☤hermes-agent
NousResearch/hermes-agent · homepage ↗
The agent that grows with you
⭐ Hugely popular: 231k stars, gaining about 4k a week
View on GitHub ↗repo profile
momentum
durability
bus factor = how many people it takes to cover more than half the commits (6 months). 1 is a solo project; higher means the work is spread across a team. top-author share is the single busiest author's slice of those commits.
since we covered it
why it's a big deal
- One of the few open agents that treats memory and skill accumulation as first-class infrastructure rather than an afterthought.
- Complex tasks trigger autonomous skill creation, those skills self-improve in use, and the agent builds a persistent user model across sessions.
- Offers an OpenClaw migration path, designed to absorb that project's installed base as it moves to foundation governance.
under the hood
- A Python agent core with a full TUI for multiline editing, slash-command autocomplete, history, and interrupt-and-redirect.
- Skills follow the open agentskills.io standard.
- Includes Atropos RL environments and trajectory-compression tooling, plus a one-line installer for Linux, macOS, and WSL2.
our take from PR#31, 2026-04-08
star history
- PR#31 27k 2026-04-08
- now 231k + 204k since first covered
curve is sampled from GitHub's star history, plus our own daily readings since we covered it; the dashed stretch is before we first covered it, the solid line since. figures at coverage are the numbers we printed then (approx.), current count is live.
understory
Output and attention are roughly in balance.
- output, commits & releases
- clout, star velocity
output = commits & releases; clout = star velocity, both 0 to 100 monthly indices; the gap where output runs above clout is the understory. The understory →
covered in
-
Self-improving, platform-agnostic AI agent with a built-in learning loop
similar projects
compare these →- 🧠 oh-my-opencode
TypeScript · leaner, 68k stars
omo/lazycodex: The coding agent for tokenmaxxers;the one and only agent harness for complex codebases. For your Codex, for your OpenCode
68k ACTIVE - 🗜️ headroom
leaner, 66k stars
Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95% fewer tokens for JSON, same answers. Library, proxy, MCP server.
66k ACTIVE - 🧠 LangGraph
leaner, 40k stars
Build resilient agents.
40k ACTIVE
comments
Sign in with GitHub to add your blip on hermes-agent.