Mnemostack MCP Server
Self-hosted hybrid agent memory on Qdrant combining vector search, BM25, temporal retrieval and an optional Memgraph knowledge graph via rank fusion.
9Python
context tax
queued
security
queued
cold start
queued
freshness
Active11d ago
Install Mnemostack MCP server
No published package or hosted endpoint yet — see the repository README for build-from-source instructions.
Freshness
Active — last maintenance signal 11d ago. The newest of the signals below sets the band.
Last commit (default branch)
2026-09-28 · 11d ago · GitHub
Latest release
2026-09-28 · 11d ago · GitHub · v2.6.2
Package published
no data · npm/PyPI
Registry entry updated
no data · official registry
FAQ
›Is Mnemostack in the official MCP registry?
No. It was indexed from awesome-mcp-servers (punkpeye).
Alternatives to Mnemostack
Other notes & knowledge MCP servers.
MemoryActiveKnowledge graph-based persistent memory for maintaining context.
Context7ActiveUp-to-date code documentation for LLMs and AI code editors.
HindsightActiveHindsight: long-term memory for AI agents modeled on human memory.
Codebase MemoryActiveIndexes a repo into a persistent local knowledge graph of functions, classes, call chains, HTTP routes and cross-service links, using tree-sitter and LSP.
CogneeActiveMemory manager for AI apps and agents using graph and vector stores, with ingestion from many data sources.
DocsActiveProvides AI assistants with direct access to Mastra.ai's complete knowledge base.