[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-290":3},{"id":4,"name":5,"fullName":6,"owner":7,"repo":5,"description":8,"homepage":9,"htmlUrl":10,"language":11,"languages":10,"totalLinesOfCode":10,"stars":12,"forks":13,"watchers":14,"openIssues":15,"contributorsCount":16,"subscribersCount":16,"size":16,"stars1d":17,"stars7d":18,"stars30d":19,"stars90d":16,"forks30d":16,"starsTrendScore":20,"compositeScore":21,"rankGlobal":10,"rankLanguage":10,"license":22,"archived":23,"fork":23,"defaultBranch":24,"hasWiki":25,"hasPages":25,"topics":26,"createdAt":10,"pushedAt":10,"updatedAt":42,"readmeContent":43,"aiSummary":44,"trendingCount":16,"starSnapshotCount":16,"syncStatus":45,"lastSyncTime":46,"discoverSource":47},290,"hermes-agent","NousResearch\u002Fhermes-agent","NousResearch","The agent that grows with you","https:\u002F\u002Fhermes-agent.nousresearch.com",null,"Python",182712,31325,715,6254,0,1977,9964,45311,9485,120,"MIT License",false,"main",true,[27,28,29,30,31,32,33,34,35,36,5,37,38,39,40,41],"ai","ai-agent","ai-agents","anthropic","chatgpt","claude","claude-code","clawdbot","codex","hermes","llm","moltbot","nous-research","openai","openclaw","2026-06-06 04:00:15","\u003Cp align=\"center\">\n  \u003Cimg src=\"assets\u002Fbanner.png\" alt=\"Hermes Agent\" width=\"100%\">\n\u003C\u002Fp>\n\n# Hermes Agent ☤\n\n\u003Cp align=\"center\">\n  \u003Ca href=\"https:\u002F\u002Fhermes-agent.nousresearch.com\u002Fdocs\u002F\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FDocs-hermes--agent.nousresearch.com-FFD700?style=for-the-badge\" alt=\"Documentation\">\u003C\u002Fa>\n  \u003Ca href=\"https:\u002F\u002Fdiscord.gg\u002FNousResearch\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FDiscord-5865F2?style=for-the-badge&logo=discord&logoColor=white\" alt=\"Discord\">\u003C\u002Fa>\n  \u003Ca href=\"https:\u002F\u002Fgithub.com\u002FNousResearch\u002Fhermes-agent\u002Fblob\u002Fmain\u002FLICENSE\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FLicense-MIT-green?style=for-the-badge\" alt=\"License: MIT\">\u003C\u002Fa>\n  \u003Ca href=\"https:\u002F\u002Fnousresearch.com\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FBuilt%20by-Nous%20Research-blueviolet?style=for-the-badge\" alt=\"Built by Nous Research\">\u003C\u002Fa>\n  \u003Ca href=\"README.zh-CN.md\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FLang-中文-red?style=for-the-badge\" alt=\"中文\">\u003C\u002Fa>\n\u003C\u002Fp>\n\n**The self-improving AI agent built by [Nous Research](https:\u002F\u002Fnousresearch.com).** It's the only agent with a built-in learning loop — it creates skills from experience, improves them during use, nudges itself to persist knowledge, searches its own past conversations, and builds a deepening model of who you are across sessions. Run it on a $5 VPS, a GPU cluster, or serverless infrastructure that costs nearly nothing when idle. It's not tied to your laptop — talk to it from Telegram while it works on a cloud VM.\n\nUse any model you want — [Nous Portal](https:\u002F\u002Fportal.nousresearch.com), [OpenRouter](https:\u002F\u002Fopenrouter.ai) (200+ models), [NVIDIA NIM](https:\u002F\u002Fbuild.nvidia.com) (Nemotron), [Xiaomi MiMo](https:\u002F\u002Fplatform.xiaomimimo.com), [z.ai\u002FGLM](https:\u002F\u002Fz.ai), [Kimi\u002FMoonshot](https:\u002F\u002Fplatform.moonshot.ai), [MiniMax](https:\u002F\u002Fwww.minimax.io), [Hugging Face](https:\u002F\u002Fhuggingface.co), OpenAI, or your own endpoint. Switch with `hermes model` — no code changes, no lock-in.\n\n\u003Ctable>\n\u003Ctr>\u003Ctd>\u003Cb>A real terminal interface\u003C\u002Fb>\u003C\u002Ftd>\u003Ctd>Full TUI with multiline editing, slash-command autocomplete, conversation history, interrupt-and-redirect, and streaming tool output.\u003C\u002Ftd>\u003C\u002Ftr>\n\u003Ctr>\u003Ctd>\u003Cb>Lives where you do\u003C\u002Fb>\u003C\u002Ftd>\u003Ctd>Telegram, Discord, Slack, WhatsApp, Signal, and CLI — all from a single gateway process. Voice memo transcription, cross-platform conversation continuity.\u003C\u002Ftd>\u003C\u002Ftr>\n\u003Ctr>\u003Ctd>\u003Cb>A closed learning loop\u003C\u002Fb>\u003C\u002Ftd>\u003Ctd>Agent-curated memory with periodic nudges. Autonomous skill creation after complex tasks. Skills self-improve during use. FTS5 session search with LLM summarization for cross-session recall. \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fplastic-labs\u002Fhoncho\">Honcho\u003C\u002Fa> dialectic user modeling. Compatible with the \u003Ca href=\"https:\u002F\u002Fagentskills.io\">agentskills.io\u003C\u002Fa> open standard.\u003C\u002Ftd>\u003C\u002Ftr>\n\u003Ctr>\u003Ctd>\u003Cb>Scheduled automations\u003C\u002Fb>\u003C\u002Ftd>\u003Ctd>Built-in cron scheduler with delivery to any platform. Daily reports, nightly backups, weekly audits — all in natural language, running unattended.\u003C\u002Ftd>\u003C\u002Ftr>\n\u003Ctr>\u003Ctd>\u003Cb>Delegates and parallelizes\u003C\u002Fb>\u003C\u002Ftd>\u003Ctd>Spawn isolated subagents for parallel workstreams. Write Python scripts that call tools via RPC, collapsing multi-step pipelines into zero-context-cost turns.\u003C\u002Ftd>\u003C\u002Ftr>\n\u003Ctr>\u003Ctd>\u003Cb>Runs anywhere, not just your laptop\u003C\u002Fb>\u003C\u002Ftd>\u003Ctd>Seven terminal backends — local, Docker, SSH, Singularity, Modal, Daytona, and Vercel Sandbox. Daytona and Modal offer serverless persistence — your agent's environment hibernates when idle and wakes on demand, costing nearly nothing between sessions. Run it on a $5 VPS or a GPU cluster.\u003C\u002Ftd>\u003C\u002Ftr>\n\u003Ctr>\u003Ctd>\u003Cb>Research-ready\u003C\u002Fb>\u003C\u002Ftd>\u003Ctd>Batch trajectory generation, Atropos RL environments, trajectory compression for training the next generation of tool-calling models.\u003C\u002Ftd>\u003C\u002Ftr>\n\u003C\u002Ftable>\n\n---\n\n## Quick Install\n\n```bash\ncurl -fsSL https:\u002F\u002Fraw.githubusercontent.com\u002FNousResearch\u002Fhermes-agent\u002Fmain\u002Fscripts\u002Finstall.sh | bash\n```\n\nWorks on Linux, macOS, WSL2, and Android via Termux. The installer handles the platform-specific setup for you.\n\n> **Android \u002F Termux:** The tested manual path is documented in the [Termux guide](https:\u002F\u002Fhermes-agent.nousresearch.com\u002Fdocs\u002Fgetting-started\u002Ftermux). On Termux, Hermes installs a curated `.[termux]` extra because the full `.[all]` extra currently pulls Android-incompatible voice dependencies.\n>\n> **Windows:** Native Windows is not supported. Please install [WSL2](https:\u002F\u002Flearn.microsoft.com\u002Fen-us\u002Fwindows\u002Fwsl\u002Finstall) and run the command above.\n\nAfter installation:\n\n```bash\nsource ~\u002F.bashrc    # reload shell (or: source ~\u002F.zshrc)\nhermes              # start chatting!\n```\n\n---\n\n## Getting Started\n\n```bash\nhermes              # Interactive CLI — start a conversation\nhermes model        # Choose your LLM provider and model\nhermes tools        # Configure which tools are enabled\nhermes config set   # Set individual config values\nhermes gateway      # Start the messaging gateway (Telegram, Discord, etc.)\nhermes setup        # Run the full setup wizard (configures everything at once)\nhermes claw migrate # Migrate from OpenClaw (if coming from OpenClaw)\nhermes update       # Update to the latest version\nhermes doctor       # Diagnose any issues\n```\n\n📖 **[Full documentation →](https:\u002F\u002Fhermes-agent.nousresearch.com\u002Fdocs\u002F)**\n\n## CLI vs Messaging Quick Reference\n\nHermes has two entry points: start the terminal UI with `hermes`, or run the gateway and talk to it from Telegram, Discord, Slack, WhatsApp, Signal, or Email. Once you're in a conversation, many slash commands are shared across both interfaces.\n\n| Action | CLI | Messaging platforms |\n|---------|-----|---------------------|\n| Start chatting | `hermes` | Run `hermes gateway setup` + `hermes gateway start`, then send the bot a message |\n| Start fresh conversation | `\u002Fnew` or `\u002Freset` | `\u002Fnew` or `\u002Freset` |\n| Change model | `\u002Fmodel [provider:model]` | `\u002Fmodel [provider:model]` |\n| Set a personality | `\u002Fpersonality [name]` | `\u002Fpersonality [name]` |\n| Retry or undo the last turn | `\u002Fretry`, `\u002Fundo` | `\u002Fretry`, `\u002Fundo` |\n| Compress context \u002F check usage | `\u002Fcompress`, `\u002Fusage`, `\u002Finsights [--days N]` | `\u002Fcompress`, `\u002Fusage`, `\u002Finsights [days]` |\n| Browse skills | `\u002Fskills` or `\u002F\u003Cskill-name>` | `\u002F\u003Cskill-name>` |\n| Interrupt current work | `Ctrl+C` or send a new message | `\u002Fstop` or send a new message |\n| Platform-specific status | `\u002Fplatforms` | `\u002Fstatus`, `\u002Fsethome` |\n\nFor the full command lists, see the [CLI guide](https:\u002F\u002Fhermes-agent.nousresearch.com\u002Fdocs\u002Fuser-guide\u002Fcli) and the [Messaging Gateway guide](https:\u002F\u002Fhermes-agent.nousresearch.com\u002Fdocs\u002Fuser-guide\u002Fmessaging).\n\n---\n\n## Documentation\n\nAll documentation lives at **[hermes-agent.nousresearch.com\u002Fdocs](https:\u002F\u002Fhermes-agent.nousresearch.com\u002Fdocs\u002F)**:\n\n| Section | What's Covered |\n|---------|---------------|\n| [Quickstart](https:\u002F\u002Fhermes-agent.nousresearch.com\u002Fdocs\u002Fgetting-started\u002Fquickstart) | Install → setup → first conversation in 2 minutes |\n| [CLI Usage](https:\u002F\u002Fhermes-agent.nousresearch.com\u002Fdocs\u002Fuser-guide\u002Fcli) | Commands, keybindings, personalities, sessions |\n| [Configuration](https:\u002F\u002Fhermes-agent.nousresearch.com\u002Fdocs\u002Fuser-guide\u002Fconfiguration) | Config file, providers, models, all options |\n| [Messaging Gateway](https:\u002F\u002Fhermes-agent.nousresearch.com\u002Fdocs\u002Fuser-guide\u002Fmessaging) | Telegram, Discord, Slack, WhatsApp, Signal, Home Assistant |\n| [Security](https:\u002F\u002Fhermes-agent.nousresearch.com\u002Fdocs\u002Fuser-guide\u002Fsecurity) | Command approval, DM pairing, container isolation |\n| [Tools & Toolsets](https:\u002F\u002Fhermes-agent.nousresearch.com\u002Fdocs\u002Fuser-guide\u002Ffeatures\u002Ftools) | 40+ tools, toolset system, terminal backends |\n| [Skills System](https:\u002F\u002Fhermes-agent.nousresearch.com\u002Fdocs\u002Fuser-guide\u002Ffeatures\u002Fskills) | Procedural memory, Skills Hub, creating skills |\n| [Memory](https:\u002F\u002Fhermes-agent.nousresearch.com\u002Fdocs\u002Fuser-guide\u002Ffeatures\u002Fmemory) | Persistent memory, user profiles, best practices |\n| [MCP Integration](https:\u002F\u002Fhermes-agent.nousresearch.com\u002Fdocs\u002Fuser-guide\u002Ffeatures\u002Fmcp) | Connect any MCP server for extended capabilities |\n| [Cron Scheduling](https:\u002F\u002Fhermes-agent.nousresearch.com\u002Fdocs\u002Fuser-guide\u002Ffeatures\u002Fcron) | Scheduled tasks with platform delivery |\n| [Context Files](https:\u002F\u002Fhermes-agent.nousresearch.com\u002Fdocs\u002Fuser-guide\u002Ffeatures\u002Fcontext-files) | Project context that shapes every conversation |\n| [Architecture](https:\u002F\u002Fhermes-agent.nousresearch.com\u002Fdocs\u002Fdeveloper-guide\u002Farchitecture) | Project structure, agent loop, key classes |\n| [Contributing](https:\u002F\u002Fhermes-agent.nousresearch.com\u002Fdocs\u002Fdeveloper-guide\u002Fcontributing) | Development setup, PR process, code style |\n| [CLI Reference](https:\u002F\u002Fhermes-agent.nousresearch.com\u002Fdocs\u002Freference\u002Fcli-commands) | All commands and flags |\n| [Environment Variables](https:\u002F\u002Fhermes-agent.nousresearch.com\u002Fdocs\u002Freference\u002Fenvironment-variables) | Complete env var reference |\n\n---\n\n## Migrating from OpenClaw\n\nIf you're coming from OpenClaw, Hermes can automatically import your settings, memories, skills, and API keys.\n\n**During first-time setup:** The setup wizard (`hermes setup`) automatically detects `~\u002F.openclaw` and offers to migrate before configuration begins.\n\n**Anytime after install:**\n\n```bash\nhermes claw migrate              # Interactive migration (full preset)\nhermes claw migrate --dry-run    # Preview what would be migrated\nhermes claw migrate --preset user-data   # Migrate without secrets\nhermes claw migrate --overwrite  # Overwrite existing conflicts\n```\n\nWhat gets imported:\n- **SOUL.md** — persona file\n- **Memories** — MEMORY.md and USER.md entries\n- **Skills** — user-created skills → `~\u002F.hermes\u002Fskills\u002Fopenclaw-imports\u002F`\n- **Command allowlist** — approval patterns\n- **Messaging settings** — platform configs, allowed users, working directory\n- **API keys** — allowlisted secrets (Telegram, OpenRouter, OpenAI, Anthropic, ElevenLabs)\n- **TTS assets** — workspace audio files\n- **Workspace instructions** — AGENTS.md (with `--workspace-target`)\n\nSee `hermes claw migrate --help` for all options, or use the `openclaw-migration` skill for an interactive agent-guided migration with dry-run previews.\n\n---\n\n## Contributing\n\nWe welcome contributions! See the [Contributing Guide](https:\u002F\u002Fhermes-agent.nousresearch.com\u002Fdocs\u002Fdeveloper-guide\u002Fcontributing) for development setup, code style, and PR process.\n\nQuick start for contributors — clone and go with `setup-hermes.sh`:\n\n```bash\ngit clone https:\u002F\u002Fgithub.com\u002FNousResearch\u002Fhermes-agent.git\ncd hermes-agent\n.\u002Fsetup-hermes.sh     # installs uv, creates venv, installs .[all], symlinks ~\u002F.local\u002Fbin\u002Fhermes\n.\u002Fhermes              # auto-detects the venv, no need to `source` first\n```\n\nManual path (equivalent to the above):\n\n```bash\ncurl -LsSf https:\u002F\u002Fastral.sh\u002Fuv\u002Finstall.sh | sh\nuv venv venv --python 3.11\nsource venv\u002Fbin\u002Factivate\nuv pip install -e \".[all,dev]\"\nscripts\u002Frun_tests.sh\n```\n\n> **RL Training (optional):** The RL\u002FAtropos integration (`environments\u002F`) ships via the `atroposlib` and `tinker` dependencies pulled in by `.[all,dev]` — no submodule setup required.\n\n---\n\n## Community\n\n- 💬 [Discord](https:\u002F\u002Fdiscord.gg\u002FNousResearch)\n- 📚 [Skills Hub](https:\u002F\u002Fagentskills.io)\n- 🐛 [Issues](https:\u002F\u002Fgithub.com\u002FNousResearch\u002Fhermes-agent\u002Fissues)\n- 🔌 [HermesClaw](https:\u002F\u002Fgithub.com\u002FAaronWong1999\u002Fhermesclaw) — Community WeChat bridge: Run Hermes Agent and OpenClaw on the same WeChat account.\n\n---\n\n## License\n\nMIT — see [LICENSE](LICENSE).\n\nBuilt by [Nous Research](https:\u002F\u002Fnousresearch.com).\n","Hermes Agent 是一个由Nous Research开发的自我改进型AI代理。它具有内置的学习循环，能够从经验中创建技能，并在使用过程中不断优化这些技能，同时还能搜索过往对话并构建用户模型。该项目支持多种语言模型，如OpenAI、Hugging Face等，并且可以在低成本VPS或云基础设施上运行。其核心功能包括全终端界面、跨平台消息传递、自动技能提升以及定时任务自动化。适合需要持续学习和适应特定用户需求的各种场景，例如个人助理、客户服务机器人或是任何需要智能交互的应用。",2,"2026-06-06 02:33:28","top_all"]