Hermes Agent

Health v2 · maintenance only

Adoption not part of the score

236895 stars · 47917 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

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

framework · maturity active

agent-framework chatbot llm-inference prompt-engineering workflow-automation scheduling cli terminal-ui artificial-intelligence large-language-models developer-tools python windows cli self-hosted cross-platform 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

For agents

markdown · JSON · MCP: product_card(name="NousResearch/hermes-agent")