PHOSPHOR//NIGHT_MARKET
01 // overview
⚚

Hermes Agent

The self-improving AI agent built by Nous Research. The only agent with a built-in learning loop.

by NousResearch · productivity

Hermes Agent from Nous Research — not a coding copilot tethered to an IDE or a chatbot wrapper around a single API. An autonomous agent that gets more capable the longer it runs, with a closed learning loop: agent-curated memory, autonomous skill creation, skill self-improvement during use, and FTS5 cross-session recall. Lives across 19+ messaging platforms (Telegram, Discord, Slack, WhatsApp, Signal, Matrix, MS Teams, Email, SMS, and more) and runs anywhere — $5 VPS, GPU cluster, or serverless. Source + install at https://github.com/NousResearch/hermes-agent.

// street lore

Hermes is not a coding copilot tethered to an IDE or a chatbot wrapper around a single API. He's an autonomous agent that gets more capable the longer he runs — agent-curated memory, autonomous skill creation, skill self-improvement during use, FTS5 cross-session recall. Drop him on a $5 VPS, a GPU cluster, or serverless, and bridge him into Telegram / Discord / Slack via the gateway. The longer you keep him alive, the more skills he writes for himself. Built by Nous Research — same lab behind Hermes, Nomos, and Psyche.

SealedDeclaredObserved
self-improvinglearning-looptelegramdiscordslackmcpskills
runtime image
ttl.sh/joe888777-phosphor-hermes-real-1778492735-ad401926:24h
manifest ref
pm.hermes-agent.v1
section 02 // upstream docs
synced fromhttps://github.com/NousResearch/hermes-agent@ faa13e4· license MIT· fetched 2026-05-08T05:22:24.126Z

Hermes Agent

Hermes Agent ☤

Documentation Discord License: MIT Built by Nous Research 中文

The self-improving AI agent built by Nous Research. 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.

Use any model you want — Nous Portal, OpenRouter (200+ models), NVIDIA NIM (Nemotron), Xiaomi MiMo, z.ai/GLM, Kimi/Moonshot, MiniMax, Hugging Face, OpenAI, or your own endpoint. Switch with hermes model — no code changes, no lock-in.

A real terminal interfaceFull TUI with multiline editing, slash-command autocomplete, conversation history, interrupt-and-redirect, and streaming tool output.
Lives where you doTelegram, Discord, Slack, WhatsApp, Signal, and CLI — all from a single gateway process. Voice memo transcription, cross-platform conversation continuity.
A closed learning loopAgent-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. Honcho dialectic user modeling. Compatible with the agentskills.io open standard.
Scheduled automationsBuilt-in cron scheduler with delivery to any platform. Daily reports, nightly backups, weekly audits — all in natural language, running unattended.
Delegates and parallelizesSpawn isolated subagents for parallel workstreams. Write Python scripts that call tools via RPC, collapsing multi-step pipelines into zero-context-cost turns.
Runs anywhere, not just your laptopSeven 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.
Research-readyBatch trajectory generation, Atropos RL environments, trajectory compression for training the next generation of tool-calling models.

Quick Install

curl -fsSL https://raw.githubusercontent.com/NousResearch/hermes-agent/main/scripts/install.sh | bash

Works on Linux, macOS, WSL2, and Android via Termux. The installer handles the platform-specific setup for you.

Android / Termux: The tested manual path is documented in the Termux guide. On Termux, Hermes installs a curated .[termux] extra because the full .[all] extra currently pulls Android-incompatible voice dependencies.

Windows: Native Windows is not supported. Please install WSL2 and run the command above.

After installation:

source ~/.bashrc    # reload shell (or: source ~/.zshrc)
hermes              # start chatting!

Getting Started

hermes              # Interactive CLI — start a conversation
hermes model        # Choose your LLM provider and model
hermes tools        # Configure which tools are enabled
hermes config set   # Set individual config values
hermes gateway      # Start the messaging gateway (Telegram, Discord, etc.)
hermes setup        # Run the full setup wizard (configures everything at once)
hermes claw migrate # Migrate from OpenClaw (if coming from OpenClaw)
hermes update       # Update to the latest version
hermes doctor       # Diagnose any issues

📖 Full documentation →

CLI vs Messaging Quick Reference

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.

ActionCLIMessaging platforms
Start chattinghermesRun hermes gateway setup + hermes gateway start, then send the bot a message
Start fresh conversation/new or /reset/new or /reset
Change model/model [provider:model]/model [provider:model]
Set a personality/personality [name]/personality [name]
Retry or undo the last turn/retry, /undo/retry, /undo
Compress context / check usage/compress, /usage, /insights [--days N]/compress, /usage, /insights [days]
Browse skills/skills or /<skill-name>/<skill-name>
Interrupt current workCtrl+C or send a new message/stop or send a new message
Platform-specific status/platforms/status, /sethome

For the full command lists, see the CLI guide and the Messaging Gateway guide.

Documentation

All documentation lives at hermes-agent.nousresearch.com/docs:

SectionWhat's Covered
QuickstartInstall → setup → first conversation in 2 minutes
CLI UsageCommands, keybindings, personalities, sessions
ConfigurationConfig file, providers, models, all options
Messaging GatewayTelegram, Discord, Slack, WhatsApp, Signal, Home Assistant
SecurityCommand approval, DM pairing, container isolation
Tools & Toolsets40+ tools, toolset system, terminal backends
Skills SystemProcedural memory, Skills Hub, creating skills
MemoryPersistent memory, user profiles, best practices
MCP IntegrationConnect any MCP server for extended capabilities
Cron SchedulingScheduled tasks with platform delivery
Context FilesProject context that shapes every conversation
ArchitectureProject structure, agent loop, key classes
ContributingDevelopment setup, PR process, code style
CLI ReferenceAll commands and flags
Environment VariablesComplete env var reference

Migrating from OpenClaw

If you're coming from OpenClaw, Hermes can automatically import your settings, memories, skills, and API keys.

During first-time setup: The setup wizard (hermes setup) automatically detects ~/.openclaw and offers to migrate before configuration begins.

Anytime after install:

hermes claw migrate              # Interactive migration (full preset)
hermes claw migrate --dry-run    # Preview what would be migrated
hermes claw migrate --preset user-data   # Migrate without secrets
hermes claw migrate --overwrite  # Overwrite existing conflicts

What gets imported:

  • SOUL.md — persona file
  • Memories — MEMORY.md and USER.md entries
  • Skills — user-created skills → ~/.hermes/skills/openclaw-imports/
  • Command allowlist — approval patterns
  • Messaging settings — platform configs, allowed users, working directory
  • API keys — allowlisted secrets (Telegram, OpenRouter, OpenAI, Anthropic, ElevenLabs)
  • TTS assets — workspace audio files
  • Workspace instructions — AGENTS.md (with --workspace-target)

See hermes claw migrate --help for all options, or use the openclaw-migration skill for an interactive agent-guided migration with dry-run previews.

Contributing

We welcome contributions! See the Contributing Guide for development setup, code style, and PR process.

Quick start for contributors — clone and go with setup-hermes.sh:

git clone https://github.com/NousResearch/hermes-agent.git
cd hermes-agent
./setup-hermes.sh     # installs uv, creates venv, installs .[all], symlinks ~/.local/bin/hermes
./hermes              # auto-detects the venv, no need to `source` first

Manual path (equivalent to the above):

curl -LsSf https://astral.sh/uv/install.sh | sh
uv venv .venv --python 3.11
source .venv/bin/activate
uv pip install -e ".[all,dev]"
scripts/run_tests.sh

RL Training (optional): The RL/Atropos integration (environments/) — see CONTRIBUTING.md for the full setup.

Community

License

MIT — see LICENSE.

Built by Nous Research.

03 // permissions
required permissions — visible before deploypm-hermes-agent-v1@1.1.0
tools
HttpRequestReadWriteNotify
fs.read
/workspace/in
fs.write
/workspace/out
net
api.anthropic.comapi.openai.comopenrouter.aiapi.groq.comgenerativelanguage.googleapis.comapi.telegram.orgdiscord.comslack.com
env
ANTHROPIC_API_KEYOPENAI_API_KEYOPENROUTER_API_KEYGROQ_API_KEYBASE_URLOPENAI_BASE_URLMODELTELEGRAM_BOT_TOKENTELEGRAM_TOKENTELEGRAM_CHAT_IDDISCORD_BOT_TOKENDISCORD_TOKENDISCORD_CHANNEL_IDSLACK_BOT_TOKENSLACK_SIGNING_SECRETHERMES_YOLO_MODEHERMES_LANGUAGEHERMES_HOME
limits
cpu=1mem=1024mbruntime≤600sfile≤10mb

Policy: default-deny. Anything not declared above is rejected by the sandbox at runtime.

04 // try it now
▲ in-marketplace preview — not the real Hermes

This panel runs a small triage helper inside phosphor-web so you can see your LLM key + Telegram bot fire end-to-end. It is NOT the NousResearch Hermes agent (closed learning loop, skill creation, MCP, 19+ gateways). The real Hermes runs as its own long-lived container — packaging lives under services/hermes-real/ and the deploy form is in section 05.

Skip the provisioning queue. JACK IN to execute this agent inside phosphor-web right now — mock mode works without an API key.

05 // deploy to sealed runtime
// provider

Keys validated against manifest.env.allowedEnvKeys — unknown keys reject the deploy.

recent runs // last 24h
  • ● run_hrm_01H9K42026-04-14 06:01:00Z9.8striaged 87 messages // 4 action, 11 meeting, 23 info, 49 skip // morning briefing drafted
  • ● run_hrm_01H9J92026-04-13 18:17:22Z7.3sslack #oncall: 3 alerts clustered // drafted reply to 2 DMs // LINE family chat: skip
  • ● run_hrm_01H9F52026-04-13 22:00:04Z10.2sgmail: 142 threads scanned // 6 invoices flagged // 1 meeting accepted // audit ledger: OK