Library
85,766 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
audrey
MCP serversLocal-first biological memory for coding agents: recall, consolidation, and pre-action Guard checks.
audrey@2.1.1 -
Hebbian Mind
MCP serversAssociative memory via Hebbian learning. Connections strengthen through use, decay through disuse.
hebbian-mind-enterprise@2.3.2 -
gctrl
MCP serversGoverned graph-native agent memory: knowledge extraction, fusion, hybrid RAG, scoped access tokens.
gctrl-mcp@1.2.0 -
haki
MCP serversLong-term memory for AI agents: bitemporal fact ledger, contradiction detection, explainability.
-
context-oversharing-auditor
MCP serversOWASP MCP10 context oversharing: session dumps, unscoped memory, shared context, prompt leaks
@guardbee/mcp-context-oversharing-auditor@0.4.1 -
engram
MCP serversLocal-first persistent memory for AI agents — SQLite + local embeddings, MCP-native, no cloud.
@hbarefoot/engram@1.6.3 -
context-sync
MCP serversUniversal AI Memory - Sync context across Claude, VsCode, Cursor, Continue, Windsurf, Zed & more
@context-sync/server@1.0.1 -
Persome
MCP serversLocal-first personal memory and model server for trusted MCP agents on macOS.
personal-model@0.3.2 -
PyMemoryEditor
MCP serversRead, write and scan process memory, Cheat Engine style, on Windows, Linux and macOS.
pymemoryeditor@3.4.3 -
context-mem
MCP serversPersistent memory for AI agents — 98%+ retrieval recall, 99% token savings, 44 tools
context-mem@3.2.1 -
limpet
MCP serversPersistent engineering memory for AI coding agents. Survives refactors, knows when it is stale.
-
Lore Context
MCP serversGoverned AI-agent memory, Evidence Ledger traces, evals, and portable context tools.
@lore-context/server@0.6.0-alpha.1 -
token-savior
MCP serversStructural codebase MCP server with persistent memory: navigate by symbol, recall across sessions.
token-savior-recall@4.13.0 -
engram-cc
MCP serversUniversal AI coding assistant memory — session handoff, SLM compression, and semantic retrieval.
@morous-dev/engram-cc@0.1.4 -
genome
MCP serversFully local memory for AI agents: zero-LLM ingest, semantic recall, air-gapped, auditable.
genome-memory@1.3.2 -
locus
MCP serversHierarchical markdown memory palace for AI agents — structured palace navigation via MCP tools.
locus-mcp@0.9.0 -
alaya-mcp
MCP serversLocal memory engine for AI agents with knowledge graphs, forgetting, and semantic recall
alaya-mcp@0.4.7 -
Thronglets
MCP serversP2P shared memory substrate for AI agents — stigmergic knowledge network via libp2p
https://github.com/Shangri-la-0428/Thronglets/releases/download/v0.2.0/thronglets-mcp-darwin-arm64@0.2.0 -
Obsidian Turbocharged
MCP serversGoverned Obsidian vault access: hybrid retrieval, Markdown-native memory, HITL confirmations.
obsidian-tc@1.34.0 -
mneme
MCP serversVault-native, accountable memory for Claude Code and MCP clients. Markdown is ground truth.
mneme-mcp-server@3.5.0 -
ContextBridge
MCP serversMCP memory server for AI coding assistants. Windows Service, ONNX embeddings, SQLite vector search.
ThunderEagle.ContextBridge@1.0.2 -
Context Fabric
MCP serversContext sync layer for AI agents. Ensures continuity and eliminates memory drift automatically.
context-fabric@1.2.2 -
PatchX Freenote Agent
MCP serversPatchX Freenote MCP: summaries, memories, model results and user-approved webhook workflows.
patchxnote-agent@0.2.15 -
myc
MCP serversTask queue, decisions and memory for coding agents. Local SQLite, no network. Requires Bun.
@aistastudio/myc@0.3.13
Indexed entries aren't reviewed or tested by InnerVault. Details come straight from each source. Anything that can reach your accounts, files or browser can do damage, so read the source before you install it.