
Validates security patches with baseline-versus-patched evidence and adversarial checks
- Open source
- 8.2K GitHub stars
- Security

Validates security patches with baseline-versus-patched evidence and adversarial checks

Finds candidate regressions in a pinned code change by tracing its callers

Pins before and after source states and gathers PR or commit context for regressions

Coordinates multi-agent hunts for regressions in PRs and commits with staged verification

Builds an interactive HTML walkthrough of branch changes with review findings

Runs independent code reviews of changes through Codex or Antigravity CLIs

Runs structural security checks on a branch or PR diff before merge

Guides an agent through changing, refactoring or reviewing NVIDIA FastGen library code

Splits a large PR into smaller ones that each need fewer CODEOWNERS reviewer groups

Guides agents on NeMo-RL documentation: docs/index.md placement and Google-style

Guides preparing NVSHMEM CUDA kernels to use TMA shared-memory transfers

Guides agents to write and review production Cloudflare Workers code with current checks
Offline review that flags agent changes which weaken tests, assertions or CI
Runs locallyProduction-aware review of changes against your AWS or Google Cloud setup, via MCP
Governed engineering agents, skills and audit trail served over MCP to your own LLM
Not checked yetSearch issues, code reviews, CI runs, deployments and team docs in Code4
Turns stakeholder pins on a live web app into work your coding agent can fix
Runs locallyFree first read of a trading bot or EA's code and trade record for faults and luck
Skills, rules and slash commands that push coding agents to verify before saying done
Runs locallyOpen-source MCP server scoring pull-request risk from blast radius and git history
Runs locallyGodot 4.7 reference, checks and safe edits so coding agents stop inventing APIs
Runs locallyMulti-model review council and parallel model sidecar for Claude Code
Runs locallyEntity-level code diffs, impact analysis and blame for coding agents
Runs locally
Rules, reasons and runnable checks that help AI agents design, code and write for people
Not checked yetShared rooms, locks and task claims so coding agents from different vendors collaborate
Runs locallyLocal, deterministic repository context and merge-readiness checks for coding agents
Runs locallyIndependent review of AI-written code before commit, plus pull request impact checks
Not checked yetTurn a coding agent's session into an Intent Document checked against the diff
Runs locally
Pack a local or remote repository into one AI-readable file for LLMs and agents
Runs locally
Hand coding tasks from Claude Code or Cursor to the OpenAI Codex CLI and review the diff
Runs locally