Sign in
← Back to search
github Not archived

sahibzada-allahyar/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.

1 awesome list

Quick read

Stars
2,858
Forks
127
Open issues
149
Commits
7

Activity and growth

Latest capture 2026-10-28 10:56

Stars · last 7 days
0 0.0%
Commits · last 7 days
0 0.0%
Stars since tracking
0
Stored snapshots
1

Compare the starting count and capture dates, not just the percentage. How to read GitHub star growth. Missing history is not zero growth.

Classification

Topics

#ai-agents #ai-for-math #ai-for-science #ai-safety #autoformalization #automated-theorem-proving #coding-agents #dafny #formal-methods #formal-verification #lean4 #llm #program-verification #proof-assistant #recursive-self-improvement #reward-hacking #rsi #self-improving-ai #theorem-proving #verified-code

Technology stack

pytest

Metadata

Language
Python
License
MIT
Default branch
main
Created
2025-02-22
First commit
2026-10-22
Last pushed
2026-10-22
GitHub updated
2026-10-27
Last synced
2026-10-28 10:56
Stack scanned
2026-10-28 10:56
Archived
No

Archive status reflects the last catalog sync, not a maintenance assessment. Check recent releases, issue responses, and fit for your project with the repository shortlisting checklist.

Sign in to like sahibzada-allahyar/Formal-Verification-RSI
README Open website View on GitHub

AI development signals

2 paths

Agent instructions and tool configuration found in this repository.

Claude Code 2

View paths

Growth history

Tracked growth

1 observed capture since 2026-10-28. Observed captures are shown by default.

Stars from first capture 0

Chart data

Observed captures only

Time horizon

All tracked data

Custom date range

Stars history

Observed snapshots

Commits history

Observed snapshots

Similar repositories

Nearest indexed repositories by embedding similarity.

llm-as-a-verifier/llm-as-a-verifier

LLM-as-a-Verifier is a general-purpose framework that provides fine-grained feedback for any agent without requiring additional training. It achieves SOTA performance across coding, robotics, and medical agentic benchmarks.

3,320 stars
Python 1 awesome list

Leonxlnx/unlazy

Anti-laziness skill for AI agents. Core: the Depth Tree method, which splits a task N layers deep and gives every leaf the full time budget of the whole task, so effort multiplies with depth. Grounded in 2025-2026 research on model laziness, underthinking and premature completion.

3,988 stars
JavaScript 1 awesome list

0xmariowu/AgentLint

The linter for your agent harness. Works with Claude Code, Codex, and Cursor.

59 stars
Shell 1 awesome list

ninjahawk/livenerf

Benchmark for tracking model capability after release.

1,592 stars
Python 0 awesome lists

raphaelchristi/harness-evolver

Automated harness evolution for AI agents. A Claude Code plugin that iteratively optimizes system prompts, routing, retrieval, and orchestration code using full-trace counterfactual diagnosis. Based on Meta-Harness (Lee et al., 2026).

56 stars
Python 1 awesome list

LucasDuys/forge

Turn a one-line idea into a branch with tested, reviewed, committed code. The brainstorm-to-commit pipeline for Claude Code.

56 stars
JavaScript 1 awesome list