Every task, routed to the right model.
Claude, GPT and Gemini are each best at different things, but most coding agents stick to one. Sparse plans your task and routes every part to the model that fits it, so you get frontier quality where it counts and pay less everywhere else.
Free. macOS on Apple Silicon. Updates itself.
Free. Windows on x64. Updates itself.
npm install -g sparse-cliOne assistant, every model
One OpenRouter key gives Sparse the whole catalog: Anthropic, OpenAI, Google, DeepSeek, Moonshot, Z.ai and more. Prefer local? Point it at Ollama.
You review every change
Edits come back as a diff you accept or undo, file by file. Work on a copy keeps them in a git worktree until you do.
See every decision
Each model pick is logged with its reason, and routing improves from the outcomes of your own runs.
Chat or code
Questions, emails and research get one well-routed answer. Coding tasks get a full pipeline: plan, edit, validate, review.
Many models. One plan.
Sparse isn't another model. It's the planner and orchestrator that decides which model does what.
1 / 3
A planner that thinks first
Sparse reads your whole request before writing a line. It breaks the work into steps and works out how hard each one really is.
2 / 3
An orchestrator that picks the model
Each step goes to the model best suited to it, from Anthropic, OpenAI, Google and more. Hard design work gets a frontier model. Routine edits get a fast, cheap one. Steps run side by side.
3 / 3
One change, checked
The pieces come back together as one change, checked against your tests before you see it. If a step falls short, a stronger model takes it over. You never have to pick a model.
Stop choosing models. Just build.
Free. macOS on Apple Silicon. Updates itself.
Free. Windows on x64. Updates itself.
Want the details first? Read the docs.
About
Sparse is built by Efe Acar. It started from a simple observation: most of a coding session isn't hard, so it shouldn't all run on the most expensive model.
- Get in touch
- efeacar2705@gmail.com
- Found a bug or want a feature?
- Open an issue on GitHub