"MCP server for remembering key project decisions, tracking framework and settings" matching MCP servers:

Hardware-accelerated codebase mapping that indexes Git repositories into Postgres/pgvector and serves code search, relationships, and static analysis results via a stdio MCP server.

Enables Claude to perform hybrid search across local documents by combining semantic vector retrieval and BM25 keyword matching for optimal context recovery. It supports multiple file formats including PDF, CSV, and Markdown, leveraging local Ollama models for private and efficient document querying.

Semantic search over project-specific decision rules using Chroma, enabling LLMs to retrieve relevant context.

A project search MCP server based on Milvus vector database, supporting semantic search, hybrid search, and exact scalar queries.

A Machine Control Protocol (MCP) server that enables storing and retrieving information from a Qdrant vector database with semantic search capabilities.

An integration server implementing the Model Context Protocol that enables LLM applications to interact with Milvus vector database functionality, allowing vector search, collection management, and data operations through natural language.

MCP server for searching, reading, listing, writing, and appending Markdown wiki content using RAG with ChromaDB.

Munin is a high-performance, pragmatic memory layer for AI agents (Cursor, Claude Code, OpenClaw, Gemini CLI,...). Unlike other solutions, Munin focuses on developer productivity with: * Multi-Project Support: Isolate memories into separate "brains" (Context Cores). * GraphRAG: Automatically builds a knowledge graph from your context. * Sub-200ms Search: Blazing fast Hybrid & Semantic

An API that enables document querying through a Retrieval-Augmented Generation system implemented with Memory-Controller-Policy architecture for improved maintainability and scalability.

Enables AI clients to search and analyze code/docs through a central Pinecone-backed vector store, inspect project inventories and git sync status, rank work by urgency, and perform deep architectural audits via MCP.

Membot is an MCP server that gives AI agents swappable, searchable memory stored on a neuromorphic substrate.

Enables users to ingest documents into a PostgreSQL/pgvector knowledge base, run semantic search over them, and get grounded answers through a retrieval-augmented generation pipeline backed by a free LLM. It also lets clients spin up specialized AI agents on demand and exposes knowledge-base stats and configuration as resources for tutoring workflows.

A local-first Graph-RAG system combining ChromaDB with metadata-based graph relationships and Gemini 2.5 Flash for intelligent Q&A over Obsidian vaults, supporting MCP clients like Claude Desktop, Cursor, and Raycast.

A server implementation that allows secure communication between MCP clients and privateGPT, enabling users to chat with privateGPT using knowledge bases and manage sources, groups, and users through a standardized Model Context Protocol.

A local Retrieval-Augmented Generation system that enables users to ingest markdown files into a FAISS-powered vector knowledge base for semantic search. It provides tools for document indexing and context retrieval to support informed LLM queries without external dependencies.

A persistent memory layer for Claude Code agents: five MCP tools (recall, remember, session, distill, status) over a markdown vault, SQLite FTS5 and an optional self-hosted Hindsight vector store, so an agent remembers facts, decisions and corrections across sessions.

Official Telys MCP server: private, on-device AI memory and retrieval powered by native Mojo kernels. 19 tools: memory CRUD, semantic + BM25 search, single-key filters, compaction/IVF/tuning and self-refreshing repo auto-indexing. Stdio. Introspection needs no credentials; execution requires a one-time free telys login. Source: packages/telys-sdk/telys/mcp.py. Registry: io.github.thyn-ai/telys.

Gives every AI agent you use one shared, versioned memory in a local SQLite file, so a fact saved from one app is found by all the others. Runs fully offline with no API key, records which agent wrote each change, and keeps every prior version so nothing is silently overwritten.

MCP server for OpenAI Vector Store API, managing vector stores, files, file batches, and semantic search.

Long-term and multimodal memory for AI agents. Store facts and conversations with add_memory, recall them with search_memories — 8 tools over stdio/SSE/HTTP. Per-character memory isolation, LLM-based semantic deduplication, FAISS + JSON storage, and a fully local option (Ollama, no API key). Drop-in compatible with Mem0.

Enables coding agents to share a persistent local memory store across sessions and clients, saving, searching, updating, and retrieving facts, decisions, incidents, preferences, references, and snippets with semantic and lexical search.

An MCP server that provides AI assistants with access to Multi Theft Auto: San Andreas function documentation through vector similarity search and smart keyword expansion. It enables efficient information retrieval with features like deprecation warnings and SQLite caching for technical documentation.

A personal memory MCP server that ingests AI agent conversation logs from multiple platforms into a searchable PostgreSQL+pgvector database, enabling cross-session recall of past reasoning and decisions.

Serves UltraRAG memory to agents over stdio MCP, providing project-local and per-user global memory. It lets agents read and append standing memory and daily dialogue rounds in UltraRAG's format, with an optional browser view.

Enables agents to run semantic search across one or more local project directories by automatically maintaining a LAN-local Qdrant index with Ollama embeddings. Indexing, staleness checks, and incremental updates happen transparently, so users can query code by meaning without managing collections, chunks, or hashes.

An MCP server that retrieves resume/experience evidence relevant to a job description via vector RAG, and tracks fit-analysis results in a configurable tracking store (Notion or SQLite), with tools like match_job, push_to_tracker, and list_applications.

Project-scoped semantic workspace memory for AI coding assistants. Watches your project files and auto-indexes code and docs into Qdrant using tree-sitter semantic chunking and hybrid search (dense + sparse + RRF)

A local-first MCP server providing persistent, project-scoped and global memory for AI agents using ChromaDB and Ollama embeddings, fully offline.

A persistent semantic memory system for Claude Code, using vector search and a judgment ledger to surface prior decisions and calibrate predictions.

Enables AI clients like Claude Desktop and Cursor to persist project knowledge across sessions and tools by extracting durable facts from conversations, deduplicating them, resolving contradictions, and retrieving only the most relevant, token-budgeted facts for the current task. Adds PII redaction, project scoping, TTL-based staleness handling, and an append-only audit log so shared context stays current and safe.