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.
-
Synapse Layer — Trust Infrastructure for AI Agents
— v2.4.4
MCP-native Trust Infrastructure for AI Agents. Persistent encrypted memory with Trust Quotient.
-
Synapse Layer — Zero-Knowledge Memory
— v1.0.7
Zero-Knowledge Context™ & Neural Handover™ for AI Agents. The Trust Layer for AI Memory.
-
io.github.syndicalt/zaxy
— v3.2.0
Event-sourced, auditable agent memory over MCP: cited checkout, replayable provenance.
-
OpenAkashic
— v1.0.0
Shared long-term memory vault for AI agents with 20 MCP tools.
-
Kirok Memory
— v1.4.2
Persistent memory for AI agents - hybrid semantic + keyword recall with autonomous consolidation
-
OpenFDA Safety Data
— v1.1.0
Search FDA safety data: drug adverse events, recalls, and device events.
-
Mimir — Persistent Memory Engine
— v2.0.0
Persistent memory for AI agents. 36+ MCP tools: encryption, decay, hybrid search, knowledge graph.
-
Perseus — Live Context Engine for AI Agents
— v1.0.9
Live context engine for AI agents. 27+ MCP tools: health, memory, skills, file trees on demand.
-
DataGraph
— v1.7.2
Urban intelligence knowledge graph. Structured locality data for civic problem-solving.
-
Monet
— v1.2.4
Local-first, state-centric memory for coding agents. MCP server + CLI.
-
io.github.teampolarity/cosmos-mcp
— v0.7.1
Personal knowledge graph every MCP client reads from and writes to. Portable across agents.
-
io.github.teflon07/memkeeper
— v0.5.3
Local-first memory for AI agents: on-device hybrid retrieval over a single SQLite file.
-
io.github.TeleAI-UAGI/telemem
— v1.8.0
Long-term and multimodal memory for AI agents - character-aware, mem0-compatible, fully-local option
-
MIND
— v0.5.4
Personal knowledge graph AI memory. 15 tools, 89 actions. Emotional intelligence, CRM, social.
-
io.github.thebasedcapital/brainbox
— v0.1.6
Hebbian memory for AI agents. Learns file patterns, predicts next tools, saves tokens.
-
mneme
— v3.5.0
Vault-native, accountable memory for Claude Code and MCP clients. Markdown is ground truth.
-
io.github.thegoodguysla/myco-brain
— v1.2.8
Self-hosted, source-traceable memory layer and MCP server for AI agents, on your own Postgres.
-
io.github.thelabvenice/memdata
— v1.4.1
Persistent memory for AI agents. Store context, retrieve it semantically.
-
agentmem
— v0.2.5
Governed memory for coding agents. Trust lifecycle, conflict detection, health scoring.
-
io.github.thomasjumper/agentbay-mcp
— v0.2.0
Persistent memory and knowledge management for AI agents with semantic search and 50+ tools.
-
StremAI
— v1.2.5
StremAI MCP: shared memory for AI coding agents. Connected agents can recall. OAuth + local stdio.
-
io.github.threadctx-dev/threadctx-mcp
— v0.5.0
Shared memory MCP server for AI coding agents — local by default, team-shared via threadctx.dev.
-
ContextBridge
— v1.0.2
MCP memory server for AI coding assistants. Windows Service, ONNX embeddings, SQLite vector search.
-
io.github.thuupx/memory-mcp-lite
— v2.0.0
A lightweight, structured, token-efficient local-first MCP memory server
-
Telys — on-device memory
— v0.1.1
Private on-device memory & retrieval for AI assistants — offline vector + lexical search.
-
io.github.TinySuiteHQ/tinycontext
— v0.2.1
Token-light local memory with SQLite hybrid retrieval for MCP agents.
-
NeuroDock Cognitive Graph
— v0.0.6
A local typed-edge graph of people, projects, and decisions that externalises memory.
-
io.github.tm42/mnemograph
— v0.5.1
Event-sourced knowledge graph memory for AI coding agents with semantic search
-
io.github.tobs-code/cozo-memory
— v1.0.3
Local-first memory system for AI agents with hybrid search and graph reasoning
-
Toolbelt
— v1.0.14
A collaborative substrate over your data: vector, knowledge graph, SQL, geospatial, streaming.
-
Mirror Memory MCP Server
— v1.0.0
Personal knowledge base MCP server with semantic search, auto-categorization, metadata extraction
-
Tribal
— v0.4.1
Self-hosted semantic memory over MCP for an engineering team's tacit knowledge. Needs Postgres.
-
io.github.tstockham96/engram
— v0.5.1
Intelligent agent memory with automatic extraction, consolidation, and bi-temporal recall.
-
io.github.turbyho/mem-context
— v0.1.4
Temporal memory MCP server with LanceDB vector search, weight-decay scoring, and LLM consolidation
-
Tycana
— v1.0.0
Gives your AI assistant persistent memory and intelligence about your work patterns.
-
io.github.umitkavala/mindpm
— v1.2.41
Persistent project memory for LLMs via SQLite. Never re-explain your project again.
-
unerr
— v0.2.1
Operational memory for AI agents: code graph, session memory & guardrails. No context rot.
-
io.github.Unima3x/agirails-mcp-server
— v0.1.7
Payment rails for AI agents — escrow, settlement, discovery, and disputes from any context window.
-
mail-index
— v1.5.1
Local-first, read-only MCP server for recall over your Gmail: search, contacts, threads, digests.
-
io.github.uuaid/mcp
— v0.1.1
Permanent identity + encrypted, quantum-ready memory that outlives the session, for any AI agent.
-
io.github.var-gg/pindoc
— v0.2.0
Code-pinned team memory for AI coding agents — typed artifacts, MCP-native, self-host.
-
io.github.varun29ankuS/shodh-memory
— v0.2.0
Cognitive memory for AI agents — semantic search, Hebbian learning, knowledge graphs.
-
io.github.varun369/superlocalmemory
— v2.7.5
Local-first AI memory with knowledge graphs and hybrid search. 17+ AI tools via MCP. Free.
-
io.github.vectros-ai/mcp-server
— v0.12.0
Typed record store + hybrid search over MCP: deterministic lookups + semantic memory, per-customer.
-
io.github.VelixarAi/memory
— v0.2.4
Persistent memory for AI assistants. Store, search, and recall across sessions.
-
io.github.veracium-ai/veracium
— v0.4.3
Provenance-aware memory for AI agents: quarantine, abstention gate, supersession-with-history.
-
io.github.verbative/verbative-memory
— v1.0.1
On-device, self-organizing memory for AI coding agents — recalls the right facts into each prompt.
-
VerifiedState Memory
— v1.1.0
Verified memory for AI agents. Signed assertions, billing attestation, session continuity.
-
MCP AutoMem
— v0.10.0
Graph-vector memory for AI assistants using FalkorDB and Qdrant
-
Context Fabric
— v1.2.2
Context sync layer for AI agents. Ensures continuity and eliminates memory drift automatically.
-
io.github.VineetV2/peon-mem
— v1.0.2
Local-first memory brain for AI coding agents: hooks capture sessions, beliefs injected per prompt.
-
io.github.VirajMishra1/wander-agent
— v0.1.1
60-tool AI travel agent: flights, hotels, visas, weather, fare watching, trip memory. No keys.
-
Subconscious
— v0.2.0
Local-first semantic memory for MCP agents. Recall, remember, forget, echo, drift, stats over stdio.
-
io.github.vola-trebla/flakiness-knowledge-graph-mcp
— v0.2.2
MCP server + Playwright reporter that builds a flakiness knowledge graph from test run history
-
io.github.volsier/memforge-memory
— v1.0.1
Team engineering memory for AI coding assistants. 47 MCP tools, pgvector semantic search.
-
io.github.VonderVuflya/yggdrasil
— v0.15.0
One shared, durable memory for your AI coding agents — local-first, zero-dependency.
-
Midas
— v0.0.1
Local-first, source-traceable agent memory — no LLM at ingest, fully offline
-
emem, the verifiable memory protocol for the physical world
— v2.0.0
Shared, verifiable memory for AI agents and robots: signed tokens that resolve and verify offline.
-
io.github.vshulcz/deja-vu
— v0.16.7
Local searchable memory over your coding-agent session histories, served back via MCP recall.
-
Ghostdom
— v1.0.0
Headless-browser-as-JSON with memorymarket cache economics. Real Chromium, crypto settlement.
Page 12 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.