Memwright
Embedded memory for AI agents with SQLite, pgvector semantic search, and Neo4j graph traversal fused via Reciprocal Rank Fusion.
Provides persistent memory for AI agents using a three-layer retrieval system combining SQLite storage, pgvector semantic search, and Neo4j entity graph traversal. Results are ranked using Reciprocal Rank Fusion for token-efficient recall at 300-500 tokens per query. Supports contradiction detection, entity timeline tracking, and runs fully locally via Docker with integrations for Claude Code, Cursor, and direct Python library usage.
Source
Repository: https://github.com/bolnet/attestor
Maintain Memwright?
Let people know it's listed here — add the badge (live metrics, light/dark aware) or a plain link to your README or docs.
[](https://getagentictools.com/mcp/bolnet-attestor?ref=badge) Related mcp
French Tax Integrates with official French tax websites (impots.gouv.fr, service-public.fr, legifrance.gouv.fr) to provide tax calculations,
EDINET Financial Disclosures Access Japanese financial disclosures from EDINET with company search and statement retrieval.
Kibela Integrates with Kibela knowledge bases to enable searching, reading, creating, and updating notes directly within conversation int
OpenGov Socrata Enables access to public government datasets from Socrata-powered portals through a unified tool for searching, querying, and anal
M3 Memory Persistent memory layer for AI agents with hybrid search, contradiction detection, and knowledge graphs.
Wikipedia Provides a structured interface for searching and retrieving Wikipedia articles in clean Markdown format, enabling access to up-to