Semantic code-search MCP server for AI coding agents: hybrid retrieval (embeddings + BM25 + reranking), tree-sitter AST chunking, 30-100x fewer tokens
A high-performance Model Context Protocol (MCP) server written in Rust that extends AI models into autonomous coding agents with semantic memory, built-in Git tools, and codebase indexers
MCP server to allow agents to learn from my personal knowledge management system.
Apple ecosystem MCP server for Claude Code, Cursor, and other AI assistants — Notes, Reminders, Contacts with BERT semantic search
Best Token-Efficient AI Coding Tools 2026 – Reduce Costs 90% with Local Memory & MCP
MCP server for searching, indexing, and retrieving scientific papers across arXiv, INSPIRE-HEP, Semantic Scholar, OpenAlex, CrossRef, NASA ADS, Europe PMC, DOAJ, and viXra. Local hybrid search with BM
Parallax - an MCP server of independent correctives for a model's predictable failure modes: adversarial verification, deterministic checks (Z3/evalexpr), verified cross-session memory, cited research
A minimal Rust vector-memory server that works with Qdrant and Ollama.
Long-term memory for coding agents over MCP: hybrid search over Markdown notes with a link graph, on PostgreSQL, Qdrant, and Ollama
Stable MCP supervisor proxy for stdio servers: cached discovery, unified mcp.wrapper lifecycle control, and on-demand backend processes.
Personal knowledge system — MCP server with PostgreSQL semantic search and temporal knowledge graph
Model Context Protocol (MCP) server for FalkorDB — read-only graph access for AI assistants
A practical repository focused on mastering Spring AI concepts through hands-on implementations including RAG pipelines, vector search, AI agents, tool calling, memory handling, MCP servers, embedding
Cross-session persistent memory MCP server for AI assistants — local SQLite + FTS5, zero external dependencies
Persistent semantic memory service and MCP adapter for AI agents, powered by PostgreSQL and local Ollama models.
A simple Memory MCP server written in Rust
(BACKEND )An MCP-compatible vector search server built in Go, powered by Pinecone and OpenAI.
Layered, self-learning knowledge base for teams, served over the Model Context Protocol. PostgreSQL + pgvector hybrid search, roles, audit log, YAML layer presets.
Session Memory MCP server for ADK-Rust Enterprise — typed session state, scoped memory, replay snapshots, resumable workflows
ExpHub is an open-source MCP server that transforms AI assistants into collaborative knowledge workers. It automatically searches past experiences, captures new solutions in structured templates, and
An MCP server to build knowledge graph of OWL ontologies
Shared, encrypted, verifiable team memory for coding agents (MCP server)
a mcp server for interacting with ChromaDB
Serveur MCP pour bases de connaissance markdown versionnées en git. Des sessions Claude isolées les lisent et y déposent des propositions ; seul le rôle gestionnaire intègre.
MCP (Model Context Protocol) Server for Retrieval Augmented Generation using Mongo and Gemini, OpenAI, with A2A support Grok
CodeNinja Atoms: a sovereign AI operating system for the physical world. Open reference architectures for physical AI, with ontologies, model registers, costs and DOIs. CC BY 4.0.
Local-first semantic-search MCP server over a personal CS/FP/graphics library
CogniMem is a local MCP server in Rust that gives coding agents a persistent cognitive memory layer.
A production-grade AI agent framework — Go MCP servers, 50+ skills, structured role workflows, and hybrid semantic search.
MCP server for enterprise local codebase indexing, semantic search, and code dependency graphs.
MCP server for Naumu - access your knowledge graph from Claude Code, Cursor, and other AI coding agents
Ebbinghaus-based persistent memory for Claude. Memories decay with time, strengthen on recall.
Local-first shared memory for AI coding agents: one searchable store, served over MCP. MIT.
Slab team knowledge base MCP server: search posts, read post, create post, verify post.
Windows AgentMemory downstream for Codex with project-scoped persistent memory, bounded cross-project recall, and an authenticated loopback MCP service; prebuilt Windows releases are available as an u
O(1) routing, semantic search, and quality-filtered demand-driven experiences over 800+ records.
Direktori lengkap
RAG, graf, dan memori jangka panjang agen. 2,624 server, yang paling banyak dipakai lebih dulu. Masing-masing membuka halaman penerbit.