A Python library for verifying code properties using natural language assertions.
Prove an AI-written fix actually fixes the bug. mini-ork certify reproduces the bug against your repo's own code, attacks the patch with generated invariants in a Docker sandbox, and returns PROVEN / REFUTED / UNVERIFIED with a JSON certificate. Part of a verifier-gated, multi-model agent runtime.
A CLI tool that verifies AI coding assistant claims against actual structural changes — catching hallucinated functions, fake calls, and missed modifications before they ship.
Checks the math in your code: proves a function equals its formula or returns the exact input that breaks it. Also an exact math engine and MCP server for AI agents (SymPy + NumPy).
Code verification protocol for vibe coding — every claim must have a verifiable practice anchor.
The verification layer for AI coding agents. Headron computes what proof each change owes, holds the landing until receipts exist, and keeps the evidence. Any agent, any model, any chat. CLI, MCP, CI.
Evidence-driven autonomous software repair powered by NVIDIA Nemotron and Nebius Token Factory.
agy-worker: a skill for Codex and Claude Code to delegate bounded repository work to Antigravity CLI (agy), then independently verify the candidate before acceptance.
Zero-Trust Verification Fabric for AI-Generated Software.
Sub-50ms Neuro-Symbolic Verification Oracle for AI Coding Agents
Code-validation kernel for AI-assisted development: source-bound signed evidence, deterministic acceptance gates and a verifiable audit trail. MIT.
An open-source verification skill for Claude Code that validates AI-generated code through automated testing, security scanning, API contract checks, browser workflows, and evidence-based diagnostics.
Independent verification for AI-generated software. Prove tests, regression fixes, CI integrity, and PR claims before merge.
Dash app for the Verification and Validation platform for DET’s code comparison exercises
Turn claims about code into executable checks and revocable warrants. Re-check affected claims as code changes, without model calls during verification.
Certus is a finetuned model that generates machine-checkable correctness certificates for Python functions, plus a checker that verifies them with counterexample search. 83% of certificates survive Hypothesis testing on unseen code.
AI-agent fixes to real C/C++ bugs, independently verified by Unfix
Evidence-based compatibility registry and verification layer for AI coding agents via MCP.
Jev-style decision models fine-tuned to judge cheap-model code: data pipeline, training image, fine-tunes
AI + deterministic code verifier that catches outdated README and docs claims and fixes them. Powered by Gemma 4 & UltSQL.
To associate your repository with the code-verification topic, visit your repo's landing page and select "manage topics."