docs: add DEAR_LLM.md with repository context for AI agents

Create a concise overview document to help AI agents understand
the Sketch repository architecture, components, and common development
workflows. Includes information about the dual binary pattern,
container system, and development gotchas that would be helpful
context for future AI assistance.

Co-Authored-By: sketch <hello@sketch.dev>
1 file changed
tree: e5db69c3873acb9ad8e8cbfbf208431aa39ac3be
  1. .github/
  2. .vscode/
  3. bin/
  4. browser/
  5. claudetool/
  6. cmd/
  7. dockerimg/
  8. experiment/
  9. httprr/
  10. llm/
  11. loop/
  12. skabandclient/
  13. skribe/
  14. termui/
  15. webui/
  16. .clabot
  17. .dockerignore
  18. .gitignore
  19. CONTRIBUTING.md
  20. DEAR_LLM.md
  21. go.mod
  22. go.sum
  23. LICENSE
  24. README.md
README.md

Sketch

Sketch is an agentic coding tool.

Sketch runs in your terminal, has a web UI, understands your code, and helps you get work done. To keep your environment pristine, sketch starts a docker container and outputs its work onto a branch in your host git repository.

Sketch helps with most programming environments, but Go is Sketch's specialty.

To get started:

go install sketch.dev/cmd/sketch@latest
sketch

Requirements

Currently sketch runs on macOS and linux. It uses docker for containers.

macOS: brew install colima (or an equivalent, like Docker Desktop or Orbstack) linux: apt install docker.io (or equivalent for your distro) WSL2: install Docker Desktop for Windows (docker entirely inside WSL2 is tricky)

The sketch.dev service is used to provide access to an LLM service and give you a way to access the web UI from anywhere.

Feedback/discussion

We have a discord server to discuss sketch.

Join if you want! https://discord.gg/6w9qNRUDzS

Development

Go Reference

See CONTRIBUTING.md

Open Source

Sketch is open source. It is right here in this repository! Have a look around and mod away.

If you want to run sketch entirely without the sketch.dev service, you can set the flag -skaband-addr="" and then provide an ANTHROPIC_API_KEY environment variable. (More LLM services coming soon!)