Open-source CLI runs your coding agent overnight: fail, self-fix, retest till green
future_coded · x · 2026-10-14
A dev shares a "sleep is now part of the dev loop" setup: the coding agent works through the night, with its definition of done being TestSprite's integration tests passing against the running app. Each failure returns as the step that broke plus a fix prompt, so the agent fixes and retests autonomously.
The CLI is open source under Apache-2.0 and works with Claude Code, Codex, Cursor, Antigravity, Kimi and Trae.
More from coding & agent
- Multi-agent tree search: pooling discoveries can scale returns as N² — Hidenori8Tanaka · 2026-10-14
- Dev praises AI bot that proactively claimed a PR and ran code review on its own — msg · 2026-10-14
- Nous Research ships Hermes Agent v0.22.0, the 'Threshold' release — Polymarket · 2026-10-14
- Cohere Labs: scaling multi-agent teams for long-horizon software engineering — Cohere_Labs · 2026-10-14
- ResearchTwin MCP server lets agents discover researchers, papers and datasets — modelcontextprotocol · 2026-10-14
- RustGIS vs QGIS: an 18-30 MB Rust app with browser WASM build and built-in AI assistant — giswqs · 2026-10-14