23 posts
Interface understanding and design-system memory for AI coding agents.
SkillDock is a skill manager and MCP manager for installing, viewing, updating, and syncing AI skills and MCP servers, with Git-aware update...
A locally-hosted, open-source firewall for AI coding agents. Detects local agent harnesses, gates risky tool calls via deterministic YAML po...
A unified toolkit for efficient and effective coding agents (Karpathy principles, Caveman, Ponytail, RTK, CodeGraph, Context-Mode). Minimal...
Stop AI coding agents from rediscovering large TypeScript/Node repos with task-aware local context packs.
Make AI coding agents safe to scale autonomously: assign work, cap spend, enforce policy, verify output, roll back failures, learn from loop...
Open-source server that refuses vulnerable package installs. The backend the refuse CLI shim calls.
CLI for benchmarks & evals of AI coding agents — on tasks you already understand, using your Claude / Codex / Gemini individual subscription...
The hivemind for AI coding agents — persistent team context recorded once and recalled across agents, machines, and teammates.
Agent harness for codebases. Gives Claude Code, Codex, and CI a shared task system, verdict ledger, and state store so agent work is traceab...
Claude Code plugin that writes grounded, verified context for your coding agent — every claim checked against your code. Lean CLAUDE.md + de...
