2965 posts
The oracle for agent-to-agent Trust on Base
Give AI Agents Interactive Terminal Capabilities
Neutral freight reference & correctness layer for AI agents — authoritative DG, customs, location & freight-math data agents can call and ci...
Open-source SkillOps / instruction-supply-chain control plane for AI-agent teams: policy packs, registry diff, evidence bundles, SARIF/SBOM,...
Hosted MCP server with data tools for AI agents. Connect at https://glim.sh/mcp.
A hardware-isolated microVM sandbox for running untrusted local AI agents on macOS.
Build shared AI workspaces for creation, simulation, verification, MCP tools, and replayable receipts.
PolicyNIM is a policy-aware engineering preflight layer for AI coding agents.
Per-message signing + replay protection for MCP and A2A traffic. TypeScript / Python / Rust. Wire version aip/0.1.
Local context infrastructure for AI agents
Local-first engine that grounds an AI agent's answers in your own Markdown and captures what it learns back into the KB — Node · TypeScript...
Measure whether an MCP server or skill actually improves your coding agent. A/B arms, deterministic gates, your own models. Negative results...
