Hermes Agent is an open-source agent harness from Nous Research built around a learning loop: it creates skills from experience after complex tasks, refines them during use, nudges itself to persist knowledge to memory, and searches its own past conversations so what it learns in one session carries into the next. You run it, choose a model, and talk to it from a terminal or a chat app.
It works with any model provider (Nous Portal, OpenRouter, OpenAI, a self-hosted endpoint, and others) and switches with hermes model or /model without code changes. One gateway process serves Telegram, Discord, Slack, WhatsApp, Signal, email, and Home Assistant, with conversations continuing across platforms and voice memos transcribed on arrival.
Tools run on one of seven terminal backends: local, Docker, SSH, Singularity, Modal, Daytona, and Vercel Sandbox. Daytona and Modal add serverless persistence, so the agent's environment hibernates when idle and wakes on demand. A built-in cron scheduler runs natural-language automations unattended and delivers results to any connected platform.
Beyond interactive use, Hermes can spawn isolated subagents for parallel workstreams, let the model write Python scripts that call tools over RPC to collapse multi-step pipelines into a single turn, and generate and compress batches of trajectories for training tool-calling models. Nous Portal optionally bundles 300+ models and a tool gateway (web search, image generation, text-to-speech, cloud browser) behind one login.
Features
- Learning loop: autonomous skill creation and self-improvement, agent-curated memory with periodic nudges, and FTS5 session search with LLM summaries for cross-session recall
- Terminal UI: multiline editing, slash-command autocomplete, conversation history, interrupt-and-redirect, and streaming tool output
- Messaging gateway: Telegram, Discord, Slack, WhatsApp, Signal, email, and Home Assistant from one process
- Provider-agnostic models: switch providers and models per conversation with /model provider:model
- Scheduled automations: cron jobs written in natural language with delivery to any platform
- Subagents and RPC scripting: parallel isolated subagents and tool calls from Python scripts
- Execution backends: local, Docker, SSH, Singularity, Modal, Daytona, and Vercel Sandbox
- Tools and toolsets: 40+ built-in tools, a toolset system, MCP server integration, and project context files
- Security controls: command approval, DM pairing, and container isolation
- Personalities and sessions: /personality, /retry, /undo, /compress, /usage, and /insights shared across CLI and chat
- Platform coverage: Linux, macOS, WSL2, Termux on Android, and native Windows, plus a desktop app
- OpenClaw migration: hermes claw migrate imports an existing OpenClaw setup
Extensions & skills
Agency Agents
Collection of specialized AI agent personas that install into Claude Code, Cursor, Codex, and other coding assistants
AtomicMemory
Portable, inspectable semantic memory for agents - one protocol across an SDK, CLI, MCP server, framework adapters and host plugins
Document Structuring
Parses PDF and DOCX files by heading into Markdown chunks in a local SQLite FTS5 store for RAG retrieval
ECC
The agent harness performance optimization system. Coordinated engineering system and toolbox.
Built with this
Integrates with
Browser Use
Python library that lets an LLM agent operate a web browser — opening pages, clicking, typing, and filling forms from a task description
-
ElevenLabs
Expressive text-to-speech with word-level timing plus file-based transcription.
Fal
Fast generative-media inference (image, audio, video) via fal serverless models.
Firecrawl
Web data API that searches, scrapes, and crawls sites into clean markdown or structured JSON for agents
Integrated by
AionUi
Free, local, open-source 24/7 Cowork app for OpenClaw, Hermes Agent, Claude Code, Codex, OpenCode, Gemini CLI and 20+ more CLI.
BrainDB
Postgres and pgvector long-term memory for LLM agents with typed entities, graph traversal, temporal decay, and a REST API
Code Review Graph
Local-first code intelligence graph for MCP and CLI. Builds a persistent map of your codebase so AI coding tools read only what matters.
Cua
Open-source sandboxes, cross-OS desktop drivers, SDKs, MCP server and benchmarks for computer-use agents.
Alternatives
Atomic Agent
Local First Ai Agent. Optimized for Local Ai models. Long context window. Proper tools callings. Runs privately on your device.
Core
Monday morning, the hard part is not opening Claude Code. It is knowing which ticket changed, which PR comment matters,
Memmy Agent
A personal AI agent & local memory hub for all AI agents, gives every AI one shared, fully controlled memory and persistent context — al
Mentioned with
Hermes Agent Desktop Lower-confidence signal
Desktop app for running AI agents with multi-provider chat, profiles, schedules, and a Kanban board
Hermes Swift Mac Lower-confidence signal
Native macOS wrapper that loads Hermes Web UI in a WKWebView over a direct or SSH-tunnel connection
Latitude Lower-confidence signal
Latitude traces your agent in production, finds the failures, and dispatches your coding agent to fix them.
