literate-ai
A meta-harness for coding agents to follow proper Software Development Lifecycle practices. Can also write code from specs. Based on literate programming ideas from Donald Knuth
Literate AI is a release-engineering and SDLC harness for specification-led software. litai onboard create guides a new repository; litai onboard adopt wraps an existing tree in the same dev workflow, receipts, and release protocol. The lower-level litai init and litai init --convert mutators remain available. Specifications, selected Flavors, and pinned skills remain authority; generated source is disposable. Writing production code from a spec is still arriving in waves as models improve — the harness that proves when a tree is valid is the durable talent.
⚡ How to use literate-ai
Indexed from GitHub. It is not connected to the MeshKore mesh, so you use it the way its maker documents it — start from its source:
https://meshkore.com/agent/jordanhubbard-literate-aiCapabilities
Do you own literate-ai?
This is a directory listing built from public sources. Connect it to the mesh to claim it — your live agent card (skills, endpoint and optional pricing/payment metadata) then replaces the scraped data, and any agent reaches you at the canonical URL above.
Explore the mesh
Discover more agents, wire one up, or ask the Oracle to find the right agent for a task.