# Hermes Agent

The agent that grows with you

Repository: https://github.com/NousResearch/hermes-agent
Canonical: https://ross.abutalabs.com/products/hermes-agent
Homepage: https://hermes-agent.nousresearch.com
Language: Python
License: MIT
License Family: permissive
Topics: ai, ai-agent, ai-agents, llm, anthropic, chatgpt, claude, claude-code, codex, hermes, hermes-agent, nous-research, openai
Last push: 2026-08-27T00:43:01+00:00

## Health v2 (maintenance only)
Score: 85/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 99, release rhythm 98, longevity 29
- inputs: {"age_days": 407, "days_push": 7, "days_rel": 12, "gap_med": 4.5, "n_releases_24m": 29}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 236895, forks 47917 (observed 2026-08-28T04:12:28.460779+00:00)

## What it is
Hermes Agent is a self-improving AI agent framework by Nous Research that builds skills from experience, maintains curated memory, and models users across sessions. It runs on a terminal TUI or cloud infrastructure and connects to Telegram, Discord, Slack, WhatsApp, and Signal through a single gateway, with pluggable LLM providers.

## Use cases
- run a personal AI agent that remembers me across sessions
- chat with my agent from Telegram while it works on a cloud VM
- build an agent that creates and improves its own skills
- automate scheduled tasks with an LLM agent
- use one agent across Telegram, Discord, and Slack
- switch between OpenAI, OpenRouter, and custom LLM endpoints without code changes
- search past agent conversations for context

## When to choose
- you want a persistent, self-improving agent with memory and skill learning
- you need one agent reachable from multiple messaging platforms
- you want provider-agnostic LLM usage with no vendor lock-in
- you want to self-host an agent on a cheap VPS or serverless infra

## When to avoid
- you need a simple stateless chatbot with no memory
- you want a fully managed hosted agent service
- you need a GUI-only experience without terminal or CLI
- you require non-Python integration out of the box

## Facets
- artifact type: framework
- maturity: active
- function: agent-framework, chatbot, llm-inference, prompt-engineering, workflow-automation, scheduling, cli, terminal-ui
- domain: artificial-intelligence, large-language-models, developer-tools
- platform: python, windows, cli, self-hosted, cross-platform
- tags: self-improving-agent, memory, skills, multi-provider-llm, messaging-gateway, tui, voice-transcription, nous-research, ai-agents, automation, linux, macos, docker, telegram, discord

## Member repositories
- NousResearch/hermes-agent (main) score 85
- NousResearch/hermes-agent-self-evolution (plugin) score 54
- NousResearch/hermes-paperclip-adapter (plugin) score 48

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:12:28.460779+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T16:10:29.546577+00:00, confidence not recorded.
  - readme: https://github.com/NousResearch/hermes-agent (fetched 2026-08-28T04:12:28.460779+00:00, sha 6dc9564271f8)
- Data as of 2026-08-30T08:39:29.467469+00:00.