A community-driven registry for the Claude Code ecosystem. Not affiliated with Anthropic.
74 packages found
Sovereign Ollama Bridge — MCP server for local and cloud Ollama models. Generated by Qwen 3.5 397B.
Self-hosted mem0 MCP server for Claude Code. Run a complete memory server against self-hosted Qdrant + Neo4j + Ollama wh
The Mind Palace for AI Agents - HIPAA-hardened Cognitive Architecture with on-device LLM (prism-coder:7b), Hebbian learn
council of models for decision
MCP Server - Bridge to local Ollama LLM. Part of HumoticaOS/SymbAIon ecosystem.
Read-only VMware vCenter/ESXi monitoring — code-level enforced safety, zero destructive operations
A collection of MCP clients.
MCP server that saves Claude Code tokens by delegating bounded tasks to local or cloud LLMs. Works with LM Studio, Ollam
Universal LLM router for AI coding tools. Works with Claude Code, Cursor, Codex, Gemini CLI, Copilot and more.
Token optimizer for Claude Code Gemini CLI & Qwen Code — compresses shell outputs via PreToolUse hook, tracks USD saving
Open-source AI agent orchestration platform — self-hosted mission control for autonomous multi-agent systems. Visual DAG
Multi-agent orchestration for Claude Code with 15-30% token optimization, self-improving agents, and automatic verificat
MCP server for OpenAI's Deep Research APIs, Gemini Deep Research Agent, Allen AI's DR-Tulu, and Hugging Face's Open Deep
PDF extraction that checks its own work. #2 reading order accuracy — zero AI, zero GPU, zero cost.
ContextLattice is the local-first control plane for long-horizon agent memory and coordination.
🧠 LLM-Driven Intelligent Memory & Context Management System （AI记忆管理与智能上下文感知平台） AI记忆管理平台 | 智能上下文感知 | RAG检索增强生成 | 向量检索引擎
Pull Deep Memory from across your Claude Code Sessions — when you need it.
The power of Claude Code / GeminiCLI / CodexCLI + [Gemini / OpenAI / OpenRouter / Azure / Grok / Ollama / Custom Model /
MCP server for @cartisien/engram — persistent semantic memory for AI agents
Verified knowledge for AI agents. Compress context, extract and store facts, define rules, and ask questions — get dete
Give your AI assistant its own AI assistants.
Self-hosted encrypted tunnel for webhooks, AI pipelines, and local development. End-to-end Noise encryption, pipeline tr
Substrate-based context compaction for Claude Code. Inspectable signal weights, local-only, MCP-ready. Alternative to /c
MCP server for multi-round AI brainstorming debates between multiple models (GPT, DeepSeek, Groq, Ollama, etc.)
Use Claude Code as the foundation for coding infrastructure, allowing you to decide how to interact with the model while
An economical and fuel(token) efficient AI tool, graph session memory for looong chat session
Self-correcting learning engine for Claude Code — persistent identity, behavioral pattern tracking, and cross-session me
Model Context Protocol server to run commands (tool: `runProcess`)
Streams are the future of AI powered by unlimited free tokens.
AlgoVoi apps & adapters — ecommerce, marketplace, AI-agent, and no-code integrations for the AlgoVoi x402 multi-chain pa
Computer Experience Layer — MCP server for native computer use on macOS. Structured perception, reliable actions, contin
YC (S26) | AI that knows what you've seen, said, or heard. Records everything you do, say, hear 24/7, local, private, se
See exactly what you spend on Claude CLI + cost optimizations functions
Fast, local-first web content extraction for LLMs. Scrape, crawl, extract structured data — all from Rust. CLI, REST API
AI-powered Adaptive Card MCP server — 9 tools for generating, validating, optimizing cards for Teams, Outlook, Copilot,
🪢 Open source LLM engineering platform: LLM Observability, metrics, evals, prompt management, playground, datasets. Int
Generate draw.io diagrams from natural language — 6 presets, vision self-check + up to 5-round refinement, codebase-to-d
Memory infrastructure for multi-agent AI systems. Shared, persistent, consistent knowledge for agents that need to stop
Persistent memory system for AI coding assistants via MCP. Works with Claude Code, Cursor, Copilot, Windsurf, Cline.
Graph-based tool retrieval for LLM agents — 248 tools → 82% accuracy, 79% fewer tokens. Zero dependencies. OpenAPI / MCP
Find the ghost tokens. Fix them. Survive compaction. Avoid context quality decay.
Know what your AI agents cost. API gateway with budget enforcement, session tracking, and MCP tools.
An LLM-powered, autonomous coding assistant. Also offers an MCP and ACP mode.
Local filesystem MCP server with 43 tools: safe delete, process management, interactive sessions, async search, OCR, ZIP
@MarkgatchaThe canonical open-source monorepo for production-ready MCP servers.
The missing cognitive primitive for AI agents. Decompose any text into classified semantic units — authority, risk, atte