Models

Mempalace Rust

The highest-scoring AI memory system ever benchmarked. Now in Rust with rich features — single-binary port from @milla-jovovich/mempalace. F...

Haiku MCP Server

MCP server for DeFi execution — lets AI agents swap, provide liquidity, lend, bridge, and run yield strategies across 22 chains

AgentDefense Bench

A comprehensive security benchmark for evaluating infrastructure-layer defenses in MCP-based AI agent systems

Hegelion

Dialectical reasoning architecture for LLMs (Thesis → Antithesis → Synthesis)

MCP Logic

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

Fable It

Autonomous delivery orchestrator for Claude Code — hand it a goal and a numbered Definition of Done, it runs the whole job to completion

EcoDB

Collective AI memory for multi-agent teams. 10-stage GAMR search engine, knowledge graph (Apache AGE), document ingestion, 32+ MCP tools.

Clawdmarket

Autonomous agent-to-agent marketplace with live Karpathy loop self-improvement. Agents discover, hire, benchmark, and evolve programmaticall...

Haiku.skills

Skill-powered AI agents implementing the Agent Skills specification with pydantic-ai

Ask Expert Consult MCP

Open Source AI Expert Agent Bridge for Cursor 2026

Cowork Bench

Multi-tool LLM agent benchmark: 496 end-to-end MCP tasks, deterministic evaluation, Russian localization

Unclog

Audit MCP servers, skills, and CLAUDE.md bloat eating your Claude Code context window.