Popular repositories Loading

1. agentic-review-gate agentic-review-gate Public

   Governed, auditable AI review platform: the review and approval work a team does by hand, as a webhook-triggered LangGraph agent with human-in-the-loop approval, Langfuse tracing, an eval-gated CI …

   Python 2

2. temporal-multi-agent temporal-multi-agent Public

   Durable multi-agent orchestration platform on Temporal: a main orchestrator agent plans a task, coordinates specialized agents running concurrently as isolated, fault-tolerant workflows, and recove…

   Python 1

3. citation-abstention-rag citation-abstention-rag Public

   RAG that refuses to guess: every served claim carries a citation the system verified back to an exact character span, unverifiable claims are dropped, and below threshold it abstains with a reason …

   Python

4. least-privilege-agent least-privilege-agent Public

   A clear policy for what an AI agent may do unsupervised, and what bounds the blast radius when it is wrong. Deny-by-default policy, purpose binding, provenance tagging, opaque handles and an egress…

   Python

5. llm-eval-gate llm-eval-gate Public

   An eval harness that gates deployment and measures its own judges. Three LLM judges score a system under test against a rubric, plus two non-voting shadows, and the gate fails CI on a golden-set re…

   Python

6. prompt-injection-benchmark prompt-injection-benchmark Public

   A reproducible prompt-injection benchmark that measures which defenses actually work: each payload is replayed against every defense, the report separates whether the agent COMPLIED from whether th…

   Python