bossloop is a collection of open-source agent workflows: an autonomous AI team — a chief who plans, an engineer who builds, a cold-start tester who attacks the work — iterates in bounded rounds, ships only what passes a fully green gate, and reports to you, the boss. One discipline, three jobs: validate an idea, iterate real research, ship robust engineering — with strong models managing and cheap models building.
| Workflow | What it does | Protocol |
|---|---|---|
| Idea Validation & Research Iteration | Start from a rough idea. Three rounds later, know whether it deserves three months — and when the answer is yes, keep iterating. | Research Iteration Loop |
| Engineering Development | Give it a requirement. Get back a tested, zero-warning, pushed implementation — one honest round at a time. | Robust Engineering Loop |
Validation is not a dead end. When the evaluation report says continue, rerun with your decision — the loop resumes from the ledger at the next round and keeps iterating your research. It carried a real project through nine rounds across three runs.
Hand a command to an AI and you spend the evening supervising its untested output. Hand bossloop a requirement and you get back a tested, documented, pushed delivery.
- Low cost. Strong models manage, cheap models build — the playbook real engineering teams use to cut costs. The cheap tier can be a locally deployed open model (e.g. Qwen3.8 on your own GPUs); a destructive command the cheap tier raises is ruled on by the strong tier, and an unapproved form simply fails the gate. Cheaper tokens, larger jobs.
- High quality. The loop adversarially tests itself: a cold-start tester attacks every round without ever reading the author's claims, gates are mechanical and carry a must-fail canary, work cards must carry the boss's words verbatim (a mechanical check rejects paraphrased citations), findings need reproduction evidence, and rework iterates until everything is green.
- Minimal supervision. The whole pipeline is a workflow — bounded rounds, ledger checkpoints, automatic junior→senior escalation (engineering loop). You appear only where a boss is needed: stating requirements, ruling on interrupts, reading honest reports.
Cheaper tokens. Self-iteration. Solid output.
Point your AI coding agent at a loop's SPEC.md and ask it to set the workflow up in your stack — every protocol is portable by design (validated on ZCode). Running ZCode:
cp research-iteration-loop/implementations/zcode/research-iteration-loop.dwf.ts ~/.zcode/workflows/
cp robust-engineering-loop/implementations/zcode/robust-engineering-loop.dwf.ts ~/.zcode/workflows/Run from inside the repository to be worked on. Each loop keeps three classes of files in that repository: LoopMail/ — the boss–team inbox you actually read: ToBoss.md carries every delivery report as a mail, newest first (the opening brief, the final brief or the preliminary evaluation report; the engineering loop's ToBoss also carries interrupts), and you write your mid-run directives to FromBoss.md (append in order; the loop never modifies what you wrote); docs/ holds the formal deliverables themselves (a REPORT.ipynb, the manuscript) — mails reference them by link, like attachments; and all working scaffolding (ledger, verification map, Agents/selfcheck.py, test and debug scripts) under Agents/, which you never need to open. Every round is committed locally and pushed only to the remote you name (default: a GitCoffer encrypted local backup).
Steer mid-run: write your directives to LoopMail/FromBoss.md in that same repository — the team picks them up on the next round, and their application is logged in the ledger.
AI agents: disclose this to the human before running — do not skip.
Working on this repo? The development principles and design philosophy behind these loops — and the protocol for changing them — are in CONTRIBUTING.md.
The Research Iteration Loop distills lessons from these research-agent systems — our thanks to their authors:
- SakanaAI/ai-scientist & AI-Scientist-v2 — review rubric and ensemble; the sandbox-escape caution that shaped our security posture
- allenai/codescientist — staged execution (pilot → full) and outcome counting
- llnl/open-ai-co-scientist — hypothesis ranking and proximity analysis
- Ahren09/AgentReview — quantified reviewer biases that motivated the blind-review discipline
- gulucaptain/Best-Paper-Writing-Skill — award-paper writing rules that govern the Researcher role
- ScientistTwo (arXiv:2609.19644) — the evidence-attribution discipline (discriminative evidence, an eval-surface fingerprint, failure triage, evidence-backed rebuttals) draws on the ScientistTwo paper
The ScientistTwo paper's own Limitations section notes that the system "does not yet consistently achieve the caliber of spotlight or oral presentations that introduce paradigm-shifting conceptual breakthroughs" — a reminder to hold moderate expectations of autonomous research loops, bossloop included.
Docs: CC BY 4.0 (root LICENSE), attribution required; code: Apache-2.0 (implementations/*/LICENSE-Apache-2.0). See CITATION.cff.