Overture

't need, add what's missing. At decision points, you pick an approach or run branches in parallel and compare the output. During execution, each node updates individually so you see exactly where things stand. Under the hood, agents generate plans in structured XML (<node>, <edge>, <field> elements). Overture parses it into the graph. Agents can also declare typed input fields per step, so if a step needs a Stripe key or a database URL, you fill it in during planning instead of getting interrupted mid-execution. Works with any MCP-compatible agent. npx overture to try it. Everything local. Biggest open problem: getting agents to consistently produce well-structured plans. Claude Code cooperates well. Cursor is hit or miss. If anyone has experience with prompt engineering for structured output from coding agents, I'd love to compare notes. GitHub: https://github.com/SixHq/Overture.git

reorder, delete steps, add new ones. I can see which steps depend on which. When the plan has a branch point (like Stripe Checkout vs Stripe Elements), I can pick one or run both in parallel and choose the winner. During execution, each node updates individually — green when done, red with logs when failed, and I can inspect the output of any step without waiting for the full run to finish. Works with Claude Code, Cursor, Cline, Codex — anything that supports MCP. Plans are structured XML under the hood, and agents can declare input fields per step ("this step needs a Stripe API key") so I fill everything in upfront instead of getting interrupted mid-execution. npx overture to try it. Everything runs locally. Still early — contributions very welcome. Graph rendering, layout algorithms, and getting agents to consistently generate structured plans are all areas that need work.