By Wolfe-Jam
Permanent Memory Layer (PML) for Claude Code. .fafm is an IANA-registered structured file (application/vnd.fafm+yaml) — cross-vendor persistent AI memory. Offline-first, your file, your soul. Wraps the faf-memory-mcp server. 400+x faster type-filter queries vs grep (falsifiable receipt: Wolfe-Jam/faf-memory-proof).
Your Claude doesn't remember yesterday. .fafm is the file that fixes that — IANA-registered, cross-vendor, offline-first. Open the same memory in grok-faf-voice — same facts, both directions tested.
/plugin install faf-memory
That's it. The plugin wires the faf-memory-mcp server into Claude Code via uvx, exposing five tools.
| Tool | What it does |
|---|---|
etch(text, id?, type?, priority?, tags?) | Write a durable fact. 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() | Enumerate all facts (no filter, no rank). |
save_soul(path?) | Persist to a .fafm file. |
load_soul(path?) | Load a .fafm from disk. |
Memory lives in .fafm — plain YAML, IANA-registered. Diffable like code. Portable to any tool that reads the format.
recall("X") surfaces what you etched last session, not just the current one..fafm file grows readably — open it, diff it, share it.grok-faf-voice — same facts. Cross-vendor proven..fafm is the structured source. It sits alongside (not against) the rest of Anthropic's memory stack:
memory_20250818 tool contract — speakable via the proprietary fafm-engine (enterprise lane)claude-md-management — maintains the rendered CLAUDE.md; .fafm is its memory siblingremember — conversational daily logs; .fafm is its structured peerPML is the standard underneath — IANA-registered, cross-vendor, offline-first.
400+× faster type-filter queries vs grep on a real 492-file AI memory corpus. Falsifiable methodology + scripts + sanitized pilot at Wolfe-Jam/faf-memory-proof — reproduce in 30 seconds with one paste.
Biases toward deterministic recall (substring + type + tags + priority + recency) over semantic recall. For semantic / LLM smart-merge, see hosted namepoints in claude-fafm-sdk. Offline-first ≠ offline-only.
faf-memory — wraps faf-memory-mcpWolfe-Jam/faf-memory-mcp — the MCP serverWolfe-Jam/faf-memory-proof — the falsifiable receiptWolfe-Jam/faf-plugin — sibling: .faf context (FCL)claude-fafm-sdk — the open Python SDKWolfe-Jam/faf — the format spec + IANA registrationMIT.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
npx claudepluginhub wolfe-jam/faf-plugins --plugin faf-memoryPersistent Project Context for AI — IANA-registered .faf format. Run /faf to score your project in Claude Code; install the CLI via `bunx faf` or `npm install -g faf-cli` for the full toolkit.
17 Claude Code skills for AI-context, testing, and MCP development. IANA-registered format (application/vnd.faf+yaml). Create .faf project DNA, score AI-readiness, sync with CLAUDE.md, build MCP servers, generate test suites.
Persistent project context for Claude Code. .faf is an IANA-registered structured file (application/vnd.faf+yaml) that generates and syncs your CLAUDE.md — project DNA that survives across sessions. Wraps the claude-faf-mcp server.
Memory compression system for Claude Code - persist context across sessions
Standalone image generation plugin using Nano Banana MCP server. Generates and edits images, icons, diagrams, patterns, and visual assets via Gemini image models. No Gemini CLI dependency required.
Streamline people operations — recruiting, onboarding, performance reviews, compensation analysis, and policy guidance. Maintain compliance and keep your team running smoothly.
Write feature specs, plan roadmaps, and synthesize user research faster. Keep stakeholders updated and stay ahead of the competitive landscape.
Create content, plan campaigns, and analyze performance across marketing channels. Maintain brand voice consistency, track competitors, and report on what's working.
Prospect, craft outreach, and build deal strategy faster. Prep for calls, manage your pipeline, and write personalized messaging that moves deals forward.