v7.6.0 | Spec | Guide | plain markdown | zero deps | MIT
One command. Zero amnesia.
Не объясняй ничего. Просто напиши saipen и продолжи работу над проектом как ни в чём не бывало, любым агентом.
A cold agent with zero chat history runs /saipen continue and resumes work in under a minute -- no rebriefing, any vendor, any day.
User -> /saipen continue
Agent -> reads STATE ("What do I do right now?")
Agent -> reads BOARD ("What task am I picking up?")
Agent -> reads next_action (executes command)
Agent -> Works.
Memory lives in the project, not in a model's head. Project -> Memory -> LLM becomes Project -> SAIPEN State -> LLM.
| Layer | Required | Purpose |
|---|---|---|
| Core | ✅ | Continue work safely |
| Maintenance | On top of Core | Evolve the software with no tasking |
Automated Evolution. Board empty, type /saipen: HUNT audits for bugs, dead code, failing tests. Clean? ADD builds the next obvious missing capability, verifies it, hunts again. Product's mature -> stops gracefully.
GOAL Mode. /saipen goal <what you want> pivots the board (old tickets demoted, never deleted) and runs the new objective to completion -- no "shall I continue?" between tickets, VERIFY/REVIEW never skipped. SHIP auto-pushes to an existing remote; a brand-new repo still asks once. Capped at 3 waves / 20 tickets per run, then checkpoints and reports.
1. Install once per machine -- teaches Claude Code, Gemini, OpenCode, Aider, Antigravity:
git clone https://github.com/vacterro/saipen
cd saipen
powershell -ExecutionPolicy Bypass -File .\bootstrap\inject.ps1 # Windows
bash bootstrap/inject.sh # macOS / Linux2. Start a project -- open an agent in your folder, type:
saipen set
No install? Paste one line to any agent:
Read /saipen/RFC.md + /saipen/STYLE.md and follow them.
- SPEC.md -- formal architecture, for framework builders.
- RFC.md -- the ruleset agents actually execute.
- GUIDE.md -- human tutorial with examples.
