5 projects
vaultrag-cli
Permission-aware RAG: access control enforced in the retrieval query, not after it.
voiceeval-cli
Evaluation for voice agents. Catches the failures text evals cannot see: latency, mis-hearing, missing confirmation, barge-in.
agentrace-cli
Observability for Claude Code subagents. Parses session transcripts, surfaces what agents actually did, and flags the failure patterns.
ctxlens-cli
A context-window profiler for AI agents: see exactly what is eating your context, flag waste, and cut tokens.
answerproof
Verifiable, tamper-evident receipts for RAG and agent answers.
