Skip to main content

faf-memory-mcp

v0.1.2 — Plugin install is faf-memory@faf-plugins (Anthropic directory listing in review).

MCP server for .fafm — the Permanent Memory Layer (PML) for Claude Code, Cursor, Grok, and any MCP host.

Cross-vendor persistent memory in a file you can read. Offline-first. Your soul, your bytes.

What's New in 0.1.2

Plugin install is faf-memory@faf-plugins (Anthropic directory listing in review).

  • Corrects 0.1.1, which said the plugin was live at faf-memory@claude-community. It isn't in that marketplace; it's in the FAF marketplace, and its Anthropic directory listing is in review.
  • Hosts: Cursor, Grok and any MCP host share one mcpServers JSON (below).
  • No code changes. Full arc: CHANGELOG.

Wraps claude-fafm-sdk via fastmcp. Receipt: 400+× faster type-filter queries vs grep on a real 492-file AI memory corpus — falsifiable methodology at Wolfe-Jam/faf-memory-proof.

PyPI CI IANA Zenodo DOI DOI: Agents paper License: MIT

Why

Every AI session, your agent starts blank — no memory of what you decided yesterday, what worked, what was tried. The fix isn't another hosted memory service; it's a file the AI reads at session start and writes back to as it learns. That file is .fafm — IANA-registered, cross-vendor, and 996 KB / 49 ms cold-load for a 492-fact corpus (full numbers: the receipt).

This server is that file, over MCP. FAFA’s etch_memory / recall_memory is the hosted namepoint path on mcpaas. Complementary, not a second product.

Install

uvx faf-memory-mcp

Use in a host

Claude Code — the faf-memory plugin, from the FAF marketplace (Anthropic directory listing in review):

claude plugin marketplace add Wolfe-Jam/faf-plugins
claude plugin install faf-memory@faf-plugins

Requires uv — the plugin launches this server with uvx.

Cursor · Grok · any host — same JSON. Cursor: ~/.cursor/mcp.json. Grok: .mcp.json (Grok also reads Cursor’s file).

{
  "mcpServers": {
    "faf-memory": {
      "command": "uvx",
      "args": ["faf-memory-mcp"]
    }
  }
}

Tools

Tool What it does
etch(text, id?, type?, priority?, tags?) Write a durable fact and persist to $FAF_SOUL_PATH. O(1) dedup by id.
recall(query?, type?, tags?, min_priority?, limit?) Filter (substring + type + tags + priority floor) → rank by priority then recency.
list_facts() List ALL facts — no filter, no rank.
save_soul(path?) Write the soul to another path (etch already saves the default file).
load_soul(path?) Load a .fafm from disk, replacing the in-memory soul.

Configuration

Env var Default What
FAF_SOUL_NAMEPOINT @local Initial soul identifier
FAF_SOUL_PROFILE knowledge .fafm profile (knowledge or voice)
FAF_SOUL_PATH soul.fafm Default save/load path

Format

.fafm is IANA-registered as application/vnd.fafm+yaml (registered 2026-05-13). Sibling of .faf (application/vnd.faf+yaml, 2025-10-30).

How to know it's working

  • Your agent doesn't ask "what is this project?" twice in the same week.
  • recall("X") surfaces what you etched last session, not just this one.
  • The .fafm file grows readably — it's plain YAML, diff it like code.
  • Open the same .fafm in grok-faf-voice — same facts. Cross-vendor proven.

Tradeoff note

Biases toward deterministic recall (substring + type + tags + priority + recency) over semantic recall. For semantic/ranked recall + LLM smart-merge, see hosted namepoints in claude-fafm-sdk. Offline-first ≠ offline-only.

The FAF Memory cluster

Citation

Wolfe, J. (2026). Permanent Memory and Instant Recall: The .fafm Standard for Multi-Profile AI Agent Memory. Zenodo. https://doi.org/10.5281/zenodo.20348942

Wolfe, J. (2026). Why Agents Need a Passport: .fafa — Portable Identity for the Agentic Era. Zenodo. https://doi.org/10.5281/zenodo.21951641

License

MIT.

Metadata

Release files for faf-memory-mcp 0.1.2

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for faf-memory-mcp 0.1.2
File Size Uploaded
faf_memory_mcp-0.1.2.tar.gz 11.2 kB Details

Built distribution (wheel)

Table of built distributions (wheels) for faf-memory-mcp 0.1.2
File Interpreter ABI Platform
faf_memory_mcp-0.1.2-py3-none-any.whl Python 3 none any Details

Total release size: 18.5 kB

Release files / faf_memory_mcp-0.1.2.tar.gz

Download URL faf_memory_mcp-0.1.2.tar.gz
Size 11.2 kB
Tags Source
SHA-256 checksum
How to use checksums
7e8de84c619e9cbeb091d0381a04d85900654d04926e0892075a74e748129bbd
BLAKE2b-256 checksum
How to use checksums
cb484e116b6f7779915d73a739427dcfca3d0dd1988aef20ef477a9de03d6156
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.14

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Oct 3, 2026.

Transparency log

Release files / faf_memory_mcp-0.1.2-py3-none-any.whl

Download URL faf_memory_mcp-0.1.2-py3-none-any.whl
Size 7.3 kB
Tags Python 3
SHA-256 checksum
How to use checksums
c1a2ccd252ab4a5b666b13a3fa2d8e0ec48113960cb023a5081806adaaefd855
BLAKE2b-256 checksum
How to use checksums
302ba33e8070ef39eac01f8b234640f06bfd49aa173f2e435331da91dd8bc63f
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.14

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Oct 3, 2026.

Transparency log

Release history Release notifications | RSS feed

This release

0.1.2 This release

2 release files

0.1.1

2 release files

0.1.0

2 release files

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page