google-research/rrsi
About the project
Research framework for automatically evolving an LLM agent's harness (prompts, tools, memory, control flow) with regularized search to avoid overfitting to the training tasks.
Useful for
- Run harness evolution on your own task set via python3 rrsi.py --domain run
- Evaluate the base harness and seed the frontier using the baseline mode
- Check the evolved harness's robustness on out-of-distribution tasks
README summarized by DeepSeek V4.1 Flash. Details may be inaccurate.
Why it’s trending
- 50 stars so far today, about 104 expected by the end of the day. The usual pace is 15 per day, so that's 6.9× as much.
- Over the last two days the pace is 4.6× that of the previous week and a half.
- The spike has held for 2 days in a row — not a one-off blip.
- The repository is 14 days old and already has 1,009 stars.
- Top new repositories this month: #99.
- Hacker News: “RRSI: Regularized Recursive Self-Improvement of Agent Harnesses” — 9 points, 1 day ago.
- About 15 forks a day — people are taking the code.
Stars per day
Bars are daily stars, the line is the usual pace. Red marks spike days.
Numbers
- Total stars
- 1,009
- Today
- 50 · ≈ 104 by evening
- Forks
- 84
- Issues and pull requests
- 4
- Watchers
- 3
- Language
- Python
- License
- Apache-2.0
- Created
- September 16, 2026
- Last push
- September 23, 2026
Star trust
Growth looks organic: forks and discussion are in line with active projects, and stars arrive unevenly, the way people give them.
These are heuristics, not a verdict: we judge by the repository’s behavior, not by a list of stargazers.
Hacker News discussions
- RRSI: Regularized Recursive Self-Improvement of Agent Harnesses9 points, September 28, 2026
Spotted in
- September 30, 2026Top new repositories this month: #99
Share
README badge
Paste it into your README — the badge shows the current magnitude and links to this page.
[](https://gitnova.dev/en/r/google-research/rrsi)More in this category
-
8.3
NVIDIA/OpenShell
A safe, private runtime for autonomous AI agents: isolated sandbox containers governed by declarative YAML policies restricting filesystem, network, and process access. Manages credential injection for agents like…
-
8.2
feder-cr/dots
Open-source web AI agent with its own patched Firefox browser that avoids detection and blocking. The model is swappable via OpenRouter, while the browser keeps a consistent identity and persistent sessions.
-
7.3
paperclipai/paperclip
Open-source Node.js and React platform for orchestrating a team of AI agents: goals, org chart, budgets, tickets and audit. Suits teams running autonomous agents (Claude Code, Codex, Cursor, etc.) and wanting to manage…
-
7.2
yetone/magpie
A menu-bar utility for macOS/Linux/Windows that lets you pick the model for each AI agent (Codex, Claude Code, Gemini CLI, etc.) and runs a local gateway translating OpenAI and Anthropic APIs between agents and…
-
7.1
rehan-remade/universal-modder
A set of skills, tools and the fal MCP for Claude Code that lets it mod almost any PC game: engine recon, reverse engineering, asset generation, in-game testing and showcase video recording.
-
7.0
mvschwarz/openrig
OpenRig is a harness orchestrator for AI coding agents: a team of agents (Claude Code and Codex) is defined in YAML and booted with one command, turning scattered terminal sessions into a managed team with a lead agent.