Memory for AI
io.github.LonelyTraderBayPublished by GitHub account LonelyTraderBayv0.11.0Updated Oct 24, 2026
Local codebase knowledge graph for AI agents — 162 languages, sub-ms queries, 99% fewer tokens.
The publisher's own server: Memory.fit
Overview
Builds a local knowledge graph of a codebase so an AI coding agent can answer structural questions with graph queries instead of reading files.
- What you can do
- Indexes a repository into a persistent SQLite graph of nodes such as functions, classes, routes and packages, and edges such as calls, imports, implements and HTTP links. It exposes 23 MCP tools, including index_repository, trace_path for callers and callees, get_architecture, detect_changes, query_graph with a read-only Cypher subset, and manage_adr for architecture decisions. A background watcher re-indexes on Git or filesystem changes, and every tool also runs as a one-shot CLI command.
- When to use it
- Useful when an agent repeatedly explores a large or unfamiliar repository and you want structural answers such as callers, blast radius, dead code, routes or architecture without reading file after file. Also useful for keeping architecture decisions and an index across sessions.
- Requirements
- Runs as a local stdio process on the user's machine; no API key, account or telemetry is declared. The README states it is native Windows x64 only, with about 2 GB free disk, PowerShell and git on PATH; ARM64, emulation, Linux, macOS and WSL are described as unsupported. Installable via npm, PyPI or platform packages, or a PowerShell installer.
Installation
In SourceWeft
- Open Memory for AI in the dashboard and add it to a workspace.
- Enable the server for the chats that should use its tools.
Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.
Other MCP clients
Follow the launch instructions in the repository.
README
This repository has no README.
Tools
0Version history
2- v0.11.0LatestSep 18, 2026
- v0.10.9Sep 16, 2026
Score
25% of the applicable checks met
How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.
- Reached in the last 30 days25 pts
Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.
- Auth declared10 pts
Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.
- Tools listed15 pts
Answer tools/list without a credential, or ship a package that starts in a sandbox without one.
- DescriptionRequired15 pts
- Logo10 pts
- Documentation15 pts
Declare a GitHub repository with a README, or serve resource_documentation in the OAuth protected-resource metadata.
- License10 pts
Declare a license in the repository or the registry entry.
Other Memory integrations
Memory.fit
fit.memoryOfficial publisher
Hosted Memory.fit server that lets an AI read your training, sleep, recovery and nutrition data and write back weekly plans, targets and meal plans.
pg.ddx.io: the PostgreSQL community's memory
io.ddx.pgOfficial publisher
pg.ddx.io: the PostgreSQL community's memory's hosted MCP server, published by pg.ddx.io; no sign-in required; Streamable HTTP; 29 tools.
var.gg Naming Memory
gg.varOfficial publisher
Remote MCP server that suggests and searches code identifier names from domain concepts in Korean, Japanese, Chinese, Vietnamese and English, and exposes ERD…
Counterparts
ai.counterparts
Local-first long-term memory for Claude Code and Claude Desktop: the assistant writes notes about you and your projects and recalls them in later sessions.
LAHZE - Persian AI Memory Platform
Published by GitHub account pedramgholizadeh
LAHZE - Persian AI Memory Platform's hosted MCP server; no sign-in required; Streamable HTTP; 13 tools.