NousResearch/hermes-agent
The official Hermes Agent — the open-source autonomous agent this whole site is built around. Start here.
The agent that grows with you
A hand-picked list of open-source repositories worth knowing when you build with Hermes Agent — the core agent itself, plus the tooling, SDKs, and integrations the community reaches for most. Know one we missed? Suggest a repo.
26 repos
The official Hermes Agent — the open-source autonomous agent this whole site is built around. Start here.
The agent that grows with you
The community awesome-list for Hermes — a curated index of skills, tools, integrations, and resources. A great map of the whole ecosystem.
Independent directory of useful skills, plugins, memory providers, tools, surfaces, and guides for Nous Research's open-source Hermes Agent.
Run open models locally with a simple API — great for testing Hermes skills offline or routing to a local model.
Get up and running with Kimi-K2.6, GLM-5.2, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.
Ready-to-run MCP servers (filesystem, git, search, and more) you can plug into Hermes to extend what your agent can do.
Model Context Protocol Servers
An open-source app for managing agents at work — a polished control surface for running, organizing, and collaborating with agents like Hermes across your team.
The open-source app everyone uses to manage agents at work
The most popular Telegram bot framework — handy when wiring Hermes up to a custom Telegram gateway or bot.
We have made you a wrapper you can't refuse
TypeScript toolkit for building AI apps and agents — useful for the web tooling and dashboards around your Hermes setup.
The AI Toolkit for TypeScript. From the creators of Next.js, the AI SDK is a free open-source library for building AI-powered applications and agents
Build your own MCP tools and integrations in Python and expose them to Hermes as first-class capabilities.
The official Python SDK for Model Context Protocol servers and clients
Self-hosted orchestration platform for agent fleets — dispatch tasks, run multi-agent workflows, monitor spend, and apply ops governance from one control center.
Self-hosted control plane for AI agents: dispatch tasks, review runs, track spend, and operate OpenClaw, Claude Code, Codex, and other runtimes.
A multi-persona AI council that deliberates your hardest decisions across multiple providers in structured, multi-round debate — great for high-stakes agent reasoning.
Structured multi-perspective deliberation for hard decisions. Run full councils, focused triads, or duo debates across Claude Code, Codex, Gemini CLI, and OpenCode.
Official ElevenLabs SDK for Text to Speech and Speech to Text — the easiest way to give your Hermes Agent a voice.
The official Python SDK for the ElevenLabs API.
Reference implementation and prompts for structured function calling with the Hermes models — the backbone of tool use.
Function-calling format, prompts, and examples for the Hermes models.
A browser-native side panel that connects the web page you're on to your local Hermes runtime — hand the agent live web context without copy-paste.
Browser-native side panel for Hermes Agent — connect web context to your local Hermes runtime.
A control-room-first template for managing a Hermes fleet — from one agent on a VPS to orchestrated specialist teams. Clone it and point your coding agent at it.
Control Room-first template for managing Hermes agents from one VPS agent to specialist teams and orchestrated workflows
A community-curated list of reasoning tasks — useful for designing skills, evaluating agents, and stress-testing prompts.
A comprehensive repository of reasoning tasks for LLMs (and beyond)
An open-source marketing ops control center for AI agent teams — CRM, outreach, content, and analytics in one place.
Local-first marketing operations control center for CRM, outreach, content, analytics, approvals, automations, and agent workflows.
A control-plane-grade harness for Claude, Codex, and Hermes — adds policy gates, verification loops, persistent memory, and auditability around your agents.
Local-first policy, evidence, memory, and recovery controls for Claude, Codex, Hermes, and other CLI coding agents.
A Hermes-native, local-first credential broker, scanner, and encrypted vault — keep your agent's secrets and API keys safe instead of scattered in plaintext.
Hermes-native local-first credential broker, scanner, and encrypted vault.
An X Intelligence CLI to search, monitor, analyze, and engage on X/Twitter — wire it into Hermes to give your agent eyes and a voice on X.
Local-first X Intelligence CLI for search, monitoring, analysis, exports, OAuth actions, and agent tooling.
A practical sovereign-agent stack — scripts, on-chain identity, and knowledge graphs for giving an agent durable memory and identity.
Curated map of AI agent frameworks, protocols, runtimes, skills, memory, identity, security, evaluation, and commerce.
A GPT-style chat front end wired to Hermes Agent — talk to your agent through a familiar conversational UI.
ChatGPT with keys to your machine. What could go wrong?
A self-hosted temporal knowledge-graph memory layer for agents (FalkorDB + Graphiti) with a hippocampus-style management layer — give Hermes durable, time-aware memory.
Synapse — Temporal knowledge graph memory for AI agents. Self-hosted FalkorDB + Graphiti with hippocampus-layer memory management.
A Solana dApp scaffold (Next.js 14, TypeScript, Tailwind, Material UI, web3.js) — a fast starting point when building on-chain tooling around your agent.
Builderz Solana dApp Scaffold (Nextjs14, App Dir, Typescript, TailwindCSS, MaterialUI, web3.js, ThemeSwitch (Dark/Light), Sonner Toast Notifications, Modal & Drawer)
A local-first bridge that speaks the Agent-to-Agent (A2A) Protocol, letting your Hermes Agent talk to other agents over the HTTP+JSON subset.
Archived — superseded by built-in Hermes A2A (https://hermes-agent.nousresearch.com/docs/user-guide/messaging/a2a)
An interactive ASCII dragon playground showcasing text interaction and visual effects — a fun, hackable demo of expressive terminal UIs.
Interactive ASCII dragon playground built with @chenglou/pretext — text measurement without DOM reflow. Features physics-based letter interaction, fire breathing, 3D text tunnel, floating enemies, and a full control panel.
A battle-tested migration tool for moving an existing OpenClaw setup over to Hermes Agent with minimal friction.
Migrate from OpenClaw to Hermes Agent — complete, battle-tested migration tool