self-improving-ai
Formal-Verification-RSI
Formal verification for AI: a Lean 4 + Dafny proof checker that catches fake AI proofs (reward hacking), and verified recursive self-improvement (RSI) for coding agents. AI for math, physics and software engineering.
- 2.9k
- Python
- MIT
- 4 wk ago
aideml
AIDE: an LLM agent for machine learning engineering - the research Weco grew out of. Referenced in OpenAI MLE-bench.
- 1.6k
- Python
- MIT
- 5 wk ago
awesome-autoresearch
Curated list of AutoResearch use cases with optimization traces and open source implementations
- 1.1k
- CC0-1.0
- 4 mo ago
awesome-rsi
A curated research map of Recursive Self-Improvement (RSI): models, agents, harnesses, embodied systems, automated AI R&D, benchmarks, and safety.
- 1.1k
- CC0-1.0
- 20 h ago
most-capable-agent-system-prompt
A copy-paste system prompt that has your coding agent (Claude Code, Codex, Cursor) build a self-improving agent system for any computer work. Try the lead follow-up demo at the website link.
- 889
- MIT
- 6 h ago
a-evolve
The official repository of "Position: Agentic Evolution is the Path to Evolving LLMs".
- 857
- Python
- 2 wk ago
claude-smart
Turns corrections into Preferences, Project-specific skills, and Shared skills for Claude Code, Codex, and OpenCode.
- 796
- Python
- Apache-2.0
- 18 h ago
reflexio
Make your agents improve themselves. Reflexio is an AI agent self-improvement harness that enables your AI agents to continuously learn from real user interactions.
- 389
- Python
- Apache-2.0
- 20 h ago
awesome-hermes-usecases
Curated real-world use cases for Hermes Agent — the self-improving AI agent from Nous Research. Backed by primary sources.
- 304
- Python
- MIT
- 4 wk ago
evolution-kernel
Self-improving code for any git repo: give it a measurable goal, a coding agent (Claude Code or Aider) proposes changes, the kernel scores them, keeps winners and rolls back failures. Open-source AlphaEvolve / FunSearch-style evolution loop, sandboxed, with an auditable ledger.
- 121
- Python
- MIT
- 3 wk ago
Deus
A token-efficient open-source AI assistant that remembers, adapts, and improves — secured, self-hosted, and entirely yours.
- 51
- Python
- MIT
- 8 d ago
POK-Agent
POK-Agent: a Windows computer-use AI agent. A large model plans (System 2) and a small fast model acts on screen (System 1: JEV or local Laya). Repeated tasks become muscle memory, so the big model is called less every time. Local-first, voice and vision, Rust + Tauri, open source.
- 3
- Rust
- Apache-2.0
- 13 d ago
molten
Run a coding model at 300+ tok/s on your Mac. Native Rust + Metal inference engine for LiquidAI LFM2.5-24B-A2B (MLX 4-bit) on Apple Silicon.
- 29
- Metal
- Apache-2.0
- 3 wk ago
agent-harness
Skills, rules and hooks that turn Claude Code, Codex or any AGENTS.md agent into a product team, CEO or portfolio manager: size the job, finish it, verify it, ask the owner one action at a time, improve itself.
- 0
- Shell
- MIT
- 5 d ago
agentic-clustering-bayesian
This project applies self-improving (Agentic) clustering with Bayesian Optimization to bridge maintenance data in some Prefecture, Japan, to automatically identify bridge groups with high maintenance priority.
- 0
- Python
- 12 mo ago
agentic-clustering
This tool applies self-improving (Agentic) clustering to bridge maintenance data in Open data at some Prefecture, Japan, to automatically identify bridge groups with high maintenance priority.
- 0
- Python
- 12 mo ago








