Generated by /office-hours + /plan-ceo-review + /plan-eng-review on 2026-03-28 Branch: garrytan/ce-features Repo: gstack Status: ACTIVE Mode: Open Source / Community
GStack runs 30+ skills across sessions but learns nothing between them. A /review session catches an N+1 query pattern, and the next /review on the same codebase starts from scratch. A /ship run discovers the test command, and every future /ship re-discovers it. A /investigate finds a tricky race condition, and no future session knows about it.
Every AI coding tool has this problem. Cursor has per-user memory. Claude Code has CLAUDE.md. Windsurf has persistent context. But none of them compound. None of them structure what they learn. None of them share knowledge across skills.
Per-project institutional knowledge that compounds across sessions and skills. Structured, typed, confidence-scored learnings that every gstack skill can read and write. The goal: after 20 sessions on the same codebase, gstack knows every architectural decision, every past bug pattern, and every time it was wrong.
/autoship (Release 4). A full engineering team in one command. Describe a feature, approve the plan, everything else is automatic. /autoship can't work without learnings, because without memory it repeats the same mistakes. Releases 1-3 are the infrastructure that makes /autoship actually work.
YC founders building with AI. The people who run gstack on real codebases 20+ times a week and notice when it asks the same question twice.
| Tool | Memory model | Scope | Structure |
|---|---|---|---|
| Cursor | Per-user chat memory | Per-session | Unstructured |
| CLAUDE.md | Static file | Per-project | Manual |
| Windsurf | Persistent context | Per-session | Unstructured |
| GStack | Per-project JSONL | Cross-session, cross-skill | Typed, scored, decaying |
Headline: Every session makes the next one smarter.
What ships:
~/.gstack/projects/{slug}/learnings.jsonl/learn skill for manual review, search, prune, exportSchema (Supabase-compatible):
{
"ts": "2026-03-28T12:00:00Z",
"skill": "review",
"type": "pitfall",
"key": "n-plus-one-activerecord",
"insight": "Always check includes() for has_many in list endpoints",
"confidence": 8,
"source": "observed",
"branch": "feature-x",
"commit": "abc1234",
"files": ["app/models/user.rb"]
}
Types: pattern | pitfall | preference | architecture | tool
Sources: observed | user-stated | inferred | cross-model
Architecture: append-only JSONL. Duplicates resolved at read time ("latest winner" per key+type). No write-time mutation, no race conditions. Follows the existing gstack-review-log pattern.
Headline: 10 specialist reviewers on every PR.
What ships:
Headline: Ship after R2 proves stable. Check in on how the core loop is performing.
Pre-check: review R2 quality metrics (PR quality scores, specialist hit rates, false positive rates, E2E test stability). If core loop has issues, fix those first.
What ships:
Headline: GStack respects your time.
What ships:
Headline: Describe a feature. Approve the plan. Everything else is automatic.
What ships:
Headline: The full-stack AI engineering studio.
What ships:
The self-learning roadmap was inspired by ideas from the Compound Engineering project by Nico Bailon. Their exploration of learnings persistence, parallel review agents, and autonomous pipelines catalyzed the design of GStack's approach. We adapted every concept to fit GStack's template system, voice, and architecture rather than porting directly.