Agent Memory MCP

io.github.ipitonPublished by GitHub account ipitonv0.16.0Updated Nov 5, 2026

Memory, docs, and repo context layer for engineering agents.

The publisher's own server: Memory.fit

VerifiedSTDIODesktop onlyKnowledge & MemoryDeveloper Tools

Overview

AI-generated overview

Local SQLite-backed MCP server giving coding agents long-term memory and project-docs search, with drift checks and a review workflow.

What you can do
  • Search memory and docs together: decisions, facts and procedures ranked alongside docs, ADRs and runbooks, with a trust signal on each hit
  • Keep memory clean: find duplicates, contradictions and stale entries and route risky ones to a review inbox
  • Detect drift: flag memories whose source file changed or disappeared
  • Promote notes to canonical status, with the final say left to the user
When to use it
For engineering agents that should recall why past decisions were made, find the runbook matching an incident, and notice when stored knowledge no longer matches the repository. Suited to per-project local use in coding assistants such as Claude Code, Codex, Cursor or similar.
Requirements
Runs as a local process on the user's machine (desktop only). The Claude Code plugin path needs no service or model; the standalone server needs one embedding provider. Installed via a plugin marketplace or Homebrew, then set up per repository and the agent restarted. Data is stored in one local SQLite database per project; an HTTP mode exists for a shared team instance.
Before you install
Memory content is stored locally in SQLite and, in HTTP team mode, shared with others. Agents cannot verify their own notes, so canonical memory should only be set through the explicit promotion step. Review what the steward sends to the review inbox before accepting it.

Installation

In SourceWeft

  1. Open Agent Memory MCP in the dashboard and add it to a workspace.
  2. 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

agent-memory-mcp

[Agent Memory MCP on mcprush]

Long-term memory and project-docs search for coding agents, in one local MCP server backed by SQLite.

Your agent remembers why a decision was made, finds the runbook that matches an incident, and notices when what it remembers no longer matches the repo.

Install

Claude Code. Nothing else to set up: no service, no model, one local database per project. Details.

text
/plugin install agent-memory --marketplace ipiton/agent-memory-mcp

Codex, Cursor, Gemini CLI, OpenCode, VS Code, Windsurf, or Claude Code without the plugin. A standalone server, which needs one embedding provider. Details, including builds without Homebrew.

bash
brew tap ipiton/tapbrew install agent-memory-mcpcd your-repoagent-memory-mcp setup codex --yes

Restart the agent afterwards.

What it does

  • Searches memory and docs together. Decisions, facts and procedures are ranked alongside your docs, ADRs and runbooks, and every hit says how far to trust it.
  • Keeps memory clean. steward_run finds duplicates, contradictions and stale entries, and sends anything risky to a review inbox.
  • Notices drift. drift_scan flags memories whose source file changed or disappeared.
  • Leaves the last word to you. Notes become canonical only through promote_to_canonical. An agent cannot verify its own notes.
  • Stays local. One binary and SQLite. An HTTP mode is there for a shared team instance.
text
> How many replicas should payments-api run, and why?
1. **Why payments-api runs 4 replicas** (relevance: 0.79)   Trust: layer=raw source=decision confidence=0.96 freshness=1.00 owner=engineering   Content: Decision 2026-09-12: payments-api runs 4 replicas, not 2. Two replicas dropped   requests during the September card-network spike. Source: ./deploy/values.yaml.

More in Features.

Documentation

TopicWhere
Claude Code pluginPLUGIN.md
Standalone install, connecting agents, team serviceINSTALLATION.md
Tools and CLIMCP_TOOLS.md, CLI.md
ConfigurationCONFIGURATION.md
Stewardship and memory lifecycleSTEWARDSHIP.md
Architecture and securityARCHITECTURE.md, SECURITY.md
Troubleshooting and changesTROUBLESHOOTING.md, CHANGELOG.md

Development

bash
make buildmake testmake vet

Conventions are in CONTRIBUTING.md. License: MIT.

Source: README.md at commit 5e418ee

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

5
  1. v0.16.0LatestNov 5, 2026
  2. v0.15.1Nov 3, 2026
  3. v0.14.0Nov 1, 2026
  4. v0.13.4Sep 25, 2026
  5. v0.13.3Sep 16, 2026

Score

50% 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
  • License10 pts

Other Memory integrations