经 AI Skill Hub 精选评估,Trinity AI工作流 获评「强烈推荐」。这款Agent工作流在功能完整性、社区活跃度和易用性方面表现出色,AI 评分 8.0 分,适合有一定技术背景的用户使用。
Trinity AI工作流 是一套完整的 AI Agent 自动化工作流方案。通过可视化的节点编排,将复杂的多步骤任务拆解为清晰的自动化流程,实现全程无人值守的智能处理。支持与数百种外部服务和 API 无缝集成,适合构建数据处理管线、业务自动化和 AI 辅助决策系统。
Trinity AI工作流 是一套完整的 AI Agent 自动化工作流方案。通过可视化的节点编排,将复杂的多步骤任务拆解为清晰的自动化流程,实现全程无人值守的智能处理。支持与数百种外部服务和 API 无缝集成,适合构建数据处理管线、业务自动化和 AI 辅助决策系统。
# 方式一:pip 安装(推荐)
pip install trinity
# 方式二:虚拟环境安装(推荐生产环境)
python -m venv .venv
source .venv/bin/activate # Windows: .venv\Scripts\activate
pip install trinity
# 方式三:从源码安装(获取最新功能)
git clone https://github.com/Abilityai/trinity
cd trinity
pip install -e .
# 验证安装
python -c "import trinity; print('安装成功')"
# 命令行使用
trinity --help
# 基本用法
trinity input_file -o output_file
# Python 代码中调用
import trinity
# 示例
result = trinity.process("input")
print(result)
# trinity 配置文件示例(config.yml) app: name: "trinity" debug: false log_level: "INFO" # 运行时指定配置文件 trinity --config config.yml # 或通过环境变量配置 export TRINITY_API_KEY="your-key" export TRINITY_OUTPUT_DIR="./output"
<p align="center"> <a href="https://www.ability.ai/trinity"> <img src="docs/assets/trinity-hero.webp" alt="Trinity — Run agents like infrastructure" width="720" /> </a> </p>
<p align="center"> <a href="#quick-start"><strong>Quick start</strong></a> · <a href="#your-whole-fleet-in-one-console"><strong>See it</strong></a> · <a href="https://youtu.be/ivljtZqsxeo"><strong>Demo</strong></a> · <a href="#documentation"><strong>Docs</strong></a> · <a href="#community--support"><strong>Community</strong></a> · <a href="https://www.ability.ai/trinity"><strong>Website</strong></a> · <a href="https://www.ability.ai/workshops"><strong>Free workshops</strong></a> </p>
<p align="center"> <a href="https://github.com/abilityai/trinity/stargazers"><img src="https://img.shields.io/github/stars/abilityai/trinity?style=flat" alt="Stars"></a> <a href="LICENSE"><img src="https://img.shields.io/badge/license-Apache%202.0-blue.svg" alt="License: Apache 2.0"></a> <a href="https://pypi.org/project/trinity-cli/"><img src="https://img.shields.io/pypi/v/trinity-cli?label=CLI&color=blue" alt="CLI"></a> <img src="https://img.shields.io/badge/python-3.11+-blue.svg" alt="Python"> <img src="https://img.shields.io/badge/vue-3.x-green.svg" alt="Vue"> <img src="https://img.shields.io/badge/docker-required-blue.svg" alt="Docker"> </p>
---
abilityai/abilities is the canonical workflow for building and managing autonomous agents with Claude Code — most Trinity usage workflows are defined there as plugins.
Abilities structures agent work as a four-step lifecycle:
1. Scaffold 2. Develop 3. Deploy 4. Iterate
/create-agent:* /agent-dev:create-playbook /trinity:connect (once) /trinity:sync
/agent-dev:add-memory /trinity:onboard /trinity:loop
/agent-dev:add-backlog (or: trinity deploy .) /create-agent:adjust
Scaffold — wizards like /create-agent:prospector or /create-agent:custom produce a fully configured, Trinity-compatible agent: CLAUDE.md, initial skills, template.yaml, a metrics dashboard, and an onboarding tracker.
Develop — /agent-dev:create-playbook adds capabilities, /agent-dev:add-memory adds persistence (file index, knowledge graph, JSON state, or workspace tracking), /agent-dev:add-backlog wires a GitHub Issues workflow.
Deploy — /trinity:connect once per instance, then /trinity:onboard per agent (or trinity deploy . via the CLI).
Iterate — /trinity:sync pushes and pulls changes, /trinity:loop runs bounded server-side task loops, /create-agent:adjust audits the agent against best practices and applies improvements.
The 5 plugins:
| Plugin | What it does |
|---|---|
| **create-agent** | Agent scaffolding: a /create-agent:create discovery entry point + 12 wizards (prospector, chief-of-staff, webmaster, recon, receptionist, ghostwriter, kb-agent, doctor, website, custom, clone, adjust) |
| **agent-dev** | Extend existing agents: playbooks, memory systems, git-sync hooks, GitHub backlog workflow, grooming, sprints, agent-owned pipelines, autonomous work loops |
| **trinity** | The platform workflow: connect, onboard, sync, loop, create-dashboard, deploy-new-instance |
| **dev-methodology** | Documentation-driven development for any codebase: implementation, testing, security audits, PR validation, release, architecture/schema/config validation |
| **utilities** | Ops & productivity: incident investigation, safe deployment, Docker ops, batch processing, conversation export |
```bash
brew install websocat jq
./scripts/deploy/build-base-image.sh
Most of the Trinity workflow lives in the abilities plugin marketplace — Claude Code plugins covering the full agent lifecycle: scaffold, develop, deploy, iterate. You need the instance from Phase A (localhost or remote) and Claude Code.
```bash
/plugin marketplace add abilityai/abilities /plugin install trinity@abilityai /plugin install create-agent@abilityai
/trinity:onboard
Trinity CLI — terminal-first alternative to the plugin workflow:
pip install trinity-cli # or: brew install abilityai/tap/trinity-cli
trinity init # connect: instance URL + email code → JWT + MCP key
cd my-agent/ && trinity deploy . # package, upload, create + start the agent
trinity chat my-agent "Hello, what can you do?"
trinity logs my-agent # container logs
trinity health fleet # fleet overview
Redeploys (trinity deploy . again), multi-instance profiles, and the full command reference: CLI documentation.
Web UI — open the Trinity web UI → Create Agent → pick a template (blank, built-in, or github:org/repo@branch) → configure credentials → start chatting.
Multi-Agent System — define a fleet in one YAML manifest and deploy via MCP (mcp__trinity__deploy_system) or the REST API. See Multi-Agent Systems below.
/plugin marketplace add abilityai/abilities /plugin install trinity@abilityai /plugin install create-agent@abilityai ```
See the abilities repository for full plugin documentation and skill references.
docker compose build backend docker compose up -d backend ```
Two phases: stand up an instance (Phase A), then build and deploy agents to it from Claude Code (Phase B).
| Guide | Use Case |
|---|---|
| [Trinity Compatible Agent Guide](docs/TRINITY_COMPATIBLE_AGENT_GUIDE.md) | **Single agents** — Template structure, CLAUDE.md, credentials, platform injection |
| [Multi-Agent System Guide](docs/MULTI_AGENT_SYSTEM_GUIDE.md) | **Multi-agent systems** — Architecture patterns, shared folders, coordination, deployment |
cp .env.example .env
export TRINITY_API_KEY="trinity_mcp_xxx"
| Variable | Required | Description |
|---|---|---|
SECRET_KEY | Yes | JWT signing key (generate with openssl rand -hex 32) |
ADMIN_PASSWORD | Yes | Admin password for admin login |
DATABASE_URL | No | PostgreSQL backend (recommended for production); unset → SQLite default (#300) |
ANTHROPIC_API_KEY | No | For Claude-powered agents (can also be set via Settings UI) |
GITHUB_PAT | No | GitHub PAT for cloning private template repos |
OTEL_ENABLED | No | Enable OpenTelemetry metrics export (default: false) |
EMAIL_PROVIDER | No | Email provider: console (dev), smtp, sendgrid, resend |
EXTRA_CORS_ORIGINS | No | Additional CORS origins |
See .env.example for the complete list.
curl -X POST http://localhost:8000/api/systems/deploy \ -H "Content-Type: application/json" \ -d '{"manifest": "...", "dry_run": false}' ```
See the Multi-Agent System Guide for architecture patterns and best practices.
Trinity includes an MCP server for external orchestration of agents:
{
"mcpServers": {
"trinity": {
"type": "streamable-http",
"url": "http://localhost:8080/mcp",
"headers": {
"Authorization": "Bearer YOUR_API_KEY"
}
}
}
}
Trinity 是一个用于构建和管理自主代理的工具集。它提供了 5 个专注的插件,涵盖代理的整个生命周期,从创建和引导到部署、调度和持续运维。
Abilities 是一个代理开发工具集,提供了 5 个专注的插件,涵盖代理的整个生命周期。它提供了 12 个向导,帮助用户创建和管理自主代理。
Trinity 需要 Docker 和 Docker Compose v2+,以及 Anthropic API 密钥(用于 Claude-powered 代理)或 Google API 密钥(用于 Gemini-powered 代理)。
要开始使用 Trinity,需要安装 CLI,使用 pip 或 brew 安装。然后,需要创建一个 Trinity 实例,配置环境,设置 MCP API 密钥,部署代理。
使用 Trinity,需要进入实例 URL,设计兼容的代理,配置环境,设置 MCP API 密钥,部署代理。Trinity 提供了多种部署方式,包括 Docker 和 pip。
Trinity 的配置包括设置 MCP API 密钥,配置环境,设置关键参数。用户需要设置 TRINITY_API_KEY,TRINITY_MCP_URL 等环境变量。
Trinity 提供了 REST API,用户可以使用 curl 命令发送请求,部署代理,管理系统。API 文档详细说明了每个 API 的使用方法和参数。
Trinity 的工作流包括创建代理,部署代理,管理系统。用户可以使用 Trinity CLI,部署代理,管理系统,查看系统状态。
高质量的AI工作流平台
该工具使用 NOASSERTION 协议,商用场景请仔细阅读协议条款,必要时咨询法律意见。
AI Skill Hub 为第三方内容聚合平台,本页面信息基于公开数据整理,不对工具功能和质量作任何法律背书。
建议在沙箱或测试环境中充分验证后,再部署至生产环境,并做好必要的安全评估。
📄 NOASSERTION — 请查阅原始协议条款了解具体使用限制。
AI Skill Hub 点评:Trinity AI工作流 的核心功能完整,质量优秀。对于自动化工程师和运维人员来说,这是一个值得纳入个人工具库的选择。建议先在非生产环境试用,再逐步推广。
| 原始名称 | trinity |
| 原始描述 | 开源AI工作流:Deep Agent Orchestration Platform — Sovereign infrastructure for deploying, orch。⭐96 · Python |
| Topics | AI工作流Python |
| GitHub | https://github.com/Abilityai/trinity |
| License | NOASSERTION |
| 语言 | Python |
收录时间:2026-06-03 · 更新时间:2026-06-05 · License:NOASSERTION · AI Skill Hub 不对第三方内容的准确性作法律背书。
选择 Agent 类型,复制安装指令后粘贴到对应客户端