AI Agent Memory

io.github.xiangzi1126Published by GitHub account xiangzi1126v0.1.1Updated Oct 27, 2026

Agent-agnostic persistent memory MCP server. Local-first: memories travel with your project.

The publisher's own server: Memory.fit

VerifiedSTDIODesktop onlyKnowledge & MemoryDeveloper Tools

Overview

AI-generated overview

Local-first persistent memory MCP server that stores project memories in a .aamm folder and shares them across agents such as Claude Code, Cursor and Qoder.

What you can do
  • Store, recall, read, filter, update, list and delete memories across user, project, process and agent categories, with fused vector, keyword and title/tag retrieval.
  • Log work journal entries and search past journal timelines as a fallback.
  • Set the user name shown in journals and check the current agent and project context.
  • Manage the store from a CLI: initialize, show status, export to Markdown, rebuild indexes from Markdown and run consistency checks.
When to use it
Useful when you want an assistant to remember preferences, project knowledge and debugging lessons across sessions, and to share one memory store between several MCP clients working on the same project. Suited to local, per-project memory rather than a hosted memory service.
Requirements
Runs as a local Python process; install the ai-agent-memory-mcp package from PyPI and use Python 3.11 or newer. An OpenAI-compatible embedding service is required, configured in .aamm/config.yml with model, base_url, api_key_env and dim; the API key is read from an environment variable named in that config, for example VOLCENGINE_API_KEY, SILICONFLOW_API_KEY or OPENAI_API_KEY, placed in the project .env. Network access to the embedding endpoint is needed.
Before you install
Memories and journal entries are written to the project's .aamm folder, including a Markdown mirror and per-day journal files, so anything stored there may be committed or shared with the project. Memory content, titles and tags are sent to the configured third-party embedding provider, which may incur usage costs. The tools can update and delete stored memories, and the journal records what was asked and done. Changing the embedding model can invalidate existing vectors.

Installation

In SourceWeft

  1. Open AI Agent Memory 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

AI Memory MCP Server

Agent-agnostic persistent memory as an MCP Server — local-first: memories travel with your project in .aamm/, shared across Claude Code / Qoder / Cursor.

[License: MIT] [Python 3.11+] [MCP] [PyPI]

中文 | 日本語

An agent-agnostic persistent memory layer exposed as an MCP Server. Any MCP client — Claude Code, Qoder, Cursor — can reuse it. Memories live in each project's .aamm/ directory and travel with the project; different agents working the same project share one memory store, with a source_agent stamp distinguishing writers.

Architecture

  • SQLite — structured source of truth (CRUD + FTS5 keyword search)
  • Chroma (embedded) — vector retrieval, persisted to .aamm/chroma/
  • Embedding — any OpenAI-compatible service (Volcengine / SiliconFlow / OpenAI / others); defaults to Volcengine doubao-embedding-vision
  • Markdown mirror — each memory is also written to .aamm/memories/<category>/<id>.md, human-readable and editable

The three layers are joined by id.

Memory categories

categoryuse
useruser preferences (tech background / dev habits / answer style)
projectproject knowledge (architecture / stack / layout / design decisions)
processwork process (solved issues / bugs / debugging / lessons)
agentagent collaboration (what was done / handoff notes)

Install

From PyPI:

powershell
pip install ai-agent-memory-mcp

From source:

powershell
cd ai_agent_memory_mcppip install .          # or: pip install -e .   (editable, for development)

Requires Python 3.11+.

Configure embedding (any OpenAI-compatible service)

The embedding layer is a generic OpenAI-compatible client — Volcengine / SiliconFlow / OpenAI / any compatible service works. On first run a default config is generated at .aamm/config.yml; edit as needed.

Fields (embedding section of .aamm/config.yml)

fieldmeaning
providerlabel (informational only)
modelembedding model name
base_urlOpenAI-compatible endpoint
api_key_envwhich env var holds the key
dimvector dim (must match the model)

Put the key in the project root .env, then edit the embedding section of config.yml.

Examples

Volcengine doubao-embedding-vision (default; Agent/Coding Plan keys must use the Plan endpoint /api/plan/v3 — standard /api/v3 returns 401)

yaml
embedding:  provider: volcengine  model: doubao-embedding-vision  base_url: https://ark.cn-beijing.volces.com/api/plan/v3  api_key_env: VOLCENGINE_API_KEY  dim: 2048

.env: VOLCENGINE_API_KEY=...

SiliconFlow bge-large-zh (Chinese-text optimized)

yaml
embedding:  provider: siliconflow  model: BAAI/bge-large-zh-v1.5  base_url: https://api.siliconflow.cn/v1  api_key_env: SILICONFLOW_API_KEY  dim: 1024

.env: SILICONFLOW_API_KEY=...

OpenAI

yaml
embedding:  provider: openai  model: text-embedding-3-small  base_url: https://api.openai.com/v1  api_key_env: OPENAI_API_KEY  dim: 1536

.env: OPENAI_API_KEY=...

Any other OpenAI-compatible service: just fill in base_url / model / api_key_env / dim.

After switching embedding model, old vectors may mismatch in dimension; clear .aamm/chroma/ and re-remember, or run python tests/rebuild_vectors.py.

Retrieval

recall uses three-way fused retrieval to maximize hit rate:

  • Vector (weight 0.6): Chroma cosine; embeddings are computed from title + tags + content, so title/tag signal enters the vector
  • Keyword (weight 0.25): SQLite FTS5 trigram
  • Title/tag match (weight 0.15): +0.15 if the query appears in the title, +0.075 if in a tag

Candidates are expanded to top_k*3, then fused down to top_k. If the query contains FTS5 special characters (., *, ", -, ...), the keyword branch falls back to LIKE substring matching instead of erroring.

Work journal

Besides searchable memories, aamm keeps a human-readable work journal. After completing a user request, the agent calls journal_entry() to log what was asked / what it did / any open question. Journals are for people reading a timeline; recall does not search them. Use search_journal() only as a fallback to recover "what happened in a past interaction".

Journals are written to .aamm/logs/:

  • journal.db — single SQLite store (the search source, spans all dates)
  • YYYY-MM-DD.md — one Markdown file per day, append-only timeline
.aamm/logs/├── journal.db        # search source (all dates)├── 2026-07-14.md     # per-day timeline└── 2026-07-15.md

MCP tools

Memory (8):

  • remember(title, content, category, tags?, scope?) — store (three-way sync, auto-embed)
  • recall(query, category?, top_k=5) — fused retrieval (vector + keyword + title match)
  • get_memory(id) — get one
  • search_memories(category?, tag?, agent?) — structured filter
  • update_memory(id, ...) — update (re-embed + refresh md)
  • forget(id) — delete (three-way sync)
  • list_memories(category?) — list
  • who_am_i() — current agent + project context

Journal (3):

  • journal_entry(question, answer_summary, key_points?, open_question?, session_id?) — log a timeline entry
  • search_journal(query, date_from?, date_to?, agent?, limit=10) — fallback search over journals
  • setup_profile(user_name) — set the user name (shown in journals)

Management CLI

powershell
python -m ai_agent_memory_mcp.cli init                  # initialize .aamm in the current projectpython -m ai_agent_memory_mcp.cli status                # store overview (categories / vectors / md / journal)python -m ai_agent_memory_mcp.cli export [--dir DIR]    # export all memories to Markdownpython -m ai_agent_memory_mcp.cli sync                  # rebuild SQLite + Chroma from Markdownpython -m ai_agent_memory_mcp.cli check                 # consistency check (db / md / chroma)python -m ai_agent_memory_mcp.cli journal [--limit N]   # show recent journal entries

Wire into Claude Code (user scope; shared code, per-project data)

From PyPI (no PYTHONPATH needed):

powershell
claude mcp add aamm -s user -- python -m ai_agent_memory_mcp --agent claude-code --project-from-cwd

From a source clone, add -e PYTHONPATH=<clone dir>\ai_agent_memory_mcp:

powershell
claude mcp add aamm -s user -e PYTHONPATH=<clone dir>\ai_agent_memory_mcp -- python -m ai_agent_memory_mcp --agent claude-code --project-from-cwd

Qoder / Cursor are the same — just change --agent.

Data layout

.aamm/├── memory.db                    # SQLite: structured memories + FTS5├── chroma/                      # Chroma vector store├── memories/<category>/<id>.md  # Markdown mirror (editable)├── logs/│   ├── journal.db               # work journal (search source)│   └── YYYY-MM-DD.md            # per-day journal timeline├── config.yml                   # embedding config└── profile.json                 # user name

License

MIT

Source: README.md at commit 467d1e9

Tools

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

Version history

1
  1. v0.1.1LatestSep 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

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.

Streamable HTTPWeb executableAuth
Location & LifestyleCredential requiredOct 29, 2026

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.

Streamable HTTPWeb executable
Databases29 toolsOct 24, 2026

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…

Streamable HTTPWeb executable
Databases7 toolsOct 27, 2026

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.

STDIODesktop only
AI & MLNot validated yetNov 7, 2026

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.

Streamable HTTPWeb executable
Location & Lifestyle13 toolsNov 3, 2026