Rust LLM request orchestrator and drop-in OpenAI-compatible proxy. Requests flow through a bounded five-stage pipeline with deduplication (the same prompt asked twice costs one model call), circuit...
Local-first Rust service and MCP server that records what AI coding agents do on a machine (commands, exit codes, files touched, whether anything checked the result), keeps 'seen together' separate...
GitHub Action for Rust projects. On every pull request that touches Cargo.toml or Cargo.lock it posts one comment with security advisories (OSV/RustSec) for the exact locked versions and the smalle...