MCP server category
Memory and knowledge MCP servers: comparison and full list
The Memory and knowledge category lists 250 open-source MCP servers, checked on GitHub. The best scored on our grid are Context7, Basic memory, and Hindsight. 79% received a commit in the last three months.
250servers
79 %active (3 months)
6official
30stars (median)
What Memory and knowledge MCP servers are for
Memory and knowledge MCP servers help an AI agent retrieve information or retain context across conversations. They support teams consulting documentation, building a knowledge base, or resuming work without restating every earlier decision. Context7 supplies code documentation, while Cognee manages memory using graph and vector stores. Basic memory offers a knowledge graph based on Markdown files that people and language models can read and write. You might ask: “Find the documented decisions for this project, cite their sources, and flag any that appear to have been superseded.” Retrieval and persistence depend on the specific server and its configuration.
Example uses:
- Retrieve a project decision together with the documents needed to verify its original context.
- Consult library documentation before proposing a code change that fits the project’s existing implementation.
- Save working notes in a memory space explicitly available to later authorized conversations and tasks.
- Prepare a searchable knowledge base from sources whose access and reuse permissions you control.
The category in figures
Of the 250 servers in the category (8% of the directory), 6 are official vendor implementations, 93% declare a licence, 26 offer a remote server and 37 need at least one API key or token according to the MCP registry. The median repository has 30 stars.
All Memory and knowledge MCP servers
Click a header to sort. Score out of 100: adoption, maintenance and framework (licence, registry, official status); risk: system access, secrets, licence, abandonment.
| Server | Stars | Last commit | Licence | Risk | Score |
|---|---|---|---|---|---|
| Context7 Up-to-date code documentation for LLMs and AI code editors. | 63,596 | Oct 23, 2026 | MIT | moderate | 90 |
| Hindsight Hindsight: long-term memory for AI agents modeled on human memory. | 53,389 | Oct 24, 2026 | MIT | low | 85 |
| Cognee Memory manager for AI apps and agents using graph and vector stores, with ingestion from many data sources. | 32,717 | Oct 23, 2026 | Apache-2.0 | low | 85 |
| Skill Seekers Turn docs, GitHub repos, PDFs, videos, Confluence, Notion and Slack/Discord into AI skills and RAG knowledge, exportable to vector databases | 15,212 | Sep 30, 2026 | MIT | low | 85 |
| Honcho Memory that reasons: continual learning for stateful agents. Better context, fewer tokens. | 7,759 | Oct 23, 2026 | AGPL-3.0 | low | 84 |
| Basic memory Local-first AI memory: a semantic knowledge graph of Markdown files that humans and LLMs both read and write, with optional cloud sync and t | 4,336 | Oct 24, 2026 | AGPL-3.0 | low | 86 |
| NoteDiscovery Self-hosted Markdown knowledge base with a web UI: search, read, create, edit, tag and template notes. | 2,848 | Oct 24, 2026 | MIT | low | 80 |
| Memanto Universal memory agent for AI: provides semantic search, namespace management, text/vector operations and RAG for local or remote environmen | 2,340 | Oct 24, 2026 | MIT | low | 84 |
| MCP memory service Memory service with semantic search, persistent storage and autonomous memory consolidation. | 2,038 | Oct 24, 2026 | Apache-2.0 | low | 78 |
| Minutes The private, owned conversation-memory layer for AI. Record, transcribe, and search every meeting. | 1,568 | Oct 23, 2026 | MIT | low | 77 |
| Superlog Open-source agent that observes and fixes your application. Query logs, traces, metrics, incidents. | 1,470 | Oct 23, 2026 | Apache-2.0 | low | 83 |
| SoloMD Read and search a folder of Markdown notes: search, backlinks, tags, tasks, outlines, git history. | 1,359 | Oct 22, 2026 | MIT | low | 76 |
| Open ontologies Ontology engineering for OWL, RDF and SPARQL: validate, query, diff, lint, version and govern knowledge graphs on an Oxigraph triple store. | 1,333 | Oct 23, 2026 | MIT | low | 76 |
| ApeRAG RAG platform combining Graph RAG, vector search and full-text search for building knowledge graphs and context engineering. | 1,321 | Sep 12, 2026 | Apache-2.0 | low | 71 |
| Deja vu Local memory over session histories from Claude Code, Codex CLI and opencode: lexical search, session-start auto-recall, secret redaction an | 1,301 | Oct 24, 2026 | MIT | low | 81 |
| Nautilus Compass Memory Local-first long-term memory for AI agents, with byte-recomputable signed verification receipts. | 1,254 | Oct 24, 2026 | — | moderate | 66 |
| MCP server chatsum Query and summarize your chat messages with AI prompts. | 1,026 | Dec 4, 2024 | — | high | 37 |
| Iai personal memory engine Local memory daemon with episodic, semantic and procedural tiers, SQLite and hnswlib storage, sleep-cycle consolidation and AES-256-GCM encr | 912 | Oct 23, 2026 | MIT | low | 75 |
| Projectmem Local-first memory for coding agents: records issues, failed attempts, fixes and decisions, re-injects them and warns at git commit before a | 866 | Oct 3, 2026 | MIT | low | 79 |
| Obsidian MCP server (cyanheads) Read, write, search, and surgically edit Obsidian notes, tags, and frontmatter via MCP. | 701 | Oct 24, 2026 | Apache-2.0 | low | 73 |
| ThoughtDAG Search local AI-agent conversation history by file or exact phrase and recall original source turns through four read-only tools. | 693 | Oct 24, 2026 | MIT | low | 78 |
| TokenSave Code intelligence for 15+ languages: semantic graph queries instead of file reads. 37 MCP tools. | 677 | Oct 24, 2026 | MIT | low | 73 |
| Vestige Local-first cognitive agent memory with FSRS-6 scheduling, smart ingest, SQLite storage, portable sync, an embedded dashboard and optional h | 656 | Oct 24, 2026 | AGPL-3.0 | low | 78 |
| MisakaNet Agent failure memory: search verified debugging lessons from real engineering sessions. | 544 | Oct 24, 2026 | Apache-2.0 | low | 77 |
| Telemem Mem0-compatible long-term and multimodal agent memory: character-isolated profiles, semantic deduplication, optional local stack and video m | 494 | Oct 23, 2026 | Apache-2.0 | moderate | 77 |
| Entroly Context control layer for coding agents: compression, prompt-prefix stabilization for caching, cheaper-model routing, local hallucination ch | 479 | Oct 22, 2026 | Apache-2.0 | low | 77 |
| Beever atlas Team knowledge base turning Slack, Discord, Teams and Mattermost chats into a knowledge graph and wiki with cited answers, semantic search a | 451 | Sep 10, 2026 | Apache-2.0 | low | 72 |
| Molio Knowledge Base Read-only access to your Molio local knowledge base: search, read, browse, and AI Q&A. | 434 | Oct 24, 2026 | — | moderate | 61 |
| MCP local rag Local document search: semantic search over PDF, DOCX, TXT and Markdown files with LanceDB vector storage and local embeddings. | 421 | Oct 22, 2026 | MIT | low | 76 |
| Equation.io Create interactive 2D and 3D graphs with validated equations, shareable links, and PNG previews. | 408 | Oct 24, 2026 | MIT | low | 77 |
| Graphlit MCP server Ingest content from Slack, Discord, websites, Google Drive, Linear or GitHub into a Graphlit project, then search and retrieve relevant know | 377 | Jan 12, 2026 | MIT | low | 51 |
| MemoryMesh Graph-based memory focused on AI role-play and story generation. | 354 | Mar 1, 2026 | MIT | low | 50 |
| Context Engine Compress logs, retrieval chunks, and code context into structured LLM-ready signal. | 326 | Jul 11, 2026 | MIT | low | 58 |
| VeritasGraph Zero-trust, air-gapped Enterprise GraphRAG MCP server with offline, citation-grounded answers. | 325 | Oct 24, 2026 | MIT | low | 70 |
| Apollo MCP Server MCP server that exposes GraphQL operations as tools for AI models. | 317 | Oct 23, 2026 | MIT | low | 70 |
| Shodh memory Cognitive agent memory with Hebbian learning, a three-tier architecture and knowledge graphs, running offline on edge devices. | 315 | Oct 19, 2026 | Apache-2.0 | moderate | 75 |
| Plur Open, local-first engram memory for AI agents: read, correct, delete; shared over MCP. | 308 | Oct 23, 2026 | Apache-2.0 | low | 70 |
| Knowledge rag Offline RAG for Claude Code with hybrid BM25 and semantic search, cross-encoder reranking, Markdown-aware chunking and query expansion. | 300 | Oct 23, 2026 | MIT | low | 70 |
| Emulo Loads a personal profile mined from your local Claude Code, Codex and OpenCode logs so agents work the way you do. | 299 | Oct 12, 2026 | MIT | low | 75 |
| Engrim Cross-model, local-first episodic memory engine for Claude Code, Cursor, Codex, and Antigravity. SQLite FTS5 (BM25) + 8MB static model2vec C | 299 | Sep 26, 2026 | MIT | low | 70 |
| Markmap MCP server Convert Markdown into interactive markmap mind maps with PNG/JPG/SVG export and live browser preview. | 289 | Aug 4, 2026 | MIT | low | 65 |
| ResiMind Exact polynomial checks, sparse expansion and verified rule memory. Local MCP tools, no model key. | 270 | Oct 15, 2026 | MIT | low | 69 |
| YourMemory Persistent agent memory with Ebbinghaus-style decay, hybrid BM25/vector retrieval, entity graph for multi-hop reasoning, auto-pruning and a | 270 | Sep 19, 2026 | — | moderate | 59 |
| Sage Local institutional memory for agents where BFT consensus among validators approves every memory before it is committed. | 257 | Oct 24, 2026 | Apache-2.0 | low | 74 |
| Yuque MCP server (yuque) MCP server for Yuque — expose your knowledge base to AI assistants. | 257 | Jul 15, 2026 | MIT | moderate | 57 |
| Neural memory Persistent memory for AI agents — 55 MCP tools, spreading activation recall. | 242 | Oct 23, 2026 | MIT | low | 69 |
| Lobu Shared, permission-aware company context for AI agents, with provenance, approvals and audit. | 230 | Oct 24, 2026 | Apache-2.0 | low | 69 |
| OMEGA Memory Local-first persistent memory for coding agents with semantic search, auto-capture, cross-session learning and intelligent forgetting. | 224 | Oct 9, 2026 | Apache-2.0 | low | 74 |
| Link Local personal memory for agents as MCP tools — remember, recall, search, context, graph traversal. | 217 | Oct 22, 2026 | MIT | low | 68 |
| NotebookLM MCP Automate Google NotebookLM: Q&A with citations, audio podcasts, video, content generation, source management and notebook library. | 208 | Oct 24, 2026 | MIT | low | 73 |
| GistPad MCP Manage personal knowledge, daily notes and reusable prompts in GitHub Gists, as a companion to GistPad. | 207 | Jan 16, 2026 | MIT | low | 48 |
| Mengram Agent memory with semantic, episodic and procedural types, a knowledge graph, Claude Code auto-save/recall hooks, smart triggers and multi-u | 204 | Oct 23, 2026 | Apache-2.0 | low | 73 |
| In Memoria Cumulative memory and pattern learning for coding assistants, with local SQLite/SurrealDB storage for semantic codebase analysis. | 175 | Dec 23, 2025 | MIT | low | 47 |
| MCP summarizer Summarize plain text, web pages, PDF documents, EPUB books and HTML content. | 167 | Feb 28, 2025 | — | high | 29 |
| Zettelkasten MCP Zettelkasten knowledge management: create, link and search atomic notes. | 167 | Apr 25, 2025 | MIT | moderate | 39 |
| Glean Remote MCP Server Remote MCP Server that securely connects Glean Enterprise Knowledge with your IDE, LLM, or agents. | 166 | Apr 17, 2026 | MIT | low | 53 |
| MCP zotero Work with collections and sources in your Zotero Cloud library. | 164 | Feb 4, 2025 | MIT | moderate | 39 |
| Piia Engram Persistent user identity across AI tools: preferences, lessons and decisions in local JSON with staged verification, AES-256-GCM encryption | 163 | Oct 23, 2026 | AGPL-3.0 | low | 72 |
| Akb Organizational knowledge base: Markdown docs, PostgreSQL tables and files linked by a URI graph, with hybrid search, Git history and multi-t | 163 | Oct 23, 2026 | — | high | 62 |
| ContextLattice Private-by-default memory and context layer for agents with staged retrieval across fused data backends and long-horizon context continuity. | 156 | Oct 21, 2026 | Apache-2.0 | low | 72 |
| Context keeper LLM-driven context and memory management: short- and long-term memory with vector, timeline and knowledge graph retrieval plus reranking. | 155 | Jan 13, 2026 | MIT | low | 47 |
| Openzim MCP Search and navigate Wikipedia and other ZIM-format knowledge archives offline, with smart retrieval and caching. | 146 | Oct 24, 2026 | MIT | low | 72 |
| Memex (iamtouchskyer) Zettelkasten-based agent memory system with bidirectional links | 144 | Sep 8, 2026 | MIT | low | 62 |
| MediaWiki MCP Server Read, search and edit any MediaWiki wiki, including Wikipedia and Fandom, with multi-wiki support and Semantic MediaWiki, Cargo, Wikibase an | 140 | Oct 22, 2026 | MIT | low | 71 |
| Aelios Self-hosted long-term memory gateway for AI clients: runs on your own Cloudflare account (Workers + D1 + Vectorize), captures conversations, | 138 | Oct 23, 2026 | AGPL-3.0 | low | 66 |
| Hexis Git-backed platform for skills, tools, and context for AI agents | 120 | Oct 23, 2026 | Apache-2.0 | low | 66 |
| Memorylane Desktop app that captures screen activity, stores AI summaries and OCR text locally, and exposes the history via semantic search and a timel | 120 | Oct 24, 2026 | GPL-3.0 | low | 66 |
| Mem0 MCP selfhosted Self-hosted mem0 for Claude Code: Qdrant vector search, Neo4j knowledge graph, Ollama embeddings and session hooks for automatic cross-sessi | 111 | Mar 13, 2026 | MIT | low | 45 |
| DocsMint Cloud or self-hosted knowledge workspace with hybrid document search, GraphRAG, and scoped MCP tools for reading and updating documents. | 109 | Oct 23, 2026 | Apache-2.0 | moderate | 70 |
| MCP server infranodus Map text into knowledge graphs to create a structured representation of conceptual relations and t… | 104 | Oct 21, 2026 | MIT | low | 71 |
| Loci Queryable second brain over your scattered notes, docs, PDFs and chat exports: hybrid retrieval (vector + BM25 fused with RRF), section-leve | 100 | Oct 22, 2026 | MIT | low | 70 |
| Knowl Persistent local memory for coding agents that retires replaced facts at write time, so agents read the current answer; facts are typed with | 99 | Oct 21, 2026 | Apache-2.0 | low | 70 |
| Claudex Persistent memory and full-text search over Claude Code conversation history indexed into SQLite, with session summaries and a web UI for ex | 97 | Jun 20, 2026 | MIT | low | 58 |
| Pensyve Universal memory runtime for AI agents — episodic, semantic, and procedural memory. | 97 | Oct 22, 2026 | — | moderate | 55 |
| Enzyme Semantic search and pattern discovery for Obsidian and markdown vaults. | 96 | Oct 24, 2026 | Apache-2.0 | low | 65 |
| Obsidian Vault MCP Local Zotero, MinerU, Obsidian literature workflow with transactional Analysis notes. | 94 | Aug 11, 2026 | MIT | low | 60 |
| Claude soul Learning engine for Claude Code: extracts signals from sessions, runs periodic reflections and promotes or retires behavioral frameworks bas | 92 | May 29, 2026 | MIT | low | 53 |
| Ragieai MCP Retrieve context from your Ragie knowledge base, connected to sources like Google Drive, Notion and Jira. | 91 | Feb 4, 2026 | MIT | low | 45 |
| Codealive MCP Semantic code search and analysis from CodeAlive for AI assistants and agents. | 90 | Sep 24, 2026 | MIT | moderate | 60 |
| KIP Knowledge Graphs to enable memory persistence, knowledge evolution, explainable interaction. | 88 | Oct 9, 2026 | MIT | moderate | 64 |
| Notebooklm MCP secure Security-hardened Google NotebookLM access: session-based conversations, notebook library management and source-grounded answers, with post- | 87 | Sep 3, 2026 | MIT | low | 64 |
| Pond Lossless archive and search for AI agent sessions across clients. | 87 | Oct 14, 2026 | Apache-2.0 | low | 69 |
| After effects MCP (JUNKDOGE-JOE) A stdio connector for the local ae-mcp After Effects panel; install the AE extension separately. | 85 | Oct 22, 2026 | MIT | low | 64 |
| Tela Self-hostable Markdown team wiki that agents can search, read and write, plus Atlas, which generates a cited wiki from git repos and Jira. | 85 | Oct 15, 2026 | AGPL-3.0 | moderate | 69 |
| Contextmcp Self-hosted documentation indexer that serves docs from various sources to agents with semantic search. | 84 | Oct 22, 2026 | Apache-2.0 | low | 64 |
| DecisionNode Record development decisions as structured JSON with Gemini embeddings and search them semantically from a local store shared across AI tool | 83 | Apr 15, 2026 | MIT | low | 44 |
| Robrain Self-hosted decision memory for coding agents: captures architectural decisions and rejected alternatives, and warns before a rejected appro | 81 | Oct 23, 2026 | Apache-2.0 | moderate | 69 |
| Cortex (cdeust) Neuroscience-inspired memory for Claude Code on PostgreSQL/pgvector: decay, consolidation, a predictive-coding write gate and lifecycle hook | 75 | Oct 24, 2026 | MIT | low | 69 |
| Total Agent Memory Local memory for coding agents: temporal knowledge graph with fact invalidation, procedural and episodic memory, AST codebase ingest and cro | 73 | Oct 14, 2026 | MIT | low | 69 |
| Codemem Persistent coding memory across sessions, machines and teammates, with memory search, optional sync, project sharing and automatic capture. | 73 | Oct 24, 2026 | MIT | low | 64 |
| Paper Distill MCP Academic paper search across 11 sources with AI curation, ranked push, Zotero and Obsidian support. | 68 | Mar 24, 2026 | AGPL-3.0 | moderate | 43 |
| Scrivener MCP Work with Scrivener 3 writing projects: document management, writing analysis, semantic search, character and plot memory, and content enhan | 68 | Oct 22, 2026 | AGPL-3.0 | low | 68 |
| Agentcairn Local-first agent memory: a Markdown Obsidian vault as source of truth plus a rebuildable DuckDB index for hybrid BM25, vector and graph rec | 68 | Oct 22, 2026 | Apache-2.0 | low | 63 |
| Myco: Agent First Cognitive Substrate Cross-session, cross-project agent memory built on a self-validating filesystem graph derived from ASTs and Markdown links, not embeddings. | 65 | Aug 12, 2026 | MIT | low | 63 |
| Docx MCP Read and edit Word (.docx) documents with tracked changes, threaded comments, footnotes, OOXML-level validation and document auditing. | 65 | Aug 5, 2026 | MIT | low | 58 |
| Devrag Local RAG for semantic vector search over Markdown documents with sqlite-vec and multilingual-e5-small embeddings, filterable by directory a | 64 | Apr 15, 2026 | — | moderate | 38 |
| Hatchdoor Self-host your Obsidian vaults: a web UI for you, MCP for your AI agents. No Obsidian, no plugins. | 62 | Oct 19, 2026 | AGPL-3.0 | low | 63 |
| ChatCrystal Local-first memory for AI coding conversations: imports chats from coding assistants into notes with semantic search, tag graphs and Markdow | 61 | Oct 23, 2026 | Apache-2.0 | moderate | 68 |
| Context Awesome Search curated awesome lists and fetch the most relevant resources for your agent. | 61 | Jun 10, 2026 | MIT | low | 56 |
| Perenna A lightweight, Git-backed permanent memory for AI agents. | 61 | Sep 9, 2026 | MIT | moderate | 58 |
| People context Local-first memory about the people in your life: identity resolution, relationships, facts, interactions, reminders and communication guida | 59 | Oct 24, 2026 | MIT | low | 68 |
| Smart connections MCP Local semantic search over Obsidian vaults via Smart Connections embeddings. Multi-vault, private. | 59 | Aug 22, 2026 | MIT | low | 58 |
| Roampal core Outcome-based persistent memory for Claude Code and OpenCode: memories that help get promoted, misleading ones get demoted. | 54 | Sep 26, 2026 | Apache-2.0 | low | 62 |
| Kaeru Memory for LLM agents: a local graph where the agent itself keeps decisions, tasks, hypotheses and reasoning between sessions, and gets a su | 48 | Oct 21, 2026 | — | moderate | 52 |
| Engram (tstockham96) Agent memory with semantic recall, automatic consolidation, contradiction detection and a bi-temporal knowledge graph. | 47 | Oct 16, 2026 | MIT | moderate | 67 |
| Callimachus Local hybrid search (SQLite FTS5 and on-device vectors) over coding-agent conversation history from multiple tools, so agents can recall the | 46 | Jul 14, 2026 | AGPL-3.0 | low | 55 |
| DollhouseMCP Reusable personas, skills, templates, agents and memory for AI clients, with dynamic permissions, versioning and a public collection of shar | 46 | Oct 24, 2026 | AGPL-3.0 | low | 67 |
| Mendeley MCP Search your Mendeley library, browse folders, get document metadata, search the global catalog and add papers to your collection. | 46 | Oct 13, 2026 | MIT | low | 62 |
| Assistant MCP ◆ Connect to your Pinecone Assistant and retrieve context from its knowledge engine. | 46 | Aug 14, 2026 | MIT | low | 67 |
| ContextStream MCP Server Persistent memory for AI coding tools with semantic code search, knowledge graphs, impact analysis and decision tracking. | 44 | Oct 24, 2026 | MIT | moderate | 72 |
| Waggle MCP Persistent graph memory that extracts facts from conversations into typed nodes with local embeddings, supporting temporal queries and confl | 44 | Oct 23, 2026 | Apache-2.0 | low | 66 |
| Lean memory Embedded local agent memory in one SQLite file per namespace: hybrid retrieval, append-only history queryable at any past time and human-rev | 43 | Aug 7, 2026 | Apache-2.0 | low | 61 |
| Kage Git-native memory for coding agents: JSON entries in the repo, verified against cited code so hallucinated citations are rejected and stale | 41 | Aug 29, 2026 | GPL-3.0 | low | 67 |
| Rms memory MCP Local-first memory for coding agents: hybrid LanceDB/Tantivy search, Markdown and code indexes, per-project vaults and recall that abstains | 40 | Oct 15, 2026 | MIT | low | 61 |
| IHMT Memory Long-term memory for coding agents as a tree of plain local files: searches before answering, keeps changed facts as history and flags them | 38 | Oct 15, 2026 | MIT | low | 66 |
| Lotus Wisdom Contemplative problem-solving using the Lotus Sutra's framework: multi-perspective reasoning, skillful means, non-dual recognition and medit | 36 | Oct 19, 2026 | MIT | low | 66 |
| Local FAISS MCP Server Local FAISS vector database for RAG with document ingestion (PDF, TXT, MD, DOCX), semantic search, re-ranking and CLI tools for indexing and | 36 | Apr 24, 2026 | MIT | low | 46 |
| Tokenmizer Session memory via a local OpenAI-compatible proxy that extracts tasks, decisions and files into a knowledge graph and checkpoints before co | 34 | Oct 23, 2026 | MIT | moderate | 65 |
| Remem Local-first memory for Claude Code and Codex: hooks capture sessions and an LLM distills them into SQLite, with auditable full-text and embe | 34 | Oct 21, 2026 | MIT | low | 65 |
| Enquire MCP Long-term agent memory backed by a local Obsidian vault: hybrid retrieval with reranking, agentic RAG, wikilink community detection, Obsidia | 34 | Oct 24, 2026 | MIT | low | 65 |
| Neotoma Deterministic state layer for agents: versioned entities like contacts, tasks and decisions with immutable observations and provenance, in l | 34 | Oct 23, 2026 | MIT | low | 60 |
| Obsidian MCP pro Obsidian vault access: full-text search, note CRUD, frontmatter queries, tags, backlinks, graph traversal, orphan and broken link detection, | 33 | Oct 23, 2026 | MIT | low | 60 |
| Vault Cortex Standalone Obsidian vault server: hybrid search, notes and files, memory and tasks; run locally or self-host for remote access. | 31 | Oct 24, 2026 | MIT | moderate | 65 |
| MCP Context Provider Static server providing persistent tool-specific context and rules to AI models. | 31 | Sep 2, 2026 | Apache-2.0 | low | 55 |
| Data Olympus Git-native Markdown knowledge base for coding agents with proposed vs. accepted guidance, validity windows, supersession chains and status-a | 30 | Oct 24, 2026 | Apache-2.0 | low | 65 |
| GEML — a plain text document format built to be edited in place, one section at a time Address Markdown and GEML documents by block instead of by line: list, get, set, add, delete, rename, revert, find and check one block, with | 29 | Oct 24, 2026 | MIT | low | 65 |
| Gnosis MCP Make Markdown documentation searchable: loads it into SQLite or PostgreSQL with keyword search and optional pgvector hybrid semantic search. | 29 | Oct 15, 2026 | MIT | low | 65 |
| Vectara MCP Access Vectara's RAG-as-a-service platform. | 29 | Jul 23, 2026 | Apache-2.0 | low | 48 |
| Engram rs Hierarchical agent memory engine with automatic decay, promotion, semantic deduplication and a self-organizing topic tree. | 28 | Mar 3, 2026 | MIT | moderate | 44 |
| ZenBrain Memory Seven-layer local agent memory that routes input into facts, episodes or procedures, searches all layers and consolidates repeated episodes | 27 | Oct 18, 2026 | Apache-2.0 | low | 70 |
| Mnemoverse Memory Hosted memory that learns and forgets: feedback re-ranks useful memories, recall fades by recency and similar memories consolidate. | 27 | Oct 23, 2026 | MIT | moderate | 64 |
| RTFM Local retrieval layer for coding agents: indexes a whole project (code, docs, PDFs, ebooks, spreadsheets, SQLite, Obsidian vaults) into SQLi | 27 | Oct 22, 2026 | MIT | low | 64 |
| Ragstack MCP Access RAGStack serverless knowledge bases on AWS: search, chat with AI answers, upload documents and media, scrape websites and analyze met | 25 | Oct 21, 2026 | Apache-2.0 | low | 64 |
| World model MCP Temporal codebase knowledge graph that links test failures to code changes, learns co-edit patterns, predicts regression risk and enforces e | 24 | Sep 15, 2026 | MIT | moderate | 59 |
| Fidelis Memory Local-first memory with verbatim recall, querying, health checks and context-sensitive orientation, using LLM-free retrieval by default. | 24 | Oct 19, 2026 | Apache-2.0 | low | 64 |
| Memo Local-first semantic memory: hybrid search, Markdown storage, MLX or CPU embeddings, contradiction detection, time-travel history and cross- | 24 | Oct 24, 2026 | MIT | low | 64 |
| SAME Stateless Agent Memory Engine Local agent memory with provenance tracking that detects when sources change, plus session handoffs, decision records, semantic search and a | 24 | Oct 15, 2026 | — | moderate | 54 |
| Celiums memory Cognitive memory engine with knowledge modules, circadian rhythm awareness, emotional state tracking, hybrid PostgreSQL/Qdrant search and pe | 23 | Aug 23, 2026 | Apache-2.0 | low | 54 |
| Mnemos Persistent memory for coding agents storing architecture decisions, bug root causes and conventions, with full-text search and token-budgete | 23 | Jul 21, 2026 | MIT | low | 47 |
| Yggdrasil Local-first memory for AI coding agents on SQLite/FTS5, curated and semantically de-duplicated, with data stored as plain rows you own. | 22 | Oct 22, 2026 | AGPL-3.0 | moderate | 63 |
| MediaWiki Connect to any MediaWiki wiki (Wikipedia, Fandom, corporate wikis) to search, read and edit pages, analyze links, view revision history and | 22 | Oct 20, 2026 | MIT | moderate | 63 |
| Memory MCP (JamesANZ) Store and retrieve conversation memories from multiple LLMs in MongoDB, with timestamps and LLM identification. | 22 | Dec 10, 2025 | MIT | low | 38 |
| Connapse Self-hosted knowledge backend for agents with hybrid vector and keyword search and container-isolated indexes. | 21 | Oct 24, 2026 | MIT | low | 63 |
| MCP me Digital identity for AI tools: your bio, career, skills and projects in local YAML profiles, auto-generated from public APIs such as GitHub, | 21 | Aug 11, 2026 | MIT | low | 58 |
| Mnemosyne OS ◆ Human-governed memory in local, domain-separated vaults with hybrid retrieval; also reads other coding agents' output. Requires the Mnemosyn | 20 | Oct 23, 2026 | — | moderate | 63 |
| Distil Reversibly compress large tool outputs into recoverable handles, expand them on demand and track token and cost savings locally. | 20 | Oct 24, 2026 | — | moderate | 53 |
| GoodMemory Local-first, auditable memory with scoped user/project storage in SQLite or Postgres, read-only recall by default and opt-in reviewed writeb | 20 | Oct 20, 2026 | MIT | low | 63 |
| Annota Annotate papers in Zotero: highlight key findings with semantic color coding, explain formulas and write structured reading notes. | 20 | Apr 17, 2026 | MIT | low | 38 |
| CacheOverflow Knowledge marketplace where agents search, publish and unlock previously solved problems, earning tokens for shared solutions. | 19 | Feb 26, 2026 | MIT | low | 43 |
| Obsidian MCP server (smith-and-web) Remote Obsidian vault management over SSE: notes, directories, frontmatter, tags, search and link operations, deployable with Docker. | 19 | Oct 24, 2026 | MIT | low | 58 |
| Noosphere Shared community repository of insights, decisions, warnings and patterns with semantic search, a 3D interactive globe and automated content | 18 | Oct 19, 2026 | Apache-2.0 | moderate | 63 |
| Alaya Neuroscience-inspired local agent memory that stores episodes, consolidates knowledge over time and builds a personal knowledge graph with s | 18 | Jul 16, 2026 | MIT | moderate | 51 |
| Agentpack Repo-native task continuity for coding agents: a reviewed task-state ledger of decisions, dead ends, evidence and checkpoints that later ses | 18 | Oct 17, 2026 | MIT | low | 63 |
| Project tessera Local workspace memory: indexes Markdown, CSV and session logs into a vector store with hybrid search, cross-session memory and knowledge gr | 18 | Mar 21, 2026 | AGPL-3.0 | low | 38 |
| Fable Full-text and semantic search over Claude Code transcript history, with exact thread recall and durable remembered facts in local SQLite. | 18 | Aug 10, 2026 | MIT | low | 53 |
| Obsidian MCP Self-hosted Obsidian server: semantic and full-text search on PostgreSQL/pgvector, wikilink graph traversal, atomic note CRUD and a self-des | 18 | Oct 24, 2026 | MIT | low | 58 |
| PipesHub Permission-aware enterprise search and RAG over business apps such as Google Workspace, Microsoft 365, Slack and Jira. | 17 | Oct 24, 2026 | Apache-2.0 | low | 62 |
| Agentic Task System (ATS) Turns your task manager into agent memory with hybrid retrieval over TickTick or an Obsidian vault, without a separate vector database. | 17 | Oct 22, 2026 | MIT | low | 62 |
| Engram (rwnalds) Git-backed, Obsidian-compatible Markdown second brain for agents: search ranks live notes above superseded ones, with per-agent tokens and a | 17 | Aug 14, 2026 | MIT | low | 57 |
| Zaxy Event-sourced agent memory on a hash-chained log with an embedded Kuzu temporal knowledge graph, salience-based forgetting and review-gated | 17 | Aug 10, 2026 | MIT | low | 57 |
| Easy obsidian MCP Create, read, update and search notes in local Obsidian vaults via filesystem access. | 17 | Oct 20, 2025 | — | high | 19 |
| Lians Agent Memory Bitemporal agent memory with deterministic fact supersession, point-in-time recall, memory lineage, conflict tracking and tamper-evident aud | 16 | Oct 19, 2026 | Apache-2.0 | moderate | 62 |
| Obsidian Everywhere Graph-native Obsidian vault access: search, backlinks, n-hop neighborhoods, paginated reads and safe partial and bulk edits with dry-run and | 16 | Oct 19, 2026 | MIT | low | 62 |
| Remembra Relay Self-hosted persistent agent memory with entity resolution, PII detection, AES-256-GCM encryption at rest and hybrid search. | 16 | Oct 24, 2026 | MIT | moderate | 62 |
| Alcove On-demand BM25 search over private project docs for coding agents, keeping docs out of public repos. | 16 | Oct 23, 2026 | Apache-2.0 | low | 57 |
| Cross llm MCP Cross-LLM communication and memory sharing so different AI models can collaborate and share context across conversations. | 16 | Oct 15, 2026 | MIT | low | 57 |
| CogniRepo Persistent memory and codebase context for coding agents: FAISS vector store, AST symbol index, knowledge graph, episodic journal and cross- | 15 | Oct 24, 2026 | MIT | low | 62 |
| Linksee memory Local-first cross-agent memory in one SQLite file with a layered structure, Ebbinghaus-style forgetting and detection of code drifting from | 15 | Sep 9, 2026 | MIT | low | 57 |
| Midas Local-first long-horizon agent memory: source-traceable recall, belief revision, selective forgetting and a guard against memory-driven dest | 15 | Jul 28, 2026 | MIT | low | 57 |
| Agent memory (xChuCx) Git-native project memory for coding agents: Markdown in your repo, reviewable staged updates, secret/PII-safe and branch-aware, without clo | 15 | Oct 2, 2026 | Apache-2.0 | low | 62 |
| NexusMem Correlates failed shell commands and their exit codes with whatever later fixed them, alongside git diffs and docs, stored locally in SQLite | 15 | Sep 27, 2026 | MIT | low | 62 |
| Recallnest Local-first memory for coding agents: hybrid vector/BM25 retrieval with reranking, knowledge graph, session checkpoint/resume and multi-scop | 15 | Oct 23, 2026 | MIT | low | 57 |
| Kremis Local deterministic knowledge graph on redb with no LLM or embedding calls, BLAKE3 state hashing and canonical export for byte-identical aud | 15 | Oct 21, 2026 | Apache-2.0 | low | 57 |
| Longhand Persistent local memory for Claude Code: indexes all sessions verbatim into SQLite and ChromaDB for semantic recall across your history, wit | 14 | Sep 28, 2026 | MIT | low | 61 |
| Memory MCP (michael-denyer) Two-tier memory (hot cache and cold semantic search) that promotes frequently used patterns, extracts knowledge from Claude outputs and link | 14 | Oct 14, 2026 | MIT | low | 61 |
| Obsidian Turbocharged Obsidian vault access with role-based access control, native search, multi-vault support, pluggable embeddings and SLSA provenance. | 13 | Oct 24, 2026 | AGPL-3.0 | low | 61 |
| Apple notes MCP (ailenshen) Read and write Apple Notes with bidirectional Markdown conversion: SQLite queries for listing and search, AppleScript for full CRUD. | 13 | Oct 16, 2026 | MIT | low | 56 |
| Lennys quotes Search Lenny's Podcast transcripts with YouTube timestamps for product management insights on PRDs, strategy and PM careers. | 13 | Oct 19, 2026 | — | moderate | 46 |
| MCP persona sessions Structured, persona-driven sessions for interview preparation, personal reflection and coaching, with timers and performance evaluation. | 13 | Mar 2, 2026 | GPL-3.0 | low | 36 |
| Empathy framework Five-level AI collaboration system with persistent local-first memory via MemDocs and anticipatory capabilities. | 13 | Apr 13, 2026 | Apache-2.0 | low | 36 |
| Claude find Retrieve memory from across your Claude Code sessions on demand. | 12 | Jun 10, 2026 | MIT | low | 49 |
| Memex (STiFLeR7) Watches git repos and builds a temporal knowledge graph of modules, symbols, decisions and open problems via Graphiti and Neo4j, served to A | 12 | Oct 21, 2026 | MIT | moderate | 61 |
| XMemo XMemo: user-owned agent memory to save, search, recall and manage scoped memories across AI tools. | 12 | Oct 24, 2026 | MIT | moderate | 61 |
| Coldstart Codebase memory for coding agents: a deterministic AST index finds task-relevant files, and in-repo Markdown notes flag themselves stale whe | 11 | Sep 29, 2026 | MIT | low | 60 |
| Skillmem Self-improving skill memory for coding agents: useful skills are reinforced, unused ones fade; local English/Russian hybrid search, tamper-e | 11 | Oct 23, 2026 | Apache-2.0 | low | 60 |
| Hive Vault On-demand Obsidian vault access: adaptive context loading, full-text and ranked search, health checks, auto git commits and delegation to ch | 11 | Oct 23, 2026 | MIT | moderate | 60 |
| Lore Local semantic search across Claude Code conversations with hybrid vector and keyword search, background indexing and per-project selection. | 11 | May 13, 2026 | MIT | low | 43 |
| LIFE Persistent identity for AI agents: servers for drives, relationships, semantic memory with decay, working threads, learned patterns, journal | 11 | Feb 16, 2026 | MIT | low | 35 |
| Genome Local persistent agent memory without LLM calls: semantic recall over SQLite with bi-temporal fact tracking. | 10 | Oct 1, 2026 | Apache-2.0 | low | 60 |
| Memory arbiter MCP Local memory middleware: targeted retrieval instead of full-memory loading, rule-based conflict arbitration and one SQLite store shared acro | 10 | Oct 21, 2026 | Apache-2.0 | low | 60 |
| KLYPIX Shared Project Memory Versioned project brain for coding agents, committed with the repo: decisions, corrections, evidence anchors that flag code drift and file-o | 10 | Oct 24, 2026 | Apache-2.0 | low | 60 |
| Lockstep Shared decision memory for teams using AI coding agents: captures engineering decisions, ranks them by blast radius and briefs agents before | 10 | Oct 21, 2026 | Apache-2.0 | low | 60 |
| Tribal Self-hosted semantic memory for an engineering team's tribal knowledge: the decisions and reasoning behind the code, queryable by the team a | 10 | Aug 6, 2026 | — | high | 45 |
| CodeCortex Persistent codebase knowledge for coding agents: symbols, dependency graphs, co-change patterns and architectural decisions extracted with t | 10 | Apr 21, 2026 | MIT | low | 35 |
| AvianSuite Safe write access for AI agents: an append-only business fact store where every change is kept, attributed to the agent that made it, and ca | 9 | Oct 16, 2026 | AGPL-3.0 | low | 66 |
| Engram (HBarefoot) Offline persistent agent memory on SQLite with local embeddings, hybrid semantic and full-text recall, secret detection and contradiction ha | 9 | Jul 7, 2026 | MIT | low | 48 |
| Artel Self-hosted coordination for agent fleets: shared semantic memory, tasks, agent-to-agent messaging, session handoffs and cross-agent knowled | 9 | Oct 20, 2026 | MIT | low | 60 |
| Sessionmem Local memory for coding assistants: watches sessions and injects a compact summary at the start of each new one, stored in a SQLite file. | 9 | Oct 23, 2026 | MIT | low | 55 |
| Mnemostack Self-hosted hybrid agent memory on Qdrant combining vector search, BM25, temporal retrieval and an optional Memgraph knowledge graph via ran | 9 | Sep 28, 2026 | Apache-2.0 | low | 55 |
| Wellread Shared research cache across agents: reuse answers from verified sources, or save new research for the next developer. | 9 | Apr 19, 2026 | AGPL-3.0 | low | 35 |
| Hypermnesic Git-first agent memory: Markdown files are the source of truth, the index is disposable and writes are reviewable commits, with hybrid searc | 9 | Sep 27, 2026 | AGPL-3.0 | low | 55 |
| Inspeximus: agent memory with provenance, GDPR erasure and a tamper evident audit trail Agent memory with a correction channel: supersede or revert stale facts, block restated old values, and prove deletions with signed tombston | 8 | Oct 22, 2026 | MIT | low | 59 |
| Crbro memory Persistent agent memory in local JSON files: neuron/synapse graph with heat scoring, fact-level search, corrections, secret redaction and te | 8 | Oct 18, 2026 | MIT | low | 59 |
| Agent memory (g1itchbot8888-del) Three-layer agent memory (identity, active, archive) with semantic search, graph relationships and conflict detection. | 8 | Feb 27, 2026 | MIT | low | 34 |
| Memstate MCP Versioned, structured agent memory storing facts as keypaths with full version history and automatic conflict detection. | 8 | Apr 1, 2026 | Apache-2.0 | low | 34 |
| AIWiki Search and read AiWiki, a bilingual English/Chinese encyclopedia of AI-coding pitfalls and LLM privacy protection, with cited evidence. | 8 | Sep 15, 2026 | CC-BY-SA-4.0 | low | 49 |
| Cogmemai MCP Cloud-based persistent memory for Claude Code with semantic search, AI extraction and project scoping. | 7 | Oct 13, 2026 | MIT | moderate | 58 |
| Krimto Team memory for coding agents stored as Markdown in git, with user, team and org access levels and hybrid SQLite/sqlite-vec retrieval. | 7 | Jun 2, 2026 | Apache-2.0 | low | 46 |
| Agent Memory OS Local-first memory for AI agent teams: private, team and project access control, associative recall and federated sync with revocation, plus | 7 | Oct 1, 2026 | Apache-2.0 | low | 58 |
| Synapse Zero-runtime-dependency Markdown memory vault with SQLite search, linked wiki pages, ChatGPT/Claude imports, and human-approved agent note p | 7 | Oct 5, 2026 | MIT | low | 53 |
| Acheron MCP server Persistent memory shared across Claude Chat, Code and Cowork, stored in local SQLite with full-text search. | 7 | Mar 26, 2026 | MIT | low | 33 |
| Context memory Persistent, searchable context storage across Claude Code sessions using SQLite FTS5, with AI session summaries, checkpoint recovery and a w | 7 | Feb 17, 2026 | MIT | low | 33 |
| Gingugu Local SQLite memory for coding assistants: typed memories with confidence lifecycle, namespaces, knowledge graph, hybrid search and keychain | 7 | Oct 24, 2026 | MIT | low | 53 |
| Passbaton Local session continuity across Claude Code, Codex CLI and Gemini CLI: context injection on start, compaction handover, memory, tasks and mu | 7 | Oct 24, 2026 | MIT | low | 53 |
| Agent Memory Bridge Local-first memory for coding agents that turns coding sessions into reusable engineering memory: decisions, gotchas and domain knowledge. | 7 | Oct 11, 2026 | MIT | low | 53 |
| Agentmem Governed memory for coding agents with trust lifecycle (hypothesis, active, validated, deprecated), conflict detection, staleness tracking a | 6 | Apr 17, 2026 | MIT | low | 38 |
| Graph MIND One local memory shared by every coding agent and model on your PC: every conversation saved verbatim with zero LLM calls, recalled as a ~3k | 6 | Oct 24, 2026 | AGPL-3.0 | low | 58 |
| Penfield Memory Penfield: persistent memory with hybrid BM25/vector/graph search, typed graph relations, context checkpoints, artifact storage and a persona | 6 | Apr 4, 2026 | AGPL-3.0 | low | 38 |
| Mindmap MCP server (ravi-labs) Local-first memory and context handoff across AI tools, with graceful decay, a persona layer and a portable memory passport. | 6 | Jul 6, 2026 | Apache-2.0 | low | 46 |
| Open memex Local-first persistent memory for AI coding agents: plain Markdown as the source of truth with SQLite FTS5 search, one memory shared across | 6 | Oct 24, 2026 | Apache-2.0 | low | 58 |
| Agenthelm Shared, versioned memory and governance for AI coding agents, resolving architectural decision conflicts across agents. | 6 | Aug 25, 2026 | MIT | low | 48 |
| Afair Self-organizing, self-hostable, encrypted memory for AI tools, with background entity extraction, conflict resolution, consolidation and dec | 6 | Oct 24, 2026 | AGPL-3.0 | low | 53 |
| Conversation handoff MCP Hand off conversation context between Claude Desktop projects and across MCP clients, stored in memory rather than files. | 6 | Sep 29, 2026 | MIT | low | 53 |
| Flaiwheel Self-hosted memory and governance for coding agents: structured knowledge capture, hybrid search with reranking, codebase analysis and git-n | 6 | Sep 11, 2026 | — | moderate | 38 |
| MCP agent memory Filesystem-based persistent agent memory: agents read, write and search memory while a background daemon handles consolidation and extractio | 6 | Oct 23, 2026 | MIT | low | 53 |
| Counsel MCP Strategic reasoning, multi-perspective debate analysis and interactive advisory sessions via the Counsel API. | 6 | Jan 15, 2026 | MIT | low | 33 |
| Waypath Local-first memory CLI for coding agents: SQLite-backed context, graph-aware recall via FTS5 and RRF, and governed memory with promote and r | 6 | Jun 30, 2026 | MIT | low | 41 |
| Ctxfile Snapshots a project's working state (files, git, plan, decisions) into one context object so a session can move between agents. Local and re | 5 | Oct 23, 2026 | Apache-2.0 | moderate | 63 |
| Kybase Self-hosted Markdown knowledge base that doubles as persistent memory for AI agents: a notes app you browse and edit (wikilinks, backlinks, | 5 | Oct 22, 2026 | AGPL-3.0 | moderate | 57 |
| Rememb Persistent agent memory in local JSON with sectioned entries (project, user, context), semantic search, a CLI and per-project scope. | 5 | Oct 5, 2026 | MIT | low | 57 |
| LINZA Review-gated sidecar for Markdown workspaces: indexes notes into SQLite and proposes links, domains and memory with evidence, editing files | 5 | Oct 16, 2026 | MIT | moderate | 57 |
| Rekindle Session continuity: start-of-session reports with gap detection and scoring, structured end-of-session capture and BM25 memory search, store | 5 | Oct 24, 2026 | MIT | low | 57 |
| Openhive MCP Shared knowledge base where AI agents search and post problem-solution pairs, with semantic search, duplicate detection and auto-scoring. | 5 | Apr 14, 2026 | — | moderate | 27 |
| Iranti Persistent shared memory for coding agents: facts stored as entity/key/value triples with hybrid semantic search, task checkpoints and confl | 5 | Jul 6, 2026 | — | high | 35 |
| Scholar RAG MCP Academic paper knowledge base over local PDFs: MinerU parsing, metadata normalization, Qdrant vector search with reranking and paginated ful | 5 | Sep 4, 2026 | MIT | low | 52 |
| Graphiti Local Local temporal knowledge graph with six read-only retrieval tools, Ollama inference, embedded LadybugDB, and a separate human-approved CLI w | 5 | Oct 23, 2026 | Apache-2.0 | low | 57 |
| Vulcanus Generates a Git-versioned Markdown vault as project memory, then serves it over MCP. recall returns a project's capsule plus the read-next l | 5 | Oct 19, 2026 | MIT | low | 57 |
| Rag kb Local-first agent memory and knowledge base: hybrid dense and BM25 retrieval, document and webpage ingestion and optional RAG answers via lo | 5 | Oct 22, 2026 | Apache-2.0 | low | 52 |
| Adhd hub Self-hosted project-continuity hub for coding agents: tracks unfinished work, progress, overlap and reminders across clients. | 5 | Oct 18, 2026 | MIT | low | 52 |
| Memkin Local-first personal memory that distills Feishu/Lark chats and Claude Code/Codex sessions into a private knowledge graph of people, project | 5 | Oct 23, 2026 | Apache-2.0 | low | 52 |
| Hipocampo Bilingual (English/Spanish) dual-memory system on PostgreSQL, pgvector and NVIDIA NIM with progressive retrieval, deduplication, checkpoints | 5 | Oct 24, 2026 | MIT | low | 52 |
| Lore MCP Persistent knowledge layer for agents: knowledge base, investigation threads and a journal with multi-agent attribution, on SQLite, PostgreS | 5 | Jun 2, 2026 | MIT | low | 40 |
| Owl MCP Work with OWL/TTL/RDF ontologies: SPARQL queries, HermiT/Pellet reasoning and CRUD operations on knowledge graphs. | 5 | Oct 7, 2026 | MIT | low | 52 |
| Devrecall Local-first index of your commits, PRs, Jira/Linear tickets, Confluence docs, Slack threads and calendar events to search and cite past work | 5 | Sep 10, 2026 | MIT | low | 47 |
| Weighted compact Inspectable memory for Claude Code: read-only search and session compaction over a local, signal-scored parse of its project logs, with no o | 5 | Jun 10, 2026 | MIT | low | 40 |
| Customgpt MCP Access the CustomGPT.ai RAG-as-a-service API. | 5 | Oct 10, 2026 | MIT | low | 52 |
| Artifacta MCP ◆ Artifact store for agent outputs: persist, retrieve and share them across runs and sessions, with content-hash dedup and expiring share link | 1 | Jul 28, 2026 | MIT | moderate | 55 |
| Brainy ◆ Self-hosted shared brain for multiple agents: Git-versioned Markdown knowledge plus a task queue with atomic claims, per-space ACL, audit lo | 0 | Oct 7, 2026 | AGPL-3.0 | low | 60 |
| Solucortex MCP ◆ Technical memory for AI agents: recall a project's approved decisions, conventions and risks at task start and record lessons at the end. | 0 | Oct 6, 2026 | MIT | moderate | 60 |
| Telys — on device memory ◆ Official Telys MCP server — private, on-device memory & retrieval for AI assistants: 19 tools covering memory CRUD, semantic + on-device BM2 | 0 | Oct 11, 2026 | Apache-2.0 | low | 60 |
Official servers
Published by the service's own vendor (per the awesome-mcp-servers list): they usually track the API closely and are better maintained.
- Assistant MCP 46 ★
- Mnemosyne OS 20 ★
- Artifacta MCP 1 ★
- Brainy 0 ★
- Solucortex MCP 0 ★
- Telys — on device memory 0 ★
Choosing and securing
Distinguish documentation retrieval from memory that stores context from your own interactions. Review source support, update mechanisms, and citation handling. Examine sharing, export, deletion, and local or remote storage options. Compare maintenance, licensing, and official or community ownership. The documentation should explain retrieval behavior and access controls clearly, including how indexed material is updated and how conflicting or outdated entries can be identified and removed.
Persistent memory can retain secrets, personal information, or assumptions that later become incorrect. Define what may be stored, who may retrieve it, and how deletion works. Malicious source material can poison the memory or introduce persistent instructions. Preserve provenance and separate users and projects. Review backups, indexes, and duplicate copies when deleting material, since removing a visible note may not remove every stored representation.
Before connecting a server to an agent with access to your data, run the AI agent security check.
Most recent
- ResiMind created October 8, 2026
- Graph MIND created October 8, 2026
- IHMT Memory created September 30, 2026
- Brainy created September 30, 2026
- Open memex created September 26, 2026
Other categories
Learn more
Frequently asked questions
What is the best Memory and knowledge MCP server?
On our grid (adoption, maintenance, framework), Context7 (90/100), Basic memory (86/100), and Hindsight (85/100) come first. The right choice mostly depends on the service you need and the rights you are willing to grant.
Are these servers free?
93% declare an open-source licence and are free to use. 37 need an API key: the connected service may be paid.
Will the agent automatically remember everything I tell it?
That depends on the exposed tools, client behavior, and storage rules. Some servers require an explicit action to write a memory. Check what is retained and where it is stored. Establish exclusions for credentials and personal information before enabling any feature that automatically records content from your conversations.
How can I keep old information from appearing current?
Retain dates and source references, and establish a process for updating or removing entries. Ask the agent to flag conflicting information and cite retrieved documents. A statement’s presence in memory does not establish that it still applies to the situation or question you are currently working on.
Related articles
- Build your own MCP server in 30 minutesOctober 24, 2026
- Automate your inbox with an AI agentOctober 18, 2026
- MCP, A2A, and tool calling: agent protocols explainedOctober 17, 2026
- Build an AI agent with n8n, without codingOctober 16, 2026
Neutrality. No affiliate links. No vendor pays to be reviewed, rated or ranked. Reviews are directed by François Chollet, neutral and factual, and every data point is dated and sourced. How we score