Memory and Knowledge MCP servers
MCP servers in the Memory and Knowledge category. Persistent agent memory, knowledge graphs and long-term context storage. We have placed 1,311 here so far, listed below and ranked by their independent trust score.
1,311 catalogued · how we score
Memory and Knowledge at a glance
- Highest score
- 97 Notes
- Median score
- 39
- Scored
- 1,311 of 1,311
- Rescanned in 7 days
- 1,272
remote 525 · npm 444 · pypi 304 · oci 60 · mcpb 52 · nuget 5 · figures as of 2026-10-17 02:37 UTC · how we score
Top 100 by trust score Trust score 0–100
- npm 97
Local markdown notes: ranked + semantic search, tags, todos, and a wiki-link knowledge graph.
- npm 97
The private, owned conversation-memory layer for AI. Record, transcribe, and search every meeting.
- pypi 96
Cross-session memory for Claude over MCP — prioritised briefs, supersession, cross-project recall.
- pypi 96
Mine your AI coding session logs into a you.md profile with dated receipts, for an agent to read.
- npm 96
io.github.sairam0424/mindforge
Read the MindForge engine over MCP: knowledge graph, project health, and audit log.
- remote 95
Append-only decisions with provenance, supersession, retrieval, and audited MCP actions.
- npm 95
Local AI memory: neuroscience-inspired Data→Information→Knowledge in SQLite you own.
- pypi 95
io.github.jarmstrong158/context-keeper
Durable project-memory MCP: decisions, constraints, and pipelines across Claude sessions.
- remote 95
Hosted MCP memory: save sessions/decisions once, search from Claude, Cursor, ChatGPT. EU-hosted FTS.
- npm 95
io.github.SAIHM-Admin/saihm-mcp
MCP standards client for your own custodial SAIHM operator. Free start: @saihm/mcp-server-pro
- npm 95
io.github.SAIHM-Admin/saihm-mcp-server-pro
Free-to-start portable memory for AI agents: encrypted, shareable, provably erased. Join SAIHM.
- pypi 95
Long-term and multimodal memory for AI agents - character-aware, mem0-compatible, fully-local option
- pypi 94
Local-only MCP server for source-attributed Markdown memory and documentation retrieval.
- remote · npm 94
Persistent memory and virtual filesystem MCP server for AI agents.
- npm 94
io.github.emretheus/claude-remind-mcp
Search past Claude Code conversations. Local BM25 over JSONL with one-click claude --resume.
- remote · npm 94
Hosted AI agent memory that learns from outcomes, with shared rooms, in Claude, Cursor and ChatGPT.
- remote 93
Give every AI you use one shared, permanent memory. Store once, recall in whichever AI you open.
- mcpb · pypi 93
io.github.egoughnour/cowork-history
Hybrid search for Cowork history: FTS, Spotlight, and semantic vectors
- npm 93
kcp-agent — KCP navigation planner
Deterministic, fail-closed planner for KCP knowledge manifests: kcp_plan, kcp_load, kcp_validate.
- pypi 93
Knowledge base for Claude Code with semantic search, feed intelligence, and teams
- npm 93
io.github.octoryn/octopus-blackboard
Shared memory & coordination for AI coding agents — a blackboard, not an orchestrator.
- npm 93
A validated Markdown memory vault your coding agent can recall, project by project.
- pypi 93
Optional diagnostics MCP server for OpenReflex's ambient project muscle memory.
- npm 92
Markdown knowledge base as agent memory. Runs against the notes directory it is started in.
- pypi 92
Durable agentic memory, encrypted at rest. Fully offline: no network, no API key, no cloud.
- npm 92
io.github.MemoriLabs/memori-mcp
Memori MCP server — persistent AI memory with recall and augmentation tools
- pypi 92
Cross-machine, file-first memory for Claude Code: markdown + SQLite FTS5, synced with git
- remote · pypi 92
io.github.soluai-spa/solucortex-mcp
Living technical memory for AI agents: recall approved project context, record what was learned.
- pypi 92
Cross-platform shared memory and ticket coordination for AI agents across MCP clients.
- pypi 92
A self-improving, verifiable memory layer for AI coding agents.
- pypi 92
io.github.yantrikos/yantrikdb-mcp
Cognitive memory for AI agents — semantic recall, knowledge graph, and contradiction detection
- remote · npm 92
Shared, governed long-term memory for AI agents across tools and sessions via MCP and REST.
- remote 91
Persistent personal memory for AI assistants — save, search, and recall across every MCP client.
- npm 91
Codebase memory for AI agents: an AST index plus agent-written notes that self-stale.
- npm 91
Provenance-aware memory format for AI agents: every claim carries its source, age and boundary.
- npm 91
io.github.dcostenco/prism-coder
Session memory for coding agents: local-first recall, drift detection, on-device inference.
- pypi 91
io.github.ignatenkofi/memshelf-mcp
Working memory for AI agents: digest-indexed episodes on a git shelf, recalled a section at a time.
- pypi 91
io.github.JinyangWang27/people-context
Local-first MCP server giving AI agents contextual knowledge about the people in your life
- remote · npm 91
io.github.LorgAI/lorg-mcp-server
Shared, peer-validated knowledge archive for AI agents — search, contribute, and validate via MCP
- npm 91
Local Redis memory MCP for AI apps with hybrid caching and optional Mem0 cloud backup.
- npm 91
AI memory across Claude, ChatGPT, Gemini, and Cursor. Save, search, and recall context everywhere.
- npm 91
io.github.sergey-goncharenko/redpill
A transparent MCP server for agent reflection, conversation, and operator-enabled task decline.
- remote · npm 91
Agent-native notes, tasks, dev-docs, vaults, sync & handoffs. MCP + OpenAPI dual surface.
- npm 91
Local-first AI PKM memory for coding conversations.
- remote 90
Your AI's work, reviewed by your team, remembered - shared artifacts with review, plus team memory.
- remote 90
Persistent memory layer that saves and recalls your project context and preferences.
- npm 90
io.github.commet/argus-decision-mcp
Preserve a user-authorized judgment and append later answers. No model verdict or human score.
- npm 90
Persistent agent memory as plain Markdown in your repo - readable, diffable, with provenance.
- npm 90
Encrypted local ledger of structured user state, shared across every MCP-aware AI tool.
- npm 90
Local-first intent and provenance for Codex, Claude Code, Cursor, Gemini CLI, and MCP agents.
- npm 90
Owned, portable working memory: a plain-files markdown brain any model can read and cite.
- npm 90
A portable persona for MCP clients — the same agent in Claude Code, Codex, Cursor and VS Code
- pypi 90
Markdown-first long-term memory for AI agents. Hybrid BM25 + vector search, runs locally.
- pypi 90
Local-first agent memory over SQLite: remember, recall, link, forget. Degrades, never fails.
- pypi 89
io.github.0Mattias/bettermemory
Memory for coding agents, checked against the filesystem and git before it is believed.
- npm 89
Graph memory that dreams: Neo4j knowledge-graph memory for AI agents with hybrid search
- npm 89
Local-first project memory with legacy MCP and 2026 discovery compatibility.
- pypi 89
Local-first, governable long-term memory for AI coding agents
- npm 89
Memory for coding conventions and standing instructions that persists across sessions.
- npm 89
A local memory engine. You own the SQLite file. Not Mem0's hosted OpenMemory MCP.
- npm 89
io.github.jagilber-org/index-server
MCP instruction indexing server with search, CRUD, validation, and cross-repo knowledge promotion.
- npm 89
io.github.keshrath/agent-knowledge
Cross-session memory for AI agents - knowledge graph, scoring, semantic search
- pypi 89
Cross-agent handoff: the next coding agent starts from the last one's facts, not a blank page.
- pypi 89
Memory for AI agents that tracks beliefs over time and surfaces contradictions
- remote 88
Memoket — access your recording transcripts, summaries, and key takeaways over MCP.
- remote 88
Persistent AI memory shared across Claude, ChatGPT, coding agents, and compatible MCP clients.
- remote 88
Mitosis agent-memory platform: pricing, docs search, platform status, agent skills. No auth.
- npm 88
Self-hosted shared memory for a team of AI agents. Rooms, L0-L3 depth, no LLM on the read path.
- npm 88
Compile documents into a cited knowledge wiki. Retrieve evidence, query, and review via local MCP.
- remote 88
Create and search memories in your personal life constellation, UluP Life.
- npm 88
Shared project memory for Claude Code, Codex and Cursor: decisions and corrections through MCP.
- pypi 88
Knowledge-lifecycle MCP: turn agent work into memory, recall it across projects, promote to org.
- npm 88
io.github.jmeyer1980/neurodivergent-memory
Persistent knowledge graph MCP server for neurodivergent thinking. BM25 search, no cloud LLM.
- pypi 88
Skill memory for coding agents: learn, recall, reinforce, decay. Local SQLite, no API key.
- pypi 88
Persistent project context for Google Gemini. Python/FastMCP. IANA-registered .faf format.
- npm 88
Predict context rot, sign every agent write, tier reads. Markdown-native, 100% local.
- remote 87
Portable AI memory you own. Keep memories and notes across Claude, ChatGPT, and other AI tools.
- npm 87
io.github.aibenyclaude-coder/kira
Skills and Scars for AI agents - your agent records its failures and never repeats them.
- pypi 87
Markdown memory for coding agents that audits itself: drift reports and session digests.
- npm 87
Search local AI conversations by file or phrase and recall source turns. Four read-only tools.
- remote 87
A portable knowledge-graph memory you pass in and get back. No database. 4 of 6 free.
- remote 87
Query one person's second brain: contacts, companies, notes, files and connected accounts.
- pypi 87
Git for your AI's context: local-first, deterministic memory over MCP. An elephant never forgets.
- npm · oci 87
Your agents share what they learn. Semantik finds it by meaning, with no topic names to agree on.
- pypi 87
Review gate for shared agent memory: an unreviewed or hand-edited memory is never served.
- remote 87
Shared, versioned context that humans and AI agents can publish, review, annotate, and continue.
- pypi 87
Agent memory where every fact carries a receipt, and deletion is provable.
- remote 87
Shared knowledge base for AI agents. Semantic search across agents, no setup required — just a URL.
- remote · oci 87
emem, the verifiable memory protocol for the physical world
Shared, verifiable memory for machines and AI. Encode where data lives; decode with any AI.
- npm 86
Trust scores & reputation for the agent-to-agent economy. Verify A2A counterparties.
- remote 86
Robert Blust: One model, true everywhere
- remote · pypi 86
Use your Fulcra secure context lake to collaborate with other agents, read and write data, and more
- remote 86
Persistent memory for AI agents. EU-hosted, privacy-first, hybrid recall, contradiction detection.
- remote 86
Delx Protocol — Agent Recovery & Continuity
Free agent recovery and continuity. Public triage; register for a token to access private memory.
- remote 86
Cross-vendor AI memory over MCP. One semantic store, readable and writeable from every MCP client.
- npm 86
OSS to create Personas, Skills, Templates, Agents, and Memories to customize your AI experience.
- remote 86
Query any public logr profile — timelines, events, full context — plus owner-authorized writes.
- remote 86
Public coordination substrate for AI systems and humans with bounded MCP discovery and creation.
- npm 86
io.github.YonasValentin/mcp-memory-graph
Local-first memory for Claude Code and any MCP client: hybrid search + knowledge graph, $0/token.
- remote 85
Recall your team's coding-agent memory. Install the Assertion plugin to capture it automatically.
Every server here has been scored. A server is placed in this category because its description and tool definitions say what it is for. That is what the server declares about itself, not something we have tested, so check the score breakdown before you trust one.