An out-of-the-box engineering framework for AI coding.
AI writes code fast, but every session it starts from scratch — no memory of your project, your conventions, or your team's requirements. Trellis persists specs, tasks, and memory into your repo, so any coding agent works to your engineering standards.
简体中文 • Ecochain Quick Start • Upstream Docs • Supported Platforms • Use Cases
| Capability | What it changes |
|---|---|
| Auto-injected specs | Write conventions once in .trellis/spec/, then let Trellis inject the relevant context into each session instead of repeating yourself. |
| Task-centered workflow | Keep PRDs, implementation context, review context, and task status in .trellis/tasks/ so AI work stays structured. |
| Project memory | Journals in .trellis/workspace/ preserve what happened last time, so each new session starts with real context. |
| Team-shared standards | Specs live in the repo, so one person's hard-won workflow or rule can benefit the whole team. |
| Multi-platform setup | Bring the same Trellis structure to 21 AI coding platforms instead of rebuilding your workflow per tool. |
- Node.js >= 18
- Python >= 3.9
# 1. Install Trellis
npm install -g @ecochain/trellis@latest
# 2. Initialize in your repo
trellis init -u your-name
# 3. Or initialize with the platforms you actually use
trellis init --cursor --opencode --codex -u your-nameThe commands above are the authoritative installation path for this Ecochain fork. The
upstream documentation remains useful for feature and
platform reference, but its installation examples use the upstream @mindfoldhq
packages rather than the Ecochain packages published here.
Natural language is the normal workflow entry:
- Describe what you want in natural language.
- Let the agent classify the request as readonly, operational, business feature, bugfix, maintenance, or review revision. It creates only the task artifacts justified by the request's scope and risk.
- Review gates and evidence when requested. Product Intent is required for business features; maintenance and bugfix work may use a reasoned
NOT_REQUIREDTask Basis. Verification is selected according to risk and applicability. - Complete through the active workflow and host. Explicit Trellis commands and skills remain available for recovery, correction, advanced control, or platforms without automatic routing; they are not a required command chain.
Trellis routes each request through the current workflow and task state. Readonly and ordinary operational work normally proceeds without a development task. Development work records a proportionate Task Basis and, when needed, a PRD, design, or implementation plan before applicable verification and completion steps run.
Execution can stay inline, where the active agent reads the task and applicable
.trellis/spec/ files directly, or use sub-agents for bounded work. Sub-agent
dispatch requires curated implement.jsonl or check.jsonl context; those files are
context manifests, not implementation logs or quality results. Inline execution does
not require JSONL, but it still loads the relevant specs and performs verification.
| Need | Link |
|---|---|
| Install the Ecochain fork | Ecochain Quick Start |
| Understand platform differences | Supported Platforms |
| See the workflow in practice | Real-World Scenarios |
| Start from spec templates | Spec Templates |
| Track releases | Changelog |
How is Trellis different from CLAUDE.md, AGENTS.md, or .cursorrules?
Those files are useful entry points, but they tend to become monolithic. Trellis adds scoped specs, task PRDs, workflow gates, workspace memory, and platform-aware generated files around them.
Is Trellis only for Claude Code?
No. Trellis is a project layer that works across multiple coding agents and IDEs.
Is Trellis for solo developers or teams?
Both. Solo developers use it for memory and repeatable workflow. Teams get the larger benefit: shared standards, task boundaries, reviewable context, and platform portability.
Do I have to write every spec file manually?
No. Many teams start by letting AI draft specs from existing code and then tighten the important parts by hand. Trellis works best when you keep the high-signal rules explicit and versioned.
Can teams use this without constant conflicts?
Yes. Personal workspace journals stay separate per developer, while shared specs and tasks stay in the repo where they can be reviewed and improved like any other project artifact.
Official Repository • AGPL-3.0 License • Built by Mindfold