GitHub · Lean

lisresearchgroup/math-rsi

MathRSI - A self-improving agent harness for mathematical discovery and proof: shared 5-stage research loop, domain plugins, workspace memory & verifiable proofs(Lean 4, DRAT) for Claude Code and Codex.

Stars
63
Forks
8
Stars gained in 24 hours
+5
Forks gained in 24 hours
+2

Topics: agent-harness, ai-for-math, ai-research, aris, autonomous-agents, claude-code, claude-code-skills, codex, combinatorics, discrete-mathematics

Latest data point: Nov 22, 2026 · 63 stars · 8 forks

Open on GitHub