GitHub · Python
macmaia/catraca
Provenance-aware authorisation for LLM agent tool calls. Denies a call when a consequential argument came from untrusted content. Stdlib only.
- Stars
- 5
- Forks
- 0
- Stars gained in 24 hours
- 0
- Forks gained in 24 hours
- 0
Topics: agent-security, ai-agents, ai-security, audit-log, authorization, data-exfiltration, information-flow-control, lgpd, llm, llm-security
Latest data point: Nov 22, 2026 · 5 stars · 0 forks