Air – Open-source black box for AI agents (tamper-evident audit trails)
Cryptographic audit chain for agents, but lacks observability dashboards competing tools provide.
Cryptographic execution log for AI systems
SHA-256 hash-chained AI audit log, but only 9 commits and ko-fi upsell.
AI system builders needing compliance audit trails
WhyLabs · Arize
New in v0.2: Execution Proof — one file that cryptographically proves your AI ran exactly this way.
Buy CEL Pro: https://ko-fi.com/s/50fccfeecd
Cryptographic audit chain for agents, but lacks observability dashboards competing tools provide.
Instead of another observability dashboard, this project builds a provable audit trail: an OpenAI-compatible reverse proxy that vaults prompts in MinIO and links calls with an HMAC-SHA256 tamper-evident chain, plus replay tooling (replayctl) and Jaeger traces. The cryptographic audit chain and the one-line SDK wrap are clever and practical; the real operational work left to teams will be key management and storage/retention strategy.
Standardizes portable cryptographic receipts for agent behavior—but adoption unclear, overlaps Nobulex heavily.
Terminal voice recorder with pause/resume when GUI apps already handle this better.
Execution-based scoring with live APIs beats LLM-graded benchmarks, but they evaluated themselves.
Symmetrical sync/async APIs and chainable model methods (.where(), .order_by(), .limit()) make day-to-day querying feel cleaner, and the .alchemize() escape hatch means you can drop to raw SQLAlchemy when you need power. Automatic driver injection and first-class Pydantic support are thoughtful conveniences, but this is an ergonomic wrapper in a crowded ORM space — useful if you like the approach, not a reinvent-the-stack play.