Memwright

Embedded memory for AI agents with SQLite, pgvector, and Neo4j graph search.

Connector by bolnet · GitHub account verified by the MCP Registry

IndexedMITLocal (stdio)★ 14

Install

Works with Claude Code, Codex, VS Code, Cursor, Windsurf, Claude Desktop. Read the repository before you give any tool access to your data.

npx agentmarket install connector/bolnet-memwright

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

About

Embedded memory for AI agents with SQLite, pgvector, and Neo4j graph search.

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this server can do and what it asks for, from its tool list and install config. Checked Oct 25, 2026.

Tools: 6 read · 2 write · 0 delete
Secrets: 3 (API keys, tokens or passwords)
Install scripts: Not scanned yet
Runs as: Python package

Tools by what they do 8

Read from the source code; the running server may list different tools.

Read 6 · Look things up without changing anything.

memory_get
memory_health
memory_recall
memory_search
memory_stats
memory_timeline

Write 2 · Create, change, send or run things.

memory_add
memory_forget

Secrets and settings it asks for

Secrets: values you paste in that let it act as you.

NEO4J_PASSWORD
OPENAI_API_KEY
OPENROUTER_API_KEY

Other settings (environment variables or headers).

PG_CONNECTION_STRING

Tools (8)

Read from the source code; the running server may differ. Descriptions are the server’s own words; hidden characters are shown as [U+…].

memory_add
Store a new memory/fact about the user or project. Use this to remember preferences, decisions, context, and important facts.
memory_forget
Archive a specific memory by ID.
memory_get
Retrieve a single memory by its ID.
memory_health
Check health of all memory system components. Reports status of the document store, vector store, graph store, and retrieval pipeline. Call this first to verify the system is working.
memory_recall
Smart retrieval: finds the most relevant memories using multi-layer search (tags, graph connections, and semantic vectors) with score fusion. Use this as the primary way to find relevant context.
memory_search
Simple keyword search with filters. Use this when you need to filter by category, entity, status, or date range. For general relevance queries, prefer memory_recall instead.
memory_stats
Get statistics about the memory store.
memory_timeline
Get the chronological history of memories about an entity.

Signals

Stars: 14
Forks: 1
Open issues: 0
Weekly downloads: 28
Last commit: Sep 18, 2026 (1 month ago)
Last release: May 26, 2026 (5 months ago)
Last package publish: Apr 14, 2026 (6 months ago)

From GitHub (fetched Oct 24, 2026) and the package registry.

Details

Registry name: io.github.bolnet/memwright
Version: 0.1.3
Auth: API key
Packages: pypi memwright
License: MIT
Repository: github.com/bolnet/agent-memory
First seen: Oct 24, 2026
Last checked: Oct 25, 2026
Source: Official MCP Registry github-graphql