MikeTrendsTrends right now

⬢github Python · 688 ★ +1 since we first saw it · pushed 1 d ago · MIT

ethanplusai/astra-flash-orchestrator

Astra plans and reviews; DeepSeek Flash builds. A native Codex workflow with phased tasks, verification, safe installation and reversible setup.

Astra Flash Orchestrator is a Python-based Codex workflow that splits AI coding labor by cost: Astra handles planning, architecture, and final review, while the cheaper DeepSeek V4.1 Flash does the bulk implementation, testing, and debugging. It packages work into coherent task bundles, collects evidence, and includes reversible, dry-run installation, with OpenCode support.

Why now: It's trending on GitHub's most-starred new repos, boosted by benchmark claims of ~98% lower cost per 1K lines versus an all-Astra workflow.

Who it is for: Developers using Codex or OpenCode who want premium-model judgment on decisions but cheap model execution for routine coding.

ai-agentscodexdeepseekdeveloper-toolsorchestrationcost-optimization

agent-orchestrationai-agentscodexcodex-skillsdeepseekdeveloper-tools

Open on GitHub →

Stars over our 11 snapshots: 687 to 688, since 1 h ago.

Where people talked about it

API: https://socialmediatrends-api.osmike.com/v1/repos/ethanplusai/astra-flash-orchestrator