Private web search for AI assistants via SearXNG — supports Claude, Cursor, and any MCP client

An ML engineering plugin for your coding agents.

An MCP server enabling automated access to LeetCode's problems, solutions, and public data with optional authentication for user-specific features, supporting leetcode.com & leetcode.cn sites.

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

Fully functional AI Logic Calculator utilizing Prover9/Mace4 via Python based Model Context Protocol (MCP-Server)- tool for Windows, Linux, Claude App etc

A Socratic supervision layer for AI coding agents.

The AI security agent guards your code.

a philosophy for talking to AI agents without getting glazed. one trigger, four meanings. /meow.

A skill library that teaches Claude Opus the working disciplines of Claude Fable 5. Move the checkpoints, not the capacity.

Bash is all you need - A nano claude code–like 「agent harness」, built from 0 to 1

⌥ Coding agent with the IDE wired in

Framework for AI agents to build and maintain a digital brain through Obsidian wiki

Portable AI agent orchestration with mechanical protocol enforcement. 186 agents, zero runtime dependencies.

Real-time behavioral enforcement for Claude Code. Monitors AI actions, detects violations, and interrupts misbehavior. Also has a cute pet.

Provider-neutral control plane for durable-state agent swarms: subprocess workers, leases, artifacts, memory, and deterministic stitching.

Context cleaning for Claude Code — prune bloated sessions, protect Agent Teams from context loss, auto-guard with tiered pruning

Open-source control plane for your AI agents. Connect tools, hire agents, track every token and dollar

Open source version of Claude Managed Agents. Fastest way to build and deploy reliable AI agents, MCP tools and agent-to-agent.

An MCP Server for Ollama

Git-backed control plane for AI-agent skills, tools, context, permissions, and identity. Self-hosted and MCP-native.

Coding agent orchestration for engineering teams — shipped as a spec plus a working reference implementation.

See how you really use AI — X-ray your AI coding sessions locally

MCP server for external memory layer for AI agents + more . Download from pypi , and get started

The semantic layer for software engineering: Connect code to meaning, build on understanding