Context Layer

Every run starts warm. No agent begins from zero.

Your architecture, your conventions, and every hard-earned lesson your team has already learned travel with every agent, on every run. The longer Fleet Work runs, the sharper its judgment gets.

Reachable from your IDE

Three layers of memory, working together

Global memory carries the conventions that apply org-wide. Repository memory holds the patterns specific to each codebase. Session memory logs exactly what happened on a given run: files touched, decisions made, contracts uncovered. Each layer surfaces to the agent exactly when it's needed.

Global Memory

Org-wide conventions

Repository Memory

Per-codebase patterns

Session Memory

What happened, per run

Memory that curates itself

Living documents, not a scrollback log

Instead of piling up a timeline, Fleet Work distills what happened after every story into tidy, deduplicated knowledge, patterns, decisions, gotchas, API contracts, organized by topic and folded straight into your global and repo memory.

Auto-merged this run
  • · Auth: token refresh must precede retry
  • · Payments API: idempotency key required
  • · Schema: soft-delete pattern for orders
Search by meaning, not keyword

Ask a question, get the decision that answered it

Past runs surface by concept rather than exact wording, so the agent walks in already knowing your setup. It follows the conventions your team already settled on instead of reinventing them, and sidesteps gotchas it's already hit once.

"how do we handle rate limiting?"
3 past decisions
2 gotchas
1 API contract

Give it a head start before day one

Load repository memory with your architecture and patterns up front, so the very first run reads like the hundredth. Memory is what separates an agent that guesses from one that knows, and it's fully yours: editable, inspectable, and always growing as more stories ship.

Give your backlog a running start.