50 packages found
MCP Docs Vector - Documentation vectorization and search via MCP
Lightweight Long-Term Memory for LLM Agents.
This MCP server provides tools for listing and retrieving content from different knowledge bases.
A modular RAG (Retrieval-Augmented Generation) system with MCP Server architecture. Using Skill to make AI follow each s
OpenAPI-generated MCP server for TokenLab text, image, video, music, 3D, audio, files, embeddings, rerank, translation,
Embedded, local-first agent memory. No server, no daemon, no mandatory cloud key.
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 structural code search engine for Al agents.
GPU-Bridge MCP Server — 30 AI services as Model Context Protocol tools. LLMs, image gen, video, audio, embeddings, reran
TeleMem is a high-performance drop-in replacement for Mem0, featuring semantic deduplication, long-term dialogue memory,
ifs-cloud-core-mcp-server
Zero-key MCP web search for AI agents: native Chinese sources, multi-engine aggregation, optional commercial backends, n
Agentic RAG over 30 Indian IT annual reports (FY2020-24). Claude Code + MCP agent that decides when to retrieve, cites s
Tessera — Memory layer for every AI. 58 MCP tools, 54 REST endpoints, local-first, AES-256 encrypted.
Persistent memory for AI agents. Agents forget. CI remembers.
Hosted memory for AI agents that learns and forgets — feedback reranks what helps, recall fades by recency. One key acro
Give Claude Code 51 research, analysis & media production tools with one command. Video analysis, deep research, academi
Semantic code searcher and codebase utility
Graph-based tool retrieval for LLM agents — 248 tools → 82% accuracy, 79% fewer tokens. Zero dependencies. OpenAPI / MCP
Lean Six Sigma PDF corpus MCP server (local snapshot of quanti/lean at HEAD 75cc41d)
Airtight math tools an AI uses over MCP — 3.7M-theorem search, PSLQ constant ID, OEIS, real Lean kernel checks, applicab
Memory that AI Agents Love!
Shrink the web for your local LLMs!
OpenAI and Anthropic compatible server for Apple Silicon. Run LLMs and vision-language models (Llama, Qwen-VL, LLaVA) wi
NEXO Brain — Shared brain for AI agents. Persistent memory, semantic RAG, natural forgetting, metacognitive guard, trust
CogmemAi — Cognitive Memory for Any Ai System. Autonomous robots, self-driving vehicles, defense systems, coding assista
The highest-scoring AI memory system ever benchmarked that isn't reliant on LLM reranking. And it's free & burns less to
Model Context Protocol (MCP) implementation for Opik enabling seamless IDE integration and unified access to prompts, pr
x402 Micropaid MCP Server — 51 Baidu AI tools for global developers. Pay-per-call with USDC, PayPal, or Alipay. No Chine
A lightweight Model Context Protocol (MCP) server for safe Obsidian vault access
Стартовый E2E RAG: LlamaIndex + ollama + Qdrant, подключаемый к агентам (qwen-code, Claude Code) через MCP. Инкременталь
Code Intelligence: Token-budgeted codebase context for Elixir agents. Solves context window limitations by providing a d
(S)AGE - (Sovereign) Agent Governed Experience
Cut your Claude / OpenAI / Gemini bill 70–95% on AI coding. Local proxy that compresses context, keeps provider caches h
Local-first RAG server for developers. Semantic + keyword search for code and technical docs. Works with MCP or CLI. Ful
Self-hosted mem0 MCP server for Claude Code. Run a complete memory server against self-hosted Qdrant + Neo4j + Ollama wh
MCP server giving LLM agents a seven-verb API over papers, documents, code, state, patents, and cached web/Wolfram/YouTu
Servidor MCP com toda a documentação da lib jangada (jangada-ai) — para devs plugarem no Claude Code/Desktop/Cursor
Extremely fast hybrid code search for agents.
Ragie Model Context Protocol Server
Fast and Accurate Code Search for Agents. Uses ~98% fewer tokens than grep+read
Docs for agents. No RAG
The unified web layer for AI agents. Search (8 engines), stealth browse, auth, and act on 24 platforms. One npm install,
RAG MCP Registry Finder (RAGMap): subregistry API + MCP server + Firestore ingestion
🦫 Privacy-first virtualization layer for LLM context with MCP protocol for tool access.
Hindsight: Agent Memory That Learns