Ordewell - Multi-agent task orchestration for coding agents
Show HN: Ordewell – turn one goal into an ordered plan of coding-agent tasks
Ordewell turns a single goal into an ordered plan of coding-agent tasks, each with its own runner, model, and mode. The planner researches your repo read-only, asks clarifying questions, and produces a typed, editable plan before any tokens are spent. Execution spawns real coding-agent sessions that respect dependencies, and a VerdictEngine confirms completion only when evidence appears. It works with Claude Code, Codex, OpenCode, and custom plugins, with no extra API key required. Available as a CLI, TUI, and VS Code extension.
A plan you can rewrite before a token is spent — every task carries a runner, model, thinking effort and mode, and you can change any of them without losing completed work or round-tripping the AI.
- ramon156
i would love a deterministic program that can confidently make plans for lower-cost models like deepseek. ofcourse the LLM part wont be deterministic, but its a lot easier to measure quality like this. you could argue an AGENTS.md is this, but from experience its not enough to make non-frontiers act have a high success rate.
- Lalabadie
I opened the page looking for a differenciator, but everything about the project is AI-written (including author replies in these comments).
- sharathr
have you tried https://github.com/highflame-ai/codeoid