A Python library for verifying code properties using natural language assertions.
Code verification protocol for vibe coding — every claim must have a verifiable practice anchor.
A CLI tool that verifies AI coding assistant claims against actual structural changes — catching hallucinated functions, fake calls, and missed modifications before they ship.
Anti-hallucination guardrails for AI coding agents - hybrid Skill + MCP server (6 tools) that verifies code before it is marked done. Works with Claude Code, Cursor, VS Code, Copilot.
Independent verification for AI-generated software. Prove tests, regression fixes, CI integrity, and PR claims before merge.
Codex skill for delegating bounded coding work to Antigravity CLI (agy), then independently checking Git scope and driver-owned verification before acceptance.
Evidence-driven governance for AI software agents: deterministic verdicts, isolated workers, signed evidence, kernel-controlled merges. Pre-release, MIT.
Math doesn't hallucinate. Formal verification for AI-generated Python code.
Gated orchestrator for AI-assisted software development. DevCouncil ensures that AI-generated work proves it satisfied the original intent by enforcing strict staff-engineer-style execution gates. It maps requirements to deterministic tasks, patches, and evidence via a persistent Artifact Graph.
🛡️ Automatically catch security vulnerabilities in AI-generated code
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.
Prove AI-written code, refute it with the exact failing input, or honestly abstain. Never guesses. Runs locally.
Add a description, image, and links to the code-verification topic page so that developers can more easily learn about it.
To associate your repository with the code-verification topic, visit your repo's landing page and select "manage topics."