Tracekit
Tracekit records what your AI agents do, decides each tool call before it runs, and gives you a signed record anyone can verify offline: tamper-evident tracing, policy gates and cross-checks for AI agents.
- 798
- Python
- MIT
- 11 h ago
Tracekit records what your AI agents do, decides each tool call before it runs, and gives you a signed record anyone can verify offline: tamper-evident tracing, policy gates and cross-checks for AI agents.
The seal of approval for agents and skills: a graph-first semantic governance registry with signed, transparency-logged publication trust.
Proof of what your AI agents did. Give your agents real power, without losing control of them.
Proof-Carrying Messages: a protocol for AI agents whose claims carry evidence the receiver checks offline
Signed, tamper-evident receipts of every AI agent execution: what ran, where, when, with what. Verifiable offline or with cosign.
Developer blind to the probes, auditor blind to the weights: a sealed-room protocol to audit AI models you can't steal. TEE + attestation + weight commitment + transparency log + extraction detector + DP noise + dual-signed transcript.
Verifiable Usage Receipts for AI APIs. Cryptographic proof that your token bill is real. Ed25519 + Fulcio signing, RFC 6962 Merkle proofs, Trillian Tessera log, C2SP witness cosigning, Rekor public anchoring, Rust tokenizer verification. No blockchain.
A PSR-18 client for the Rekor v2 transparency log — submit entries and read checkpoints in PHP.
Parse, verify and sign signed notes (the transparency-log / Go sumdb format used by Sigstore Rekor checkpoints) in PHP.