exiw-ai/proofloop

AI orchestrator that runs until done. Define what "done" means, go to sleep, wake up to verified results. Supports OpenCode, Codex, Claude Code,

38
/ 100
Emerging

Implements autonomous task execution with declarative completion conditions—agents automatically retry failed steps up to 50+ iterations while a supervisor detects loops and regressions. Integrates with OpenCode, Codex, and Claude Code as pluggable providers, with independent verification via shell commands (pytest, mypy, make) or text assertions rather than agent self-assessment. Coordinates multi-repository changes and persists task state for resumable long-running workflows across hours of execution.

No Package No Dependents
Maintenance 10 / 25
Adoption 7 / 25
Maturity 11 / 25
Community 10 / 25

How are scores calculated?

Stars

41

Forks

4

Language

Python

License

Apache-2.0

Category

ai-coding-loops

Last pushed

Feb 28, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/agents/exiw-ai/proofloop"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.