Knowledge flow
Knowledge flow
Raw captures become compound intelligence through a pipeline that runs automatically. You never trigger it. You just work - and the knowledge compounds.
The flow
Capture → Digest → Seal → Pending → Kept → Synthesis → Sub-vaults → Knowledge
Capture. While your session is open, fai writes JSONL files continuously -
AI transcripts, file diffs, git events, terminal commands. Zero AI calls.
Zero cost. Happens on every SealInterval (default: 60 seconds).
Digest. Before sealing, captures are grouped and summarized into digest files. These are structured documents the synthesis agents can efficiently read.
Seal. You seal the session. The journal/<name> branch merges to pending.
All digests are now queued for synthesis.
Pending. The staging area. Sessions accumulate here until the
ProposalThreshold is met - enough sessions have sealed to make a synthesis
run worthwhile.
Synthesis. When the threshold is met, four synthesis agents run in parallel - one per sub-vault (Context, Pattern, Decision, Petnames). Each agent reads the digests relevant to its domain and produces updated vault knowledge.
Kept. The synthesized knowledge commits to the kept branch. This is the
stable, distilled record of what your workbench has learned from all sealed sessions.
Sub-vaults. The four sub-vaults (ContextVault, PatternVault, DecisionVault, PetnamesVault) each hold their synthesized knowledge as structured files.
Knowledge. The KnowledgeVault aggregates all four sub-vaults into:
FAI-PROJECT.md- everything this project knowsFAI-PERSONAL.md- everything about how you work
Every AI you connect reads these on startup.
What triggers synthesis
Synthesis runs automatically when enough sessions have sealed. You configure
this threshold when you run fai synthesize:
fai synthesize
The interactive setup asks which synthesis provider to use (Ollama, LM Studio, OpenRouter, Groq, OpenAI, claude-code, or capture-only) and how frequently to synthesize. After that, it runs on its own.
The result
By session 10, your AI starts a session already knowing:
- Your architecture decisions from the last 9 sessions
- The naming conventions you've been using
- The patterns you apply consistently
- What you said you'd work on next
No re-explaining. No context pasting. Just: continue.
Pure mechanical observation
Everything you do is written to disk as structured JSONL. Git activity, file changes, terminal output, AI transcripts. No model calls, no cost. Runs continuously. This is the foundation - nothing can compound without this.
Patterns, decisions, context
AI agents read captured digests and synthesise meaning into the appropriate vault types. Each sub-vault runs its own agent. Runs continuously, periodically, or on demand.
The moment your vault becomes your brain
The full cascade: captures → all four sub-vaults synthesised → knowledge vault aggregated. Runs automatically after a configured number of seals. After this runs, every connected AI gets your full accumulated knowledge injected on startup.