2299 posts
Persistent memory for AI coding agents using TOON format (40% fewer tokens than JSON)
World-class Codex Skill and MCP harness for orchestrating Claude Code workers through CCSwitch multi-model routing.
Recursive Language Models for Claude Code - Infinite memory solution inspired by MIT CSAIL paper
Unofficial OpenEvidence MCP server — query OpenEvidence from Claude Code, Codex, and any MCP client through your own logged-in browser tab (...
Local-first repo memory and context for coding agents.
MCP server with 35 local tools for AI agents: read PDFs, exact math, image convert & resize, QR codes, crypto, timezone, regex, JSON/CSV. Wo...
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 + CLI for production-grade software assets (logos, app icons, favicons, OG, illustrations) — routes across 30+ image models, zero...
Team knowledge evaporates daily — pairing sessions, debugging context, architectural rationale lost to Slack. Distillery captures it at the...
Cut a Claude Code session's context tokens losslessly: bulky tool output moves to a local backup, every prompt stays verbatim, and the sessi...
First open-source OpenEvidence MCP server: browser-session medical research tools for Codex, Claude Code, and MCP clients
MCP server for Linux desktop GUI automation on KDE Plasma 6 Wayland -- 30 tools for virtual and live sessions
