Tracekit AI
Tamper-evident logging and approval for AI agents with cryptographic
Visit tracekit.tech ↗What is Tracekit AI?
Tracekit intercepts tool calls from AI agents, checks them against your policies before execution, and records each decision in a cryptographically signed hash chain. Every run produces a `.tkb` file that anyone can verify offline, making agent actions auditable and tamper-proof. It works with 25+ agent frameworks including Claude Code, Codex, Cursor, and Gemini CLI, plus custom Python and TypeScript agents. The open-source version (MIT) installs via pip and requires one line of code to instrument an agent.
Momentum
Daily activity over the last 30 days: upvotes, unique visits, new GitHub stars and Hacker News points.
How do we know it's vibe coded?
vibetrend discovered Tracekit AI automatically. Evidence: Rising on GitHub: agent files (claude-code) in Cygnux-Labs/Tracekit. View source.
Similar vibe-coded apps
#1 this weekOpen-source local voice cloning, dubbing, transcription, and audiobook creation
#2 this week
#5 this weekSlash commands and agents for engineers using AI without compromising standards
#6 this week523 free lessons building AI systems from math and first principles
#8 this week
#10 this weekAI-powered design intelligence toolkit for building professional interfaces
Manage teams of AI agents to run your business from one dashboard
Persistent memory for AI agents across Claude Code, Cursor, and MCP clients