Popular repositories Loading

1. 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

2. agentic-review-gate agentic-review-gate Public

   Governed, auditable AI review platform: a webhook-triggered LangGraph agent with human-in-the-loop approval, Langfuse tracing, an eval-gated CI pipeline, and a tamper-evident hash-chained audit tra…

   Python

3. typed-agent-service typed-agent-service Public

   Typed AI agent service (TypeScript): Zod 4 tool schemas as the single source of truth (runtime validation, inferred types, generated JSON Schema), a bounded provider-agnostic tool-use loop, SSE str…

   TypeScript

4. 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

5. least-privilege-agent least-privilege-agent Public

   An AI agent that cannot exceed its grant, even when the data it reads tells it to. Deny-by-default policy, purpose binding, provenance tagging, opaque handles and an egress allowlist, with a hash-c…

   Python

6. 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