RSIHub

A research framework for principled agent self-improvement under frozen evaluators and declared mutation boundaries, recording verifiable lineage to make it reproducible and auditable.

simple-agent-lab/RSIHub

View on GitHub ↗

A research framework for principled agent self-improvement under frozen evaluators and declared mutation boundaries, recording verifiable lineage to make it reproducible and auditable.

RSIHub grew +106.0% in the last 30 days, ranks 1167th of 2,795 in Agent SDK / Framework, last commit 25 days ago.

Star trajectory

82 days tracked
2026-08-31379 stars today2026-11-22
Momentum

+106.0% in 30d, above the Agent SDK / Framework median of +1.4%.

Maintenance

Last commit 25 days ago, staler than the median of 15d.

How it compares in Agent SDK / Framework

RSIHub
379
stars
+106.0% 30d
commit 25 days ago
Agent SDK / Framework median
290
stars
+1.4% 30d
commit ~15d ago
Leader · rea
473.2k
stars
+28.6% 30d
commit today

Ranked 1167th of 2,795 by stars.

Ranked by shared tags, then keywords, then stars
  1. Make your agents improve themselves. Reflexio is an AI agent self-improvement harness that enables your AI…

    +7 (+1.8%) in 30d · Committed today · Python · Apache-2.0

    Shares Agent SDK / Framework, Evaluation & Guardrails

  2. Independent Auditing of AI Agents. Run by human or the agent itself, to answer the most crucial question in…

    +13.4k (+40%) in 30d · Committed yesterday · Python · Apache-2.0

    Shares Evaluation & Guardrails, Agent SDK / Framework

  3. Formal verification for AI: a Lean 4 + Dafny proof checker that catches fake AI proofs (reward hacking), and…

    +60 (+2.1%) in 30d · Committed 30d ago · Python · MIT

    Shares Evaluation & Guardrails, Agent SDK / Framework

  4. Toolkits for Recursive Self-improvement (RSI). A modular framework for recursive harness evolution.

    +336 (+191%) in 30d · Committed 3d ago · TypeScript · MIT

    Shares Agent SDK / Framework, Evaluation & Guardrails

  5. The collaboration layer for teams building AI agents. Test, simulate, and trace your agents, while domain…

    +7 (+1.8%) in 30d · Committed today · Python · Other license

    Shares Evaluation & Guardrails, Agent SDK / Framework

  6. 🔁 Improve your agent harness autonomously overnight

    +7 (+2.2%) in 30d · Committed 208d ago · Python · MIT

    Shares Agent SDK / Framework, Evaluation & Guardrails

  7. Make AI agents and AI workflows measurably reliable. Epistemic measurement, Noetic RAG, Sentinel gating, and…

    +6 (+2.4%) in 30d · Committed yesterday · Python · MIT

    Shares Evaluation & Guardrails, Agent SDK / Framework

  8. Introducing XSafeClaw: The Open-Source Agent Safety Platform from Fudan University

    +1 (+0.6%) in 30d · Committed 134d ago · Python · MIT

    Shares Evaluation & Guardrails, Agent SDK / Framework

  9. EvoPolicyGym is infrastructure for evaluating coding agents and generating training experience through…

    -22 (-13%) in 30d · Committed 36d ago · Python · MIT

    Shares Evaluation & Guardrails, Agent SDK / Framework

  10. Top Open-Source AI Engineering Platform 2026 Qyvaria Kernel

    +0 (+0.0%) in 30d · Committed today · HTML

    Shares Agent SDK / Framework, Evaluation & Guardrails

Language
Python
License
Apache License 2.0
Contributors
10
Forks
20
Watchers
3
Open issues
2
Releases
0
Created
2026-07-03
Stars this week
+12

You've seen where RSIHub stands today.

Get the moves before everyone else: the 5 Agent SDK / Framework repos climbing fastest, every Tuesday.

Free weekly digest. Double opt-in, unsubscribe anytime.

Maintain RSIHub?

Claim this page to add your own call-to-action.

Claim this page