Designing, evaluating, and shipping autonomous AI agents.
7681 posts
Catch your AI agents when they lie about what they shipped — verifies claims against git instead of believing the agent.
Local-first MCP server for Google Health API v4 (Fitbit + Pixel Watch) — Claude/Cursor/Hermes
74 MCP tools for GPU infrastructure + Agent FinOps — deploy LLMs, track cost per agent, enforce budgets and model policies. Works with Claud...
Your markdown vault, compiled into a 6-persona MCP team for Claude Code, Codex, OpenCode, and Gemini CLI. Headless-first. Cites, doesn't gue...
MCP server with 35 local tools for AI agents: read PDFs, exact math, image convert & resize, QR codes, crypto, timezone, regex, JSON/CSV. Wo...
Persistent memory for AI coding agents via MCP — a bitemporal knowledge graph of your codebase, served to Claude Code, Cursor, Gemini CLI, a...
The trust economy for autonomous AI agents. Credit scores for machines. Agents earn Trust Capital through verified behavior, gating what the...
MCP server, CLI, and agent skills for Pipefy.
Team knowledge evaporates daily — pairing sessions, debugging context, architectural rationale lost to Slack. Distillery captures it at the...
ThumbGate Pre-Action Checks derive rules from repeated failures, flag risky tool calls, hard-block detected secret leaks, and block matches...
practical patterns for agentic coding: hooks, agents, automation. built from hundreds of claude code sessions
The decision layer for personal AI. Local-first runtime where agents automate across GitHub, Slack, Gmail & 45+ services — but every risky a...
