This is an early release preview. You may encounter bugs.
Framework
Hermes logo
Unclaimed

development memory messaging

Hermes

Self-improving AI agent with a learning loop that creates and refines skills, recalls past sessions, and runs across chat platforms

A 84/100 GitHub score ? This grade is derived from GitHub signals — not user votes. Open for the full breakdown.
100% recommend · 1 rater

01 / About

About Hermes.

Hermes Agent is an AI agent from Nous Research built around a closed learning loop. Rather than resetting each session, it creates skills from experience, refines them during use, is periodically nudged to persist knowledge, searches its own past conversations (FTS5 session search with LLM summarization), and builds a model of the user across sessions using Honcho dialectic user modeling. Its skills are compatible with the agentskills.io open standard.

It works with any model, switchable via hermes model without code changes (Nous Portal, OpenRouter, OpenAI, custom endpoints, and others), and is reachable from a terminal TUI or from Telegram, Discord, Slack, WhatsApp, Signal, and CLI through a single gateway, with voice-memo transcription and cross-platform continuity. It can run on a low-cost VPS, a GPU cluster, or serverless backends (six terminal backends including local, Docker, SSH, Singularity, Modal, and Daytona, with Modal and Daytona hibernating when idle). Additional features include a built-in cron scheduler with delivery to any platform, isolated subagents for parallel workstreams, and batch trajectory generation and compression for research.

02 / Discussion CREDIBILITY-GATED

Discussion · 0

Reading is open to everyone. Only verified humans or builders at GitHub B+ can post or vote — every thread carries its author's credibility.

  • No discussions yet — start the first thread.

04 / Build

Build with Hermes.

Browse the catalogue for frameworks, tools, and blueprints — each scored on real GitHub credibility.

Browse the catalogue