Skip to content
repository radar
Agents & Orchestration
Repo of the Month May 2026 · +75% Repo of the Month Apr 2026 · +151%

hermes-agent

ACTIVE BREAKOUT

NousResearch/hermes-agent · homepage ↗

The agent that grows with you

⭐ Hugely popular: 231k stars, gaining about 4k a week

View on GitHub ↗

repo profile

vintage 2025 1 year old
delivery library
language Python
license MIT

momentum

total stars 231k
stars added last week +4k
weekly downloads 93k /wk · PyPI
commits / week 1110 steady · -12% vs prior mo
issues closed 61% ~13d to close, median
contributors 3k (+357 in 15d)
release cadence weekly
last activity today

durability

backing VC-backed Nous Research (Paradigm)
openness permissive
bus factor 2 concentrated
top-author share 38% 6 mo

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

monthly average + 47k/mo (+175%/mo) · + 204k total since PR#31

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 · 27k231k now Jul 2025Aug 2026
  1. PR#31 27k 2026-04-08
  2. 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.

+0 understory score output 100 · clout 100
Aug 2025 Jul 2026
  • 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

  • PR#31 2026-04-08 on the radar

    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.

loading comments…