Pinned Loading

1. clinical-agent-eval-demo clinical-agent-eval-demo Public

   A deployment layer for a guardrailed clinical conversational agent: real FHIR over MCP, PHI redaction, a hash-chained audit trail, and an evaluation harness measured on held-out data it was never t…

   Python

2. regulated-support-eval regulated-support-eval Public

   An eval suite for a customer-support agent in a regulated setting: durable Temporal workflows, an explicit state machine, guardrail classifiers and path-based scoring. Synthetic data.

   Python

3. staledep staledep Public

   Detect stale-dependency candidates (TOCTOU windows) in LLM agent trajectories

   Python

4. stride stride Public

   A serving runtime for large language models in Rust: paged KV cache with content-addressed prefix reuse, deadline-ranked continuous batching, and capacity planning for large dense and MoE transform…

   Rust

5. gradcheck gradcheck Public

   Finite-difference gradient checking for Rust ML frameworks. Verifies an autodiff engine against an independent numerical oracle, with a negative control that must fail.

   Rust 1

6. agent-assay agent-assay Public

   Evaluation-integrity layer for tool-calling agents: scores trajectory, arguments and final state, and refuses to report until the harness has proven it can fail

   Python