🌿 Trellis

Open standard · Apache-2.0 · agent-independent

Let AI-built software
grow without sprawling.

Generating code is easy now. Keeping it under control is not. Trellis is a capability-first, evidence-governed standard that keeps AI-generated software understandable, testable and maintainable as it grows - on top of the agent you already use.

Build your starter → View the standard

The problem Trellis solves

Spec tools tell an agent what to build. Trellis preserves why it was built that way, how each piece is verified, how much it can grow, and when it must be reconsidered.

Unbounded growth

Duplicated responsibilities, runaway dependencies, ballooning files.

Architecture drift

Locally sensible changes that are globally inconsistent.

Lost rationale

Decisions live in chat history, not in the repository.

Hidden tests

Only engineers can see whether a feature actually works.

Nine pillars, one standard

Wizard

Pick your setup. Get a tailored AI spec to paste into your agent, a reproducible npx command, or a ready-to-use .zip - all generated by the same engine the CLI uses.

1 · Platforms adapter files to generate
2 · Profile drives default budgets & mandatory tests
3 · Project type
4 · Strictness how many gates are enforced
5 · Pillars to enable
Paste into your agent: “Read TRELLIS.md and bootstrap this repo accordingly.” 

          


          

            

              Deterministic, CI-friendly. Reproduces the same setup.
              
            

            

          


          

            

              A ready-to-use governed starter, filtered to your pillars.