Trellis
The best agent harness.
At a glance.
A compact read before the deeper capability notes and official setup links.
Core features.
Feature cards focus on what the tool helps users do, not generated setup commands.
Task-centered workflow Keep PRDs, implementation context, review context, and task status in .trellis/tasks/ so AI work stays structured.
Team-shared standards Specs live in the repo, so one person's hard-won workflow or rule can benefit the whole team.
Trellis runs a 4-phase loop with auto-invoked skills and sub-agents:
Research-heavy items go to a trellis-research sub-agent.
The result is curated specs + research files referenced from implement.jsonl / check.jsonl.
Implement — a trellis-implement sub-agent writes code from the PRD with the curated context auto-injected, no git commit.
Verify — a trellis-check sub-agent reviews the diff against specs and runs lint, type-check, and tests, self-fixing where it can.
See the workflow in practice Real-World Scenarios
Agent / Skill / MCP / Workflow fit.
This panel keeps technical format separate from the user-facing AI category.
Official setup path.
Generated install snippets are intentionally not mirrored here because they drift. The page links to source-owned setup docs instead.
Evidence and adoption notes.
These notes help a user decide whether to investigate the official project further.
Source repository last pushed at 2026-05-18T03:39:10Z.
Generated from source metadata; confirm operational details in the official project before adopting it.
Review the upstream license, maintenance activity, and issue history before using it in production.