deerwork-ai
Featured
deer-workflow
An open-source Dynamic Workflow runtime that combines deterministic TypeScript orchestration with replaceable Agent runtimes.
AI repository intelligence
FR-AI / ANALYSISWhy it is worth attention
It is built by a team that has earned over $1.5M in bug-bounty payouts, distilling their internal research workflow into a configurable, model-agnostic tool that gives security researchers full control over prompts, workflows, and infrastructure.
Who it is for
- Security researchers performing code audits
- Bug bounty hunters seeking automated assistance
- Security-minded developers integrating AI into their review process
- Teams wanting self-hosted, private vulnerability scanning
Use cases
- Scanning private codebases for vulnerabilities without sending code to third parties
- Reusing and chaining prompt-based security research playbooks across different repositories
- Validating and prioritizing AI-generated findings with post-scripts and custom severity rankers
- Building proofs of concept for discovered vulnerabilities via tool-enabled agents
Strengths
- Focused, task-decomposition approach improves reliability over whole-repo prompts
- Self-hosted with full control over model providers, workflows, and data
- Built from proven real-world bug-bounty methodology (team's $1.5M track record)
- Supports Codex, Claude Code, OpenAI, Anthropic, and OpenRouter – bring your own model access
Considerations
- Runs as root inside disposable containers with internet access – requires dedicated Docker host or VM and awareness of threat model before scanning untrusted code
- No built-in application authentication; backend binds to localhost only and must be kept private
- Requires Git, Docker Compose, and Node.js 20+, which adds infrastructure overhead for some users
README quick start
Getting started
Description
Orchestrate AI agents to find real vulnerabilities in code.
Related repositories
Similar projects matched by category, topics, and programming language.
HezaoHezao
Featured
poirot
Poirot is a deep research agent kernel with a middleware-first architecture, five-layer long-term memory, multi-agent orchestration, sandbox isolation, and a three-layer skill self-evolution system, backed by 2400+ tests.
7-e1even
Featured
learn-agent
A collection of notes on building coding agents, derived from the production development of the desktop agent Reina, with each mechanism simplified into a zero-dependency, single-file Node.js demo.