CEL v0.2 Pro – cryptographic black box recorder for AI systems (Python)
SHA-256 hash-chained AI audit log, but only 9 commits and ko-fi upsell.
OTW receipt framework is clever, but 0 stars and embryonic implementation limit credibility.
AI governance teams, compliance officers
Arize AI · WhyLabs · Fiddler AI
SHA-256 hash-chained AI audit log, but only 9 commits and ko-fi upsell.
Recording what an agent considered — not just what it executed — is a tidy, concrete insight. GhostTrace already gives record/replay commands, a .ghost.json schema and a --show-phantoms terminal replay so you can inspect rejected actions and the agent's reasoning. The thing that will decide if this takes off is integrations (LangChain/OpenAI Agents/CrewAI) and the promised web/VS Code UIs; without those it's a very useful niche tool, not yet a platform.
Single-file Python CLI that names and backgrounds loops so you can stop writing while-true.
Lint-time DataFrame checking when Pandera only validates at runtime.
Flags LLM judge verdicts unsupported by evidence without needing a second model.
Content-aware rule matching on diffs surfaces only relevant decisions, not noise.