/ README.md
README.md
1 <p align="center"> 2 <img src="assets/banner.png" alt="Hermes Agent" width="100%"> 3 </p> 4 5 # Hermes Agent ☤ 6 7 <p align="center"> 8 <a href="https://hermes-agent.nousresearch.com/docs/"><img src="https://img.shields.io/badge/Docs-hermes--agent.nousresearch.com-FFD700?style=for-the-badge" alt="Documentation"></a> 9 <a href="https://discord.gg/NousResearch"><img src="https://img.shields.io/badge/Discord-5865F2?style=for-the-badge&logo=discord&logoColor=white" alt="Discord"></a> 10 <a href="https://github.com/NousResearch/hermes-agent/blob/main/LICENSE"><img src="https://img.shields.io/badge/License-MIT-green?style=for-the-badge" alt="License: MIT"></a> 11 <a href="https://nousresearch.com"><img src="https://img.shields.io/badge/Built%20by-Nous%20Research-blueviolet?style=for-the-badge" alt="Built by Nous Research"></a> 12 </p> 13 14 **The self-improving AI agent built by [Nous Research](https://nousresearch.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. 15 16 Use any model you want — [Nous Portal](https://portal.nousresearch.com), [OpenRouter](https://openrouter.ai) (200+ models), [NVIDIA NIM](https://build.nvidia.com) (Nemotron), [Xiaomi MiMo](https://platform.xiaomimimo.com), [z.ai/GLM](https://z.ai), [Kimi/Moonshot](https://platform.moonshot.ai), [MiniMax](https://www.minimax.io), [Hugging Face](https://huggingface.co), OpenAI, or your own endpoint. Switch with `hermes model` — no code changes, no lock-in. 17 18 <table> 19 <tr><td><b>A real terminal interface</b></td><td>Full TUI with multiline editing, slash-command autocomplete, conversation history, interrupt-and-redirect, and streaming tool output.</td></tr> 20 <tr><td><b>Lives where you do</b></td><td>Telegram, Discord, Slack, WhatsApp, Signal, and CLI — all from a single gateway process. Voice memo transcription, cross-platform conversation continuity.</td></tr> 21 <tr><td><b>A closed learning loop</b></td><td>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. <a href="https://github.com/plastic-labs/honcho">Honcho</a> dialectic user modeling. Compatible with the <a href="https://agentskills.io">agentskills.io</a> open standard.</td></tr> 22 <tr><td><b>Scheduled automations</b></td><td>Built-in cron scheduler with delivery to any platform. Daily reports, nightly backups, weekly audits — all in natural language, running unattended.</td></tr> 23 <tr><td><b>Delegates and parallelizes</b></td><td>Spawn isolated subagents for parallel workstreams. Write Python scripts that call tools via RPC, collapsing multi-step pipelines into zero-context-cost turns.</td></tr> 24 <tr><td><b>Runs anywhere, not just your laptop</b></td><td>Six terminal backends — local, Docker, SSH, Daytona, Singularity, and Modal. 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.</td></tr> 25 <tr><td><b>Research-ready</b></td><td>Batch trajectory generation, Atropos RL environments, trajectory compression for training the next generation of tool-calling models.</td></tr> 26 </table> 27 28 --- 29 30 ## Quick Install 31 32 ```bash 33 curl -fsSL https://raw.githubusercontent.com/NousResearch/hermes-agent/main/scripts/install.sh | bash 34 ``` 35 36 Works on Linux, macOS, WSL2, and Android via Termux. The installer handles the platform-specific setup for you. 37 38 > **Android / Termux:** The tested manual path is documented in the [Termux guide](https://hermes-agent.nousresearch.com/docs/getting-started/termux). On Termux, Hermes installs a curated `.[termux]` extra because the full `.[all]` extra currently pulls Android-incompatible voice dependencies. 39 > 40 > **Windows:** Native Windows is not supported. Please install [WSL2](https://learn.microsoft.com/en-us/windows/wsl/install) and run the command above. 41 42 After installation: 43 44 ```bash 45 source ~/.bashrc # reload shell (or: source ~/.zshrc) 46 hermes # start chatting! 47 ``` 48 49 --- 50 51 ## Getting Started 52 53 ```bash 54 hermes # Interactive CLI — start a conversation 55 hermes model # Choose your LLM provider and model 56 hermes tools # Configure which tools are enabled 57 hermes config set # Set individual config values 58 hermes gateway # Start the messaging gateway (Telegram, Discord, etc.) 59 hermes setup # Run the full setup wizard (configures everything at once) 60 hermes claw migrate # Migrate from OpenClaw (if coming from OpenClaw) 61 hermes update # Update to the latest version 62 hermes doctor # Diagnose any issues 63 ``` 64 65 📖 **[Full documentation →](https://hermes-agent.nousresearch.com/docs/)** 66 67 ## CLI vs Messaging Quick Reference 68 69 Hermes 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. 70 71 | Action | CLI | Messaging platforms | 72 |---------|-----|---------------------| 73 | Start chatting | `hermes` | Run `hermes gateway setup` + `hermes gateway start`, then send the bot a message | 74 | Start fresh conversation | `/new` or `/reset` | `/new` or `/reset` | 75 | Change model | `/model [provider:model]` | `/model [provider:model]` | 76 | Set a personality | `/personality [name]` | `/personality [name]` | 77 | Retry or undo the last turn | `/retry`, `/undo` | `/retry`, `/undo` | 78 | Compress context / check usage | `/compress`, `/usage`, `/insights [--days N]` | `/compress`, `/usage`, `/insights [days]` | 79 | Browse skills | `/skills` or `/<skill-name>` | `/<skill-name>` | 80 | Interrupt current work | `Ctrl+C` or send a new message | `/stop` or send a new message | 81 | Platform-specific status | `/platforms` | `/status`, `/sethome` | 82 83 For the full command lists, see the [CLI guide](https://hermes-agent.nousresearch.com/docs/user-guide/cli) and the [Messaging Gateway guide](https://hermes-agent.nousresearch.com/docs/user-guide/messaging). 84 85 --- 86 87 ## Documentation 88 89 All documentation lives at **[hermes-agent.nousresearch.com/docs](https://hermes-agent.nousresearch.com/docs/)**: 90 91 | Section | What's Covered | 92 |---------|---------------| 93 | [Quickstart](https://hermes-agent.nousresearch.com/docs/getting-started/quickstart) | Install → setup → first conversation in 2 minutes | 94 | [CLI Usage](https://hermes-agent.nousresearch.com/docs/user-guide/cli) | Commands, keybindings, personalities, sessions | 95 | [Configuration](https://hermes-agent.nousresearch.com/docs/user-guide/configuration) | Config file, providers, models, all options | 96 | [Messaging Gateway](https://hermes-agent.nousresearch.com/docs/user-guide/messaging) | Telegram, Discord, Slack, WhatsApp, Signal, Home Assistant | 97 | [Security](https://hermes-agent.nousresearch.com/docs/user-guide/security) | Command approval, DM pairing, container isolation | 98 | [Tools & Toolsets](https://hermes-agent.nousresearch.com/docs/user-guide/features/tools) | 40+ tools, toolset system, terminal backends | 99 | [Skills System](https://hermes-agent.nousresearch.com/docs/user-guide/features/skills) | Procedural memory, Skills Hub, creating skills | 100 | [Memory](https://hermes-agent.nousresearch.com/docs/user-guide/features/memory) | Persistent memory, user profiles, best practices | 101 | [MCP Integration](https://hermes-agent.nousresearch.com/docs/user-guide/features/mcp) | Connect any MCP server for extended capabilities | 102 | [Cron Scheduling](https://hermes-agent.nousresearch.com/docs/user-guide/features/cron) | Scheduled tasks with platform delivery | 103 | [Context Files](https://hermes-agent.nousresearch.com/docs/user-guide/features/context-files) | Project context that shapes every conversation | 104 | [Architecture](https://hermes-agent.nousresearch.com/docs/developer-guide/architecture) | Project structure, agent loop, key classes | 105 | [Contributing](https://hermes-agent.nousresearch.com/docs/developer-guide/contributing) | Development setup, PR process, code style | 106 | [CLI Reference](https://hermes-agent.nousresearch.com/docs/reference/cli-commands) | All commands and flags | 107 | [Environment Variables](https://hermes-agent.nousresearch.com/docs/reference/environment-variables) | Complete env var reference | 108 109 --- 110 111 ## Migrating from OpenClaw 112 113 If you're coming from OpenClaw, Hermes can automatically import your settings, memories, skills, and API keys. 114 115 **During first-time setup:** The setup wizard (`hermes setup`) automatically detects `~/.openclaw` and offers to migrate before configuration begins. 116 117 **Anytime after install:** 118 119 ```bash 120 hermes claw migrate # Interactive migration (full preset) 121 hermes claw migrate --dry-run # Preview what would be migrated 122 hermes claw migrate --preset user-data # Migrate without secrets 123 hermes claw migrate --overwrite # Overwrite existing conflicts 124 ``` 125 126 What gets imported: 127 - **SOUL.md** — persona file 128 - **Memories** — MEMORY.md and USER.md entries 129 - **Skills** — user-created skills → `~/.hermes/skills/openclaw-imports/` 130 - **Command allowlist** — approval patterns 131 - **Messaging settings** — platform configs, allowed users, working directory 132 - **API keys** — allowlisted secrets (Telegram, OpenRouter, OpenAI, Anthropic, ElevenLabs) 133 - **TTS assets** — workspace audio files 134 - **Workspace instructions** — AGENTS.md (with `--workspace-target`) 135 136 See `hermes claw migrate --help` for all options, or use the `openclaw-migration` skill for an interactive agent-guided migration with dry-run previews. 137 138 --- 139 140 ## Contributing 141 142 We welcome contributions! See the [Contributing Guide](https://hermes-agent.nousresearch.com/docs/developer-guide/contributing) for development setup, code style, and PR process. 143 144 Quick start for contributors — clone and go with `setup-hermes.sh`: 145 146 ```bash 147 git clone https://github.com/NousResearch/hermes-agent.git 148 cd hermes-agent 149 ./setup-hermes.sh # installs uv, creates venv, installs .[all], symlinks ~/.local/bin/hermes 150 ./hermes # auto-detects the venv, no need to `source` first 151 ``` 152 153 Manual path (equivalent to the above): 154 155 ```bash 156 curl -LsSf https://astral.sh/uv/install.sh | sh 157 uv venv venv --python 3.11 158 source venv/bin/activate 159 uv pip install -e ".[all,dev]" 160 scripts/run_tests.sh 161 ``` 162 163 > **RL Training (optional):** The RL/Atropos integration (`environments/`) ships via the `atroposlib` and `tinker` dependencies pulled in by `.[all,dev]` — no submodule setup required. 164 165 --- 166 167 ## Community 168 169 - 💬 [Discord](https://discord.gg/NousResearch) 170 - 📚 [Skills Hub](https://agentskills.io) 171 - 🐛 [Issues](https://github.com/NousResearch/hermes-agent/issues) 172 - 🔌 [HermesClaw](https://github.com/AaronWong1999/hermesclaw) — Community WeChat bridge: Run Hermes Agent and OpenClaw on the same WeChat account. 173 174 --- 175 176 ## License 177 178 MIT — see [LICENSE](LICENSE). 179 180 Built by [Nous Research](https://nousresearch.com).