32 packages found
MCP server that saves Claude Code tokens by delegating bounded tasks to local or cloud LLMs. Works with LM Studio, Ollam
OpenAI and Anthropic compatible server for Apple Silicon. Run LLMs and vision-language models (Llama, Qwen-VL, LLaVA) wi
Airtight math tools an AI uses over MCP — 3.7M-theorem search, PSLQ constant ID, OEIS, real Lean kernel checks, applicab
Self-hosted mem0 MCP server for Claude Code. Run a complete memory server against self-hosted Qdrant + Neo4j + Ollama wh
memory-mcp-1file
clarifyprompt-mcp
TeleMem is a high-performance drop-in replacement for Mem0, featuring semantic deduplication, long-term dialogue memory,
Unreal Engine plugin for LLM/GenAI models & MCP UE5 server. OpenAI GPT-5, Deepseek R1, Claude Opus/Sonnet, Gemini 3, Gro
Token-lean web microfetch for LLM agents: any URL → clean markdown via CLI, MCP server, and Claude Code plugin. Real bro
Industrial-grade speech recognition toolkit: 170x realtime, 50+ languages, speaker diarization, emotion detection, strea
for AI Agents - give your text-only model eyes. Use any OpenAI-compatible vision model API through MCP tools for image
The Mind Palace for AI Agents - HIPAA-hardened Cognitive Architecture with on-device LLM (prism-coder:7b), Hebbian learn
Embedded, local-first agent memory. No server, no daemon, no mandatory cloud key.
Chat with your robotics, drone, and IoT data — ChatGPT for the physical world.
Serverless AI agent using LangChain.js and Model Context Protocol (MCP) integration to order burgers from a burger resta
Graph-based tool retrieval for LLM agents — 248 tools → 82% accuracy, 79% fewer tokens. Zero dependencies. OpenAPI / MCP
Universal LLM router for AI coding tools. Works with Claude Code, Cursor, Codex, Gemini CLI, Copilot and more.
MCP server for token-efficient large document analysis via the use of REPL state
vMLX - JANGTQ Uber Compressed MLX Models - L2 Disk Cache (survives restart) + L1 Paged (super fast ttft) + Hybrid SSM Sc
A list of open-source AI projects you can use to generate income easily.
MCP server for the Bitcoin Benji API — Lightning-paid Bitcoin mempool intelligence + sovereign on-prem AI inference (L40
rca-mcp-connector
NEXO Brain — Shared brain for AI agents. Persistent memory, semantic RAG, natural forgetting, metacognitive guard, trust
Стартовый E2E RAG: LlamaIndex + ollama + Qdrant, подключаемый к агентам (qwen-code, Claude Code) через MCP. Инкременталь
Comprehensive, scalable ML inference architecture using Amazon EKS, leveraging Graviton processors for cost-effective CP
MCP proxy that condenses verbose JSON and YAML tool responses into compact TOON text, dramatically reducing token usage
Pull Deep Memory from across your Claude Code Sessions — when you need it.
Substrate-based context compaction for Claude Code. Inspectable signal weights, local-only, MCP-ready. Alternative to /c