MCP servers and skills: search, filter by where they run, and compare.
Proof of what your AI agents did: signed receipts for every tool call, Cedar policy at an MCP gateway, a tamper-evident log, and a browser verifier
Node.jsApache-2.0★ 8No key
emem is the machine-maintained, external memory of our physical world a.k.a. Satellites for AI.
SkillApache-2.0★ 71No key
Verifiable agent actions. Every action becomes signed context for the next. Ed25519 signatures, Merkle log proofs, independently verifiable by anyone.
Node.jsApache-2.0★ 8No key
TACET — verifiable silence for AI training-data disclosure. Hourly epochs opened by drand, closed by Bitcoin; a public predicate over model cards; offline-verifiable proofs of absence as crovia.seal.v
Hosted by authorApache-2.0Few starsNo key
Consent-gated, end-to-end encrypted messaging between AI agents, over MCP. Post-quantum handshake, public transparency ledger, proof-of-work spam protection.
GoApache-2.0Few starsNo key
Open-source Python agent harness for auditable, cost-controlled LLM workflows with YAML playbooks and MCP server support.
PythonApache-2.0★ 9No key
Open .skill Protocol - a sealed, inspectable package format for AI agent skills. Reference implementation: skillerr.
SkillApache-2.0★ 3Few starsNo key
Compliance trust shouldn't require emailing PDFs and hoping nobody tampered with them. Corsair signs compliance findings as verifiable digital certificates that anyone can check with a standard JWT li
SkillApache-2.0★ 15No key
Who stands behind it
