"asset_kind":28,"target_tools":111,"install_mode":99,"entrypoint":100,"risk_profile":112,"dependencies":113,"content_hash":97,"verification":118},[33,34,35],{"executes_code":30,"modifies_global_config":30,"requires_secrets":39,"uses_absolute_paths":30,"network_access":30},{"npm":114,"pip":115,"brew":116,"system":117},[],[],[],[],{"commands":119,"expected_files":120},[],[],{"target":34,"score":60,"status":61,"policy":62,"why":122,"asset_kind":28,"install_mode":99},[64,65,123,67,68,69,70],"install_mode docker|compose",{"author_trust_level":72,"verified_publisher":30,"asset_signed_hash":97,"signature_status":73,"install_count":12,"report_count":12,"dangerous_capability_badges":125,"review_status":75,"signals":126},[],[77,78,79],{"owner_uuid":91,"owner_name":92,"source_url":128,"content_hash":97,"visibility":19,"created_at":129,"updated_at":130},"https:\u002F\u002Ftokrepo.com\u002Fen\u002Fworkflows\u002Fzhikuncode-self-hosted-multi-agent-coding-suite","2026-05-13 14:51:50","2026-05-14 10:31:36",141.91813040142924,[133,134,135,136],"shared-tag","topic-match","same-kind","same-target",[28,138],"cli-tools",{"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":12,"parent_id":12,"parent_uuid":13,"lang_type":15,"steps":145,"files":39,"tags":146,"has_voted":30,"visibility":19,"share_token":13,"is_featured":12,"content_hash":97,"asset_kind":28,"target_tools":148,"install_mode":149,"entrypoint":150,"risk_profile":151,"dependencies":152,"verification":157,"agent_metadata":160,"agent_fit":171,"trust":174,"provenance":177,"created_at":179,"updated_at":179,"__relatedScore":180,"__relatedReasons":181,"__sharedTags":183},3712,"1a7eee44-32ea-5323-b7a1-e8d69df26610","orla-serving-library-for-multi-agent-systems","Orla — Serving Library for Multi-Agent Systems","Orla is a library for serving LLM-based multi-agent systems; verified 244★ and offers an orla daemon via Homebrew plus a Python client SDK (`pyorla`).",[],[147],{"id":26,"name":27,"slug":28,"icon":29},[33,34,35],"brew|pip","brew install --cask harvard-cns\u002Forla\u002Forla",{"executes_code":30,"modifies_global_config":30,"requires_secrets":39,"uses_absolute_paths":30,"network_access":30},{"npm":153,"pip":154,"brew":155,"system":156},[],[],[],[],{"commands":158,"expected_files":159},[],[],{"asset_kind":28,"target_tools":161,"install_mode":149,"entrypoint":150,"risk_profile":162,"dependencies":163,"content_hash":97,"verification":168},[33,34,35],{"executes_code":30,"modifies_global_config":30,"requires_secrets":39,"uses_absolute_paths":30,"network_access":30},{"npm":164,"pip":165,"brew":166,"system":167},[],[],[],[],{"commands":169,"expected_files":170},[],[],{"target":34,"score":60,"status":61,"policy":62,"why":172,"asset_kind":28,"install_mode":149},[64,65,173,67,68,69,70],"install_mode brew|pip",{"author_trust_level":72,"verified_publisher":30,"asset_signed_hash":97,"signature_status":73,"install_count":12,"report_count":12,"dangerous_capability_badges":175,"review_status":75,"signals":176},[],[77,78,79],{"owner_uuid":9,"owner_name":10,"source_url":178,"content_hash":97,"visibility":19,"created_at":179,"updated_at":179},"https:\u002F\u002Ftokrepo.com\u002Fen\u002Fworkflows\u002Forla-serving-library-for-multi-agent-systems","2026-05-14 10:46:54",140,[133,134,135,136,182],"same-author",[28,138],{"id":185,"uuid":186,"slug":187,"title":188,"description":189,"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":190,"parent_id":12,"parent_uuid":13,"lang_type":15,"steps":191,"files":39,"tags":192,"has_voted":30,"visibility":19,"share_token":13,"is_featured":12,"content_hash":97,"asset_kind":194,"target_tools":195,"install_mode":36,"entrypoint":196,"risk_profile":197,"dependencies":198,"verification":203,"agent_metadata":206,"agent_fit":217,"trust":224,"provenance":227,"created_at":229,"updated_at":230,"__relatedScore":231,"__relatedReasons":232,"__sharedTags":233},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.",21,[],[193],{"id":26,"name":27,"slug":28,"icon":29},"cli_tool",[33,34,35],"README.md",{"executes_code":30,"modifies_global_config":30,"requires_secrets":39,"uses_absolute_paths":30,"network_access":30},{"npm":199,"pip":200,"brew":201,"system":202},[],[],[],[],{"commands":204,"expected_files":205},[],[],{"asset_kind":194,"target_tools":207,"install_mode":36,"entrypoint":196,"risk_profile":208,"dependencies":209,"content_hash":97,"verification":214},[33,34,35],{"executes_code":30,"modifies_global_config":30,"requires_secrets":39,"uses_absolute_paths":30,"network_access":30},{"npm":210,"pip":211,"brew":212,"system":213},[],[],[],[],{"commands":215,"expected_files":216},[],[],{"target":34,"score":218,"status":219,"policy":219,"why":220,"asset_kind":194,"install_mode":36},29,"stage_only",[64,221,66,67,222,223,70],"asset_kind cli_tool","policy stage_only","asset_kind cli_tool is not activated directly for Codex",{"author_trust_level":72,"verified_publisher":30,"asset_signed_hash":97,"signature_status":73,"install_count":12,"report_count":12,"dangerous_capability_badges":225,"review_status":75,"signals":226},[194],[77,78],{"owner_uuid":9,"owner_name":10,"source_url":228,"content_hash":97,"visibility":19,"created_at":229,"updated_at":230},"https:\u002F\u002Ftokrepo.com\u002Fen\u002Fworkflows\u002Fhector-self-hosted-agent-runtime-binary","2026-05-12 01:55:11","2026-05-14 09:27:24",134.01363402123332,[133,134,136,182],[28,138],{"id":235,"uuid":236,"slug":237,"title":238,"description":239,"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":240,"files":39,"tags":241,"has_voted":30,"visibility":19,"share_token":13,"is_featured":12,"content_hash":97,"asset_kind":28,"target_tools":243,"install_mode":244,"entrypoint":245,"risk_profile":246,"dependencies":247,"verification":252,"agent_metadata":255,"agent_fit":266,"trust":269,"provenance":272,"created_at":274,"updated_at":275,"__relatedScore":276,"__relatedReasons":277,"__sharedTags":278},3473,"0c91e357-65d1-528d-91fa-f3e581629195","orca-multi-agent-ide-for-cli-agents","Orca — Multi-Agent IDE for CLI Agents","IDE for running multiple CLI coding agents with worktree isolation, diff review, and notifications. Works with Claude Code, Codex, OpenCode, and more.",[],[242],{"id":26,"name":27,"slug":28,"icon":29},[33,34,35],"download|brew","brew install --cask stablyai\u002Forca\u002Forca",{"executes_code":30,"modifies_global_config":30,"requires_secrets":39,"uses_absolute_paths":30,"network_access":30},{"npm":248,"pip":249,"brew":250,"system":251},[],[],[],[],{"commands":253,"expected_files":254},[],[],{"asset_kind":28,"target_tools":256,"install_mode":244,"entrypoint":245,"risk_profile":257,"dependencies":258,"content_hash":97,"verification":263},[33,34,35],{"executes_code":30,"modifies_global_config":30,"requires_secrets":39,"uses_absolute_paths":30,"network_access":30},{"npm":259,"pip":260,"brew":261,"system":262},[],[],[],[],{"commands":264,"expected_files":265},[],[],{"target":34,"score":60,"status":61,"policy":62,"why":267,"asset_kind":28,"install_mode":244},[64,65,268,67,68,69,70],"install_mode download|brew",{"author_trust_level":72,"verified_publisher":30,"asset_signed_hash":97,"signature_status":73,"install_count":12,"report_count":12,"dangerous_capability_badges":270,"review_status":75,"signals":271},[],[77,78,79],{"owner_uuid":9,"owner_name":10,"source_url":273,"content_hash":97,"visibility":19,"created_at":274,"updated_at":275},"https:\u002F\u002Ftokrepo.com\u002Fen\u002Fworkflows\u002Forca-multi-agent-ide-for-cli-agents","2026-05-13 09:19:12","2026-05-14 10:33:05",132.8061799739839,[133,134,135,136,182],[28,138]]