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.imashishkh21/atlaso
— v0.1.0a6
Open-source memory for AI agents. Conflict-flagging recall, scope-bag dispersion, local SQLite.
-
io.github.Indhar01/memograph
— v0.4.0
Graph-based memory system for LLMs with knowledge graphs and semantic search.
-
Contextful
— v0.1.0
Efficient context management: code search, evidence packs, and memory for coding agents.
-
CryptoAgentMail
— v0.4.0
Hosted email MCP for AI agents with inboxes, send/receive, memory, recovery, and credits.
-
io.github.infoinlet-marketplace/mcp-memory
— v0.1.1
Persistent searchable memory for AI agents — save/get/search across sessions, tags.
-
Inite Brain
— v0.1.0
Open-source bitemporal memory layer for LLM agents — knowledge graph with conflict resolution.
-
io.github.Intina47/context-sync
— v1.0.1
Universal AI Memory - Sync context across Claude, VsCode, Cursor, Continue, Windsurf, Zed & more
-
Persome
— v0.3.2
Local-first personal memory and model server for trusted MCP agents on macOS.
-
io.github.ionasrobert/tacitus-mcp-server
— v0.1.1
Long-term memory for AI agents: local-first PKM with provenance and hybrid search.
-
Postgram
— v0.1.3
Self-hosted memory for AI agents with hybrid search, knowledge graphs, tasks, and document sync.
-
codebase-synapse
— v0.1.13
Indexes codebase into a local knowledge graph with 40+ AI tools and codebase-guard.
-
Memory MCP Server
— v1.7.0
SQLite-backed MCP server for persistent memory, full-text retrieval, and graph traversal.
-
memo
— v4.9.3
Memory for AI agents — MLX (Apple Silicon) or CPU (Linux), sqlite-vec + BM25, zero cloud.
-
io.github.jamjet-labs/engram-server
— v0.5.0
Durable memory for AI agents: fact extraction, hybrid retrieval, temporal graph. SQLite/Postgres.
-
Cambium
— v0.2.0
Knowledge-lifecycle MCP: turn agent work into memory, recall it across projects, promote to org.
-
cambium (remote)
— v0.2.0
Cloudflare Worker for read-only recall of cambium knowledge. MCP 2026-07-28, dual-era.
-
io.github.jarmstrong158/context-keeper
— v0.19.0
Durable project-memory MCP: decisions, constraints, and pipelines across Claude sessions.
-
Cairn
— v0.21.2
Persistent memory for AI agents and humans. Store, search, and discover patterns.
-
io.github.jdhart81/agent-provenance
— v0.2.0
Genesis certificates, lineage, and cascading recalls: birth certificates + bloodlines for the agent
-
Heartwood Memory
— v0.2.1
Governed agent recall with signed provenance and policy gates. BUSL-1.1; not OSI open source.
-
io.github.jerrysrodz/goldhold
— v1.5.1
Persistent memory for AI agents. Search, store, and recall across sessions.
-
Booboo
— v0.5.0
Query your AI system's wiring, knowledge, memory, agents and crons as one rooted graph over MCP.
-
Booboo
— v0.5.2
Query your AI system's wiring, knowledge, memory, agents and crons as one rooted graph over MCP.
-
io.github.JesusGarcia9009/lethe
— v0.6.2
Context GC for LLM agents: offload large tool outputs and recall them to save tokens.
-
0Latency Memory
— v1.0.0
Persistent memory layer for AI agents. Sub-100ms recall, semantic search, knowledge graphs.
-
io.github.jghiringhelli/codeseeker
— v2.0.1
Graph-powered code intelligence with semantic search and knowledge graph for AI assistants
-
Kindex
— v0.27.1
Persistent knowledge graph and MCP server for AI workflows with git-tracked project context.
-
io.github.jmeyer1980/neurodivergent-memory
— v0.1.8
Persistent knowledge graph MCP server for neurodivergent thinking. BM25 search, no cloud LLM.
-
TokenKnows
— v0.3.0
Distill AI coding sessions into weekly reports, ADRs and a knowledge graph - self-hosted
-
io.github.jordanhindo/lore
— v0.1.1
Lightweight MCP for infinite agent memory. Any agent, any session, anytime.
-
io.github.JubaKitiashvili/context-mem
— v3.2.1
Persistent memory for AI agents — 98%+ retrieval recall, 99% token savings, 44 tools
-
io.github.juliangeymonat-jpg/wikimoth
— v0.2.1
Deterministic, token-minimal agent memory: multi-hop [[wikilink]] recall with no LLM in the loop.
-
Junê
— v0.1.3
Shared, cited knowledge-graph memory for agents — ask, search, and remember against a June endpoint
-
BrainstormRouter MCP Server
— v1.0.0
AI routing, memory, guardrails, and governance. Routes across Claude, GPT, Gemini.
-
io.github.jyswee/agenticmemory
— v1.8.0
Persistent memory for AI agents — history, context, semantic search, queues. 17 tools, stdio/SSE.
-
io.github.jyswee/ainpc-cli
— v1.5.3
AI NPCs with persistent memory for game studios. NPC CRUD, dialogue, voice. Stdio or remote SSE.
-
io.github.kaaustubh/project-memory-mcp
— v1.6.0
Persistent memory for AI coding agents — past bugs, decisions, and your corrections, in your repo.
-
io.github.kael-bit/engram
— v0.10.0
Hierarchical memory for AI agents. Three-layer (buffer/working/core) with decay and promotion.
-
io.github.KairosMobius/memory-nexus-mcp
— v1.0.0
Persistent semantic memory for AI agents with knowledge graphs and Intelligence Packs.
-
io.github.KairosMobius/nexus-memory-mcp
— v1.0.2
Persistent semantic memory for AI agents with knowledge graphs and Intelligence Packs.
-
io.github.keshrath/agent-knowledge
— v1.9.7
Cross-session memory for AI agents - knowledge graph, scoring, semantic search
-
io.github.KhiipAI/khiip
— v0.2.4
Capture the web, keep your copy as plain Markdown, and recall it by meaning. Local-first daemon.
-
memex
— v0.6.0
Local MCP memory for coding agents. SQLite on your machine — preferences persist across chats.
-
io.github.kira-autonoma/agent-memory-mcp
— v0.1.3
Agent memory MCP server with provenance tracking, decay-weighted recall, and feedback loops.
-
Handoff
— v0.4.0
Cross-session memory for Claude over MCP — prioritised briefs, supersession, cross-project recall.
-
io.github.krimto-labs/krimto
— v0.2.47
Memory for AI coding agents — markdown in your own git, not a vendor database. Apache-2.0.
-
Mini Data Engine Runtime Copilot
— v0.1.12
MCP runtime copilot for health checks, regressions, explainability, and operational memory.
-
io.github.KSym04/limpet
— v0.14.0
Persistent engineering memory for AI coding agents. Survives refactors, knows when it is stale.
-
io.github.kunwar-shah/claudex
— v1.3.4
Persistent memory + FTS5 search MCP server for Claude Code conversation history.
-
io.github.kurovu146/memory-fts
— v1.0.1
Long-term memory for Claude Code with SQLite FTS5 search and BM25 ranking
-
Acta — Verifiable Agent Memory
— v1.0.0-rc.1
Verifiable agent memory with signed ledger receipts — verify every write offline.
-
io.github.l-agence/agence
— v1.0.0
AI governance MCP server — policy enforcement, skills, memory, multi-LLM consensus
-
io.github.l33tdawg/sage
— v11.17.15
Persistent, consensus-validated institutional memory for AI agents. Runs locally.
-
Banyan Memory
— v1.5.1
Persistent, governed local memory for MCP-compatible AI clients.
-
Copilot Memory MCP
— v1.0.0
Persistent semantic memory for AI agents using local ChromaDB vector search. No cloud required.
-
io.github.las7/memharness
— v0.1.2
Bi-temporal, provenance-carrying long-term memory for AI agents, in one SQLite file.
-
io.github.lazymac2x/agent-memory
— v1.0.0
Cloudflare Workers MCP server: agent-memory
-
io.github.ldclabs/KIP
— v1.0.1
Knowledge Graphs to enable memory persistence, knowledge evolution, explainable interaction.
-
io.github.LeandroPG19/cuba-memorys
— v0.21.0
Persistent memory MCP server. 29 tools, BM25+MMR+OOD retrieval, tamper-evident audit, code graph.
-
io.github.learningloons-hash/lithtrix
— v0.20.1
Search, browse, memory and blob storage for AI agents. One key at lithtrix.ai, Spark trial free.
Page 7 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.