Memory and context
Everything here was classified as memory and context by keyword match against the maintainer's own description, so treat the grouping as a starting point rather than a verdict.
The list is ordered by the most recent commit, not by stars. A popular project that stopped in 2024 is not a better answer than a smaller one shipped last week.
Listed, not yet verified by us (60)
Published to the registry, but we have not yet checked its repository. Treat the entry as the maintainer’s claim only.
-
io.github.litheonhq/author-mcp-server
— v0.1.1
Recall, check, search, timeline, and graph tools for fiction writers via Seizn Memory v3.
-
UltraMemory
— v1.9.13
One memory, every AI: Claude, ChatGPT, Perplexity, Gemini, Cursor, OpenClaw, Hermes, any MCP client.
-
io.github.lonniev/personalbrain-mcp
— v1.16.3
FastMCP server for TheBrain API — AI access to a personal knowledge graph, Tollbooth-monetized
-
io.github.looptech-ai/understand-quickly
— v0.1.1
Public registry of code-knowledge graphs for AI agents with schema validation and drift detection.
-
Lore Context
— v0.6.0-alpha.1
Governed AI-agent memory, Evidence Ledger traces, evals, and portable context tools.
-
io.github.lorenzo-cambiaghi/lynx
— v1.7.5
100% local MCP server for semantic code search: AST chunking, hybrid retrieval, code knowledge graph
-
Droste
— v1.1.6
Local code-memory graph for AI coding agents.
-
io.github.louis49/melchizedek
— v1.0.2
Persistent memory for Claude Code — offline, single-file, hybrid search.
-
io.github.lucasmella-stack/mismem
— v0.2.0
Cooperative persistent memory for LLMs: episodes, memories and traits over SQLite (FTS5, Hebbian)
-
Dense Knowledge
— v1.2.0
Local-first MCP memory server for persistent LLM knowledge with BM25 retrieval.
-
Toon Memory
— v4.3.5
Offline persistent memory for AI coding agents — 35 tools, 80% fewer calls, no LLM
-
io.github.LuizEduPP/rememb
— v0.3.5
Persistent memory for AI agents — local JSON, zero config, no server required.
-
io.github.lulzasaur9192/agent-infra-mcp
— v1.0.2
18 tools: agent memory, API drift detection, and HMAC-signed trust receipts
-
io.github.lumayapartners/memini
— v0.4.0
Local-first project memory and mistake-prevention guardrails for AI coding agents.
-
io.github.Lyellr88/marm-mcp-server
— v2.37.0
Universal MCP Server with advanced AI memory capabilities and semantic search.
-
io.github.madezmedia/acmi-mcp
— v1.4.0
Persistent agent memory via ACMI — Profile/Signals/Timeline. 16 tools on Upstash Redis.
-
io.github.MagneticDogSon/fixflow
— v1.0.0
Collective memory for AI agents. One agent solves a bug — every agent gets the fix instantly.
-
io.github.mahabubul470/gpp
— v0.1.1
Project knowledge graph with history-checked belief staleness, changeset proposals, cost reporting
-
io.github.majiayu000/remem
— v0.6.51
Local-first automatic memory for Claude Code and Codex: capture, distill, recall from SQLite.
-
Performance Co-Pilot
— v1.5.1
Query system performance metrics via MCP - CPU, memory, disk I/O, network, processes
-
Pensyve
— v1.0.4
Universal memory runtime for AI agents — episodic, semantic, and procedural memory.
-
fish-bridge — Session Knowledge Graph
— v0.1.3
Compresses AI chat sessions into a typed knowledge graph. Local/offline via Ollama.
-
io.github.malkreide/lindas-mcp
— v0.2.1
MCP server for LINDAS — the Swiss administration's linked-data SPARQL knowledge graph (cube.link)
-
io.github.MarcelRoozekrans/memorylens-mcp
— v1.7.1
MCP server for .NET memory profiling with JetBrains dotMemory integration
-
io.github.marerem/longmem
— v0.2.1
Persistent cross-project memory for Cursor and Claude Code using local semantic search.
-
io.github.Mars-proj/verifiable-memory
— v0.1.2
Memory for AI agents that can't hallucinate — cited or abstains, provable forget, deterministic.
-
MarsNMe
— v0.3.0
Agent-agnostic memory backend that preserves continuity between humans and AI over time.
-
US Safety Recalls
— v1.0.0
NHTSA vehicle recalls and FDA food/drug recalls. 4 tools.
-
io.github.MastadoonPrime/agent-memory
— v0.1.0
Persistent, agent-owned memory with encrypted storage and shared knowledge commons.
-
Yagami AI Context Firewall
— v0.7.3
Govern model, retrieval, memory, and tool access for AI applications and agents.
-
io.github.MauriceIsrael/SmartMemory
— v1.0.1
Neuro-symbolic memory for LLMs (POC)
-
Compartment
— v4.5.0
Durable agentic memory, encrypted at rest. Fully offline: no network, no API key, no cloud.
-
engRAM
— v1.12.0
Fully offline, encrypted-at-rest vector memory for AI agents. AEAD-encrypted vectors, no cloud.
-
Ariadne
— v0.8.5
Local-first multilingual memory for Codex, Claude Code, and MCP clients using Qdrant and Ollama.
-
Mirror
— v0.4.0
Give Claude an honest self-model — behavioral tendencies built from evidence, not session memory. Mi
-
io.github.mdfifty50-boop/token-lens
— v0.1.2
Context window token analysis and budget management
-
FDA Data MCP
— v1.0.0
Clean FDA regulatory data: company resolution, facilities, recalls, inspections, approvals.
-
io.github.meharajM/agent-loop-mcp
— v1.0.3
Agentic memory manager. Install Skill: npx skills add meharajM/agent-loop-mcp
-
LLMemory
— v0.1.0
Search your AI chat history (ChatGPT, Claude, Codex) from any MCP client. Remote, private, read-only
-
io.github.mem0ai/mem0
— v1.0.0
Persistent memory for AI agents: add, search, update, and delete long-term memories.
-
io.github.MemoriLabs/memori-mcp
— v1.0.0
Memori MCP server — persistent AI memory with recall and augmentation tools
-
io.github.memoweft/memoweft
— v0.2.3
Portable AI memory as MCP tools: five reads and three controlled writes.
-
Memphora
— v0.1.3
Add persistent memory to AI assistants. Store and recall info across conversations.
-
nMEMORY
— v0.1.2
Memory your agent can trust — every answer carries its source; when it doesn't know, it says so.
-
io.github.Mibayy/token-savior
— v4.13.0
Structural codebase MCP server with persistent memory: navigate by symbol, recall across sessions.
-
io.github.Mibayy/token-savior-recall
— v4.11.0
Structural codebase MCP server with persistent memory: navigate by symbol, recall across sessions.
-
io.github.michael-denyer/hot-memory-mcp
— v0.8.0
Two-tier memory: hot cache (0ms) + semantic search. Self-organizing.
-
io.github.michielinksee/linksee-memory
— v0.11.5
Catches when your project drifts from its own decisions. Local-first cross-agent memory MCP.
-
OpenOCD Debugger
— v0.4.5
Debug microcontrollers via OpenOCD: flash, breakpoints, memory, registers and variables.
-
io.github.mifactory-bot/mifactory-agent-memory
— v1.3.1
Persistent memory for AI agents across Claude, ChatGPT and any MCP client.
-
Memory Vault
— v1.0.6
Local-first AI memory layer with hybrid search. Postgres + pgvector. Self-hosted, MIT.
-
io.github.Mikerichardmail/clarik-mcp-server
— v0.1.1
Clarity and memory persistent workspace context manager for Claude.
-
Provenio — Art Intelligence
— v0.4.2
Art provenance intelligence — 282K-node knowledge graph with cited answers and honest gaps.
-
datamcp — Hosted Model Context Protocol for Databases, APIs, and Agent Memory
— v0.9.9
PostgreSQL, MySQL, OpenAPI/Swagger, and shared Agent Memory with scoped access.
-
io.github.mnemopay/sdk
— v1.4.1
Memory + wallet for AI agents. Real payment rails, Agent FICO 300-850, Merkle audit, identity.
-
Mnemoverse Memory
— v0.8.0
Hosted memory for AI agents that learns and forgets — one key across Claude, Cursor & ChatGPT.
-
io.github.mnemox-ai/tradememory-protocol
— v0.5.4
MCP memory for AI trading agents. Store trades, recall similar setups, track strategy performance.
-
Linux MCP
— v0.2.12
Linux MCP server for real-time system monitoring - CPU, memory, disk, network, processes, Docker.
-
io.github.Morous-Dev/engram-cc
— v0.1.4
Universal AI coding assistant memory — session handoff, SLM compression, and semantic retrieval.
-
Motecloud Memory
— v0.1.0
Cloud-hosted MCP server for durable AI memory
Page 8 of 14
How this page is ordered
Entries are grouped by whether anyone is still working on them, using the date of the most recent push to the repository. They are not ordered by stars, because a star is a bookmark somebody left once and never took back.
Where we have not checked an entry yet, it says so rather than being mixed in with the verified ones.