Persistent memory for Claude Code. Your AI never starts from scratch again.

A lightweight, Git-backed permanent memory for AI agents.

Fast and Accurate Code Search for Agents. Uses 99% fewer tokens than grep+read

Run Coding Agents in Sandboxes. Control Them Over HTTP. Supports Claude Code, Codex, OpenCode, and Amp.

Give your AI Agent a whole IDE, not just the files

An autonomous agent that conducts deep research on any data using any LLM providers

Prismer Cloud

Browser automation clicks buttons. OpenTabs calls APIs.

Recursive Language Model patterns for Claude Code — handle massive contexts (10M+ tokens) by treating them as external variables

Countbean plugin for Claude Code — hosted plain-text (Beancount) accounting. Published from the countbean monorepo; do not edit here.

Yet another WebUI for Nginx

Control Ableton Live with any LLM: create tracks, arrange clips & compose music via MCP

Search, archive, and recall your AI conversations. ChatGPT, Claude, Gemini, Grok, Kimi. Local-first, MIT licensed.

Your Windows syscall hooking factory - feat Canterlot's Gate - All accessible over MCP

A fast, keyboard-driven HTTP intercepting proxy and hacking & pentesting toolkit for the terminal.

Skills and plugins to accelerate security workflows with the Orca Cloud Platform

Full computer-use for AI agents. Self-learning workflows. Native macOS. No screenshots required.

Collection of resources to help AI agents build better with Sanity.

A Neovim plugin to integrate Gemini CLI well (+ Qwen-code now)

:octocat: GitHub Emoji for C#, dotnet and beyond

Bulk port forwarding Kubernetes services for local development.

Bring Your Own Browser — let your AI agent use the Chrome you already have open

Open-Source Platform for Subagents and Agent Teams. Long-running, collaborative, proactive.

The AI security agent guards your code.