agent-trellis
v0.9.1
Published
A unified Code Agent Runtime for Skills, MCP, Memory, and shared instructions across Claude Code, Codex, Kiro, pi, Kimi Code, and ZCode.
Maintainers
Readme
Trellis
One canonical source for Skills, MCP, Memory, and shared instructions — projected safely into Claude Code, Codex, Kiro, pi, Kimi Code, and ZCode.
中文:一个 canonical source 统一管理多个 Code Agent 的 Skill、MCP、Memory 与共享指令,支持预览、备份与回滚。

Quick start
npm install -g agent-trellis
trellis onboard --dry-run # preview: migration source, managed agents, MCP, memory
trellis onboard # apply — every write is backed up automatically
trellis doctor # verify state, any time
# import a GitHub Skill into Trellis canonical storage, then sync it
npx trellis add mattpocock/skills --skill loop-me --dry-runSomething went wrong? trellis rollback inverts the last run.
How it compares
| | Skills / Rules | MCP | Memory | Secret hygiene | Agents covered |
|---|---|---|---|---|---|
| ai-rules, skills-link, agent_sync | ✅ | ❌ | ❌ | ❌ | Many — but not Kiro or pi |
| skillshare, skills-hub | ✅ skills only | ❌ | ❌ | ❌ | Codex, Claude, … |
| mcp-router | ❌ | ✅ desktop router | ❌ | config in its own dashboard | — |
| MetaMCP, mcp-hub | ❌ | ✅ aggregator | ❌ | ❌ | — |
| cli-agent-orchestrator | ❌ | ❌ | ❌ | ❌ | Runs agent fleets, doesn't unify config |
| Trellis | ✅ | ✅ native config, Runtime, or hub mode | ✅ shared memory + handoffs | ✅ references only, secrets audit | Claude Code, Codex, Kiro, pi, Kimi Code, ZCode |
Sync tools stop at rules and skills. MCP routers manage servers but hold their
own config — a second source of truth (we hit real token drift with exactly
that setup). Trellis is the only one treating Skills + MCP + Memory +
instructions as one canonical system, and the only one covering Kiro and
pi. Full landscape survey: docs/research.md.
Design principles
- One canonical source, many adapters — agent-native configs are generated artifacts, never hand-edited.
- No plaintext secrets, ever — outputs hold variable references;
trellis secrets auditrejects raw values. - Verify, don't assume — every adapter claim is backed by an executed probe in isolated Docker sandboxes, never a developer's own dotfiles.
Trellis aligns with the emerging .agents Protocol
draft rather than inventing another standard.
Docs
- Overview (中文) — what it is and why
- Getting started — every command, with example output
- Architecture — what we build vs. deliberately reuse
- Research — the full competitive landscape
Status
Early, pre-1.0. All CLI commands are implemented, unit-tested, and verified against real agents in isolated containers. Known limitations are listed in Getting started; please open an issue for anything a clean-room sandbox wouldn't catch.
License
MIT — see LICENSE.
