Open Kritt

Open Kritt is an open-source, self-hosted AI vulnerability research tool that orchestrates agents to find and validate security issues in code.

Open Kritt is an AI security research tool that orchestrates multiple agents to find and validate vulnerabilities in codebases. It decomposes codebases into focused tasks, runs parallel agent research, performs verification passes, and ranks findings according to custom severity rules. The platform is available as a self-hosted, open-source engine under the AGPL-3.0 license or as a managed scanning service operated by the company team. Users can bring models like Codex or Claude Code and target local or GitHub repositories. It is built for security researchers and development teams seeking to automate vulnerability discovery and exploit validation.

Open Kritt at a glance

Best for: Software engineer
Runs on: Web, Self-hosted, Open source
Pricing: Open source is free; managed scans and enterprise plans require custom scoping and quotes.
Released: July 2026
Category: AI coding tool
Website: kritt.ai

Key features

Decompose codebases into security tasks
Run parallel agent research across functions
Execute verification passes per finding
Rank, normalize, and de-duplicate findings
Self-host the open-source engine
Target local or GitHub repositories
Bring Codex or Claude Code models

Use it for

Find vulnerabilities in local or GitHub repositories
Run parallel security research agents
Validate exploit paths and build proofs of concept
Rank and de-duplicate security findings

Companions

Tools that articles about Open Kritt recommend using with it, each with its job.

Context7 — Provides up-to-date documentation for AI agents and code editors.
Ollama — Run local models at zero marginal cost, with code kept on your machine.
OpenRouter — Access over 500 models and 80 providers through one unified API.
Daytona — Runs sessions in isolated sandboxes synced to git branches.
Composio — Equips AI agents with tools, managed user auth, and sandboxes across 1,500+ apps
Oh My OpenCode Slim — Lightweight multi-agent orchestration and background tasks.

Alternatives to Open Kritt

OpenCode — Works with 75+ model providers, local models, and existing subscriptions
OpenSandbox — Provides isolated environments with multi-language SDKs and lifecycle management.
OpenResearch — Run parallel research workflows locally or on remote compute.
jevgrep — Reduces coding agent costs by providing targeted, relevant repository context.
Mantis — Automates vulnerability discovery and patching using AI agents.
Crit — It keeps human feedback localized and precise for AI agent code iterations.
OpenAPPA — Tracks data flows algebraically to prevent prompt injection without breaking agents.
OpenChamber — Run and review multi-model AI coding agents from desktop, browser, and mobile devices.
opensrc — Provides AI agents direct access to package source code rather than types.
ARTEX — Runs autonomous multi-agent penetration testing with a dual-graph architecture.
OpenAgentsControl — Generates code matching your patterns and requires approval before execution.
OpenClaude — Connects one terminal interface to over 200 different AI models.

All Open Kritt alternatives