How it works

Work. Capture. Compound. Crystallize.

How Fathym turns every working session into compound intelligence — and what you can configure along the way.

Work

as normal

Capture

auto

Compound

background

Crystallize

over time

Step one

Work with any AI, any tool.

Fathym doesn't replace your tools. It wraps around them. Claude Code, Cursor, Windsurf, Codex, Cline, Ollama — whatever you already use keeps working exactly as it does today. You just run fai first.

That one command loads your three vaults — session, project, and personal — and hands all of that context to whatever AI you're using next. No configuration. No re-explaining yourself. Your context travels with you, not with the tool.

Claude CodeCursorCodexWindsurfClineOllama+ whatever's next

Your context loads instantly. Session 50 picks up exactly where session 49 left off — even across tools.

~ fai
$ fai # or: fai --continue──────────────────────────── Loading vaults...session · project · personal 63 patterns · 18 decisions · 5 agents────────────────────────────Detected tool: claude-code> switch to cursor for this session Switched. All 63 patterns now active in Cursor.
Step two

Everything you do gets captured.

As you work, Fathym captures every AI interaction in real time — via hooks inside Claude Code, Cursor, and any other tool you've connected. You don't press anything. It just happens.

Captures are written as JSONL files on a journal/<session-name> git branch — not a database, not someone else's cloud. Your project directory. Your git history. Plain files you can read, inspect, and take with you.

Every prompt & responseDecisions you madePatterns you settled intoPreferences you expressed

Every connected AI tool writes to the same session. Seal when you're done — everything you did is now queued for synthesis.

vault lifecycle — per session
1
Capture → journal/<session>

AI transcripts, file changes, terminal commands, git events — written as JSONL files continuously. Zero AI calls. Zero cost.

2
Seal → pending

You seal the session. The journal branch merges to pending — the staging area for synthesis. Other active sessions on the project inherit your context.

3
Synthesize → sub-vaults

When enough sessions have sealed, four synthesis agents run in parallel — one each for Context, Pattern, Decision, and Petnames sub-vaults.

4
Commit → kept

Synthesized knowledge commits to the kept branch — the stable, distilled record every new session inherits from.

📄 three vault types · one portable brain
session vault

Live captures. JSONL files on journal/<session>. AI transcripts, file changes, terminal activity. Temporary — feeds the knowledge vaults through synthesis.

project vault

What this project knows. Architecture decisions, naming conventions, stack choices. Shared by everyone on the project. Exports FAI-PROJECT.md — read by every AI on startup.

personal vault

How you work, everywhere. Lives at ~/.fai/ — follows you across every project and machine. Exports FAI-PERSONAL.md.

Step three

Captures become compounding intellect.

This is where Fathym goes beyond anything your AI tools do on their own. Their memory is per-session, per-tool, and gone when you switch. What Fathym builds is structured, typed context — decisions with lineage, patterns with frequency, preferences with evidence.

In the background, synthesis agents read your captures and update the four sub-vaults: Context (current focus), Pattern (recurring behaviours), Decision (architectural choices), and Petnames (session naming). These aggregate into FAI-PROJECT.md and FAI-PERSONAL.md — what every AI reads on startup.

Here's the test: delete your .fai folder. You'll feel the regression immediately — the AI suddenly asking things it already knew, forgetting preferences you'd stopped thinking about. That gap is what Fathym is filling.

This isn't memory, and it isn't context. It's trained instinct — the compound result of everything you've done, synthesized into something the AI applies without being asked.

~ fai — compound context
63 patterns · 18 decisions · 5 agents────────────────────────────> Build me a REST API for user authApplying compounded context:PostgreSQL · your preference since session 4JWT tokens · decided session 8, never overriddenTitle case members · enforced across 31 sessionsRepository pattern · 14 prior uses Scaffolding with your standards...
What compounds session by session
Session 1
Start from scratch — once.Everything captured from here. Your vault starts growing immediately.
Session 5
AI knows your stack.Preferences, naming, test patterns — learned without being told. You stop being asked the same questions.
Session 20
AI anticipates your decisions.Architecture choices stop being relitigated. Your patterns become its defaults. Cross-project preferences travel with you.
Session 50
Trained instinct.Not recall. Not memory. The AI applies your standards as if they were its own — across every tool, every project.
Step four

Repeated patterns become tools you own.

Compounding intelligence is powerful. But there's a fourth step most tools skip entirely: crystallization.

When Fathym notices you running the same workflow repeatedly — same input, same output, same structure — it can propose locking that pattern into a deterministic micro-agent. Typed input schema. Typed output. No AI thrashing. No model variance.

The pattern runs fast, cheap, and reliably. If a model upgrade breaks it, you fix the prompt once. And the more you crystallize, the less AI you actually need.

Think of it like micro frameworks for your workflow. Crystallize the repetitive stuff. Save the AI for the work that actually needs it.

1

Compounding reveals patterns

The vault notices you've run this same workflow 12 times. Same inputs, same structure, same preferences applied every time.

2

Fathym proposes a micro-agent

A typed input schema and output spec are generated. You review and approve — or edit to refine.

3

Pattern locks in

The crystallized agent runs without full AI. Input in, output out. Cheap, fast, predictable.

4

Stays current automatically

If a new model or preference changes the output, you update the prompt once. The agent self-corrects everywhere.

Sessions

Name your work. Resurrect it later.

Sessions are how you organize context. Name a session "auth" and everything you build — decisions, patterns, active workstreams — is scoped to that name. Close it when you're done.

Six months later, when auth work comes back up, you don't start from scratch. You resurrect that session. The branch reopens. Every decision from last time is still there. Your AI picks up like no time has passed.

And when you and a teammate are working on the same project? Every time your session seals, their session automatically receives your latest context. No merge conflicts. No catch-up conversations.

Sessions let you scope context to the work — not the calendar. Past work is never lost. It's just archived, waiting to be resumed.

~ fai sessions
$ fai sessions list──────────────────────────── auth active · 47 seals · last: 2h ago billing archived · 31 seals · 3 months ago api-v2 archived · 89 seals · 6 months ago$ fai sessions billing compound Resuming "billing" session... Context restored · picks up where you left offStripe integration decisions · all 31 seals intact
Operating modes

Start free. Scale when ready.

fai's vault structure never changes. What changes is when synthesis runs and which model runs it. Configure once with fai synthesize — then it runs automatically.

Capture-only is free forever. A developer who captures for six months, then switches on synthesis, immediately gets six months of compound intelligence synthesized. Capture is never wasted.

Local models (Ollama, LM Studio) run synthesis free on your machine. No API key. No cost. Full privacy.

three modes · same architecture
1
Capture only · free

Everything captured to disk as JSONL. No synthesis, no AI calls. Vaults are searchable and inspectable. No API key needed.

2
Scheduled synthesis · managed cost

Capture + synthesis on your schedule. Works with local models (Ollama, LM Studio) or cloud (OpenRouter, Groq, OpenAI). ~$1–2/day at moderate cadence with cloud.

3
Always-on synthesis · power mode

Synthesis runs after every configured number of seals. Maximum freshness. Higher cost — immediate compound intelligence after each work block.

~ fai synthesize
$ fai synthesize────────────────────────────Select synthesis provider:ollama local · free · privatelmstudio local · free · privateopenrouter cloud · many modelsclaude-code cloud · high qualitycapture-only no synthesis · free Synthesis configured. Runs automatically.

Your AI finally knows you.

Install in under a minute. Your first session starts building context immediately — and it only gets smarter from there.

deno run -A jsr:@fathym/fai/install