Vigil is an AI harness for code audits, web pentests and bug bounty hunting. It coordinates Claude Code or Codex through broad review, focused rereads, authenticated testing and runtime reproduction, and carries findings, evidence and coverage across sessions.
Be the first to rate Vigil. Your feedback helps other users decide.
The first pass is a starting point; higher-risk code gets another look with a different objective, and specialists follow callers, challenge guards and hunt variants.
Promising leads stay on the books when runtime proof or access is still missing, so an unsupported impact claim does not ship.
Findings, evidence, coverage and handoffs carry across sessions rather than restarting each run.
Similar tools in the same category — compare side-by-side
Faplex is a status list for the Claude Code, Codex and OpenCode sessions you already have, on every ...
Rutter is a personal memory layer for AI agents. It keeps a record of what you decided, which notes ...
Spectra is a drop-in optimizer replacement for AdamW that shifts gradient optimization to the freque...
Guides and comparisons about code tools
Eleven Show HN launches built for the moment after the agent finishes: PR walkthroughs, review bots, drift tests for MCP servers and scoped access.
Ten Hacker News launches that treat agent context, persistent memory and token accounting as first-class problems instead of afterthoughts.
Eleven recent open-source and self-hosted projects for building, sandboxing and deploying coding agents you own outright rather than rent.
Eleven recent projects that turn the Model Context Protocol from a neat demo into deployable infrastructure: registries, compiled servers, and gateways.
Eleven recent open-source projects for running inference, transcription, deep research and security work entirely on hardware you control.
