赫菲斯托斯 是 AI Skill Hub 本期精选Agent工作流之一。综合评分 8.0 分,整体质量较高。我们强烈推荐将其纳入你的 AI 工具库,帮助提升工作效率。
赫菲斯托斯 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。
赫菲斯托斯 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 hephaestus
# 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 hephaestus
# 方式三:从源码安装(获取最新功能)
git clone https://github.com/agentlas-ai/Hephaestus
cd Hephaestus
pip install -e .
# 验证安装
python -c "import hephaestus; print('安装成功')"
# 命令行使用
hephaestus --help
# 基本用法
hephaestus input_file -o output_file
# Python 代码中调用
import hephaestus
# 示例
result = hephaestus.process("input")
print(result)
# hephaestus 配置文件示例(config.yml) app: name: "hephaestus" debug: false log_level: "INFO" # 运行时指定配置文件 hephaestus --config config.yml # 或通过环境变量配置 export HEPHAESTUS_API_KEY="your-key" export HEPHAESTUS_OUTPUT_DIR="./output"
<p align="center"> <a href="https://agentlas.cloud"> <img src="assets/agentlas-agent-lab-banner.svg" alt="Agentlas Agent Lab banner"> </a> </p>
<p align="center"> <strong>Open Agent OS for Claude Code, Codex, and Cursor: meta-agent builder, A2A Hub routing, local ontology, and governed memory/security gates.</strong> </p>
<p align="center"> Build developer-owned agents, route them across runtimes, give them project context, and let them evolve only through explicit memory, skill, verification, and security gates. </p>
<p align="center"> <a href="https://github.com/agentlas-ai/Hephaestus/releases/latest"> <img alt="Latest release" src="https://img.shields.io/github/v/release/agentlas-ai/Hephaestus?label=release"> </a> <a href="LICENSE"> <img alt="License: Apache-2.0" src="https://img.shields.io/badge/license-Apache--2.0-green"> </a> <img alt="Runtimes" src="https://img.shields.io/badge/runtimes-Claude%20Code%20%7C%20Codex%20%7C%20Gemini%20%7C%20Antigravity%20%7C%20Cursor%20%7C%20OpenCode%20%7C%20OpenClaw%20%7C%20Hermes%20%7C%20Ollama%20%7C%20Terminal-black"> </p>
<p align="center"> <a href="README.md">English</a> · <a href="README.ko.md">Korean</a> · <a href="README.zh-CN.md">中文</a> · <a href="README.ja.md">日本語</a> · <a href="README.hi.md">हिन्दी</a> </p>
<p align="center"> <a href="#paste-to-install-let-your-ai-do-it">Paste Install</a> · <a href="#quickstart">Quickstart</a> · <a href="#what-you-open-and-where-you-type">Where To Type</a> · <a href="#visual-install-guide">Visual Install Guide</a> · <a href="#what-it-builds">What It Builds</a> · <a href="#architecture">Architecture</a> · <a href="#compare">Compare</a> · <a href="https://agentlas.cloud/desktop">Desktop</a> </p>
<p align="center"> <img src="assets/agentlas-meta-agent-architecture.svg" alt="Figure 1. Agentlas Meta-Agent architecture decomposition"> </p>
<p align="center"> <sub>Figure 1. Request shaping, three builders, generated package contracts, memory curation, skill lifecycle, runtime adapters, and sync boundaries.</sub> </p>
New to terminals? Don't run anything yourself. Open any AI coding tool — Claude Code, Codex, Gemini CLI, Antigravity, or Cursor — and paste the message below into its chat box. The agent runs the installer for you, then tells you the exact command to use next:
Set up the Hephaestus Agentlas meta-agent in this workspace from this GitHub repo:
https://github.com/agentlas-ai/Hephaestus
Use the latest release/instructions, then tell me the exact six-command surface
for the tool I am using (Claude Code, Codex, Gemini CLI, Antigravity, or Cursor)
and the Agentlas native plain-language boundary. If anything fails, read the
error, fix it, and retry.
When it finishes, use /hep-build, /hep-network, /hep-cloud, /hep-search, /hep-call, or /hep-upload in external LLM hosts. In Agentlas Terminal or the Agentlas app, just describe the task; native routing should attach research or Stormbreaker behavior when the context calls for it. Prefer to run the commands yourself? Use the terminal Quickstart below.
---
Use this only when you are already inside Claude Code and want to install from the Claude chat UI instead of the OS terminal.
Claude Code chat:
/plugin marketplace add https://github.com/agentlas-ai/Hephaestus --sparse .claude-plugin claude/plugins
/plugin install hephaestus@agentlas-core-engine
/reload-plugins
/hep-build ontology
Codex does not accept /plugin marketplace add inside the app. In Codex, install from the OS terminal with codex plugin ..., then restart Codex and use /plugins only to browse or enable installed plugins. After Hephaestus is installed, run /prompts:hep-build ontology.
If a Claude chat window does not show the new command after install, restart Claude Code in that project.
Use the Claude slash-command image only when you are already inside Claude Code. For Codex, install from the OS terminal; inside the Codex app, use /plugins to browse installed plugins.
Installation also registers the agentlas Hub MCP for you — Claude Code gets it from the bundled .mcp.json, Codex/Antigravity from the one-touch install script, and Gemini CLI from the extension manifest. No separate MCP setup needed.
Hephaestus leaves behind a repository that another runtime can inspect, install, verify, and keep improving.
| You ask for | It routes to | You get |
|---|---|---|
| "Make one agent that does X" | 10-single-agent-builder | One installable worker with skills, memory contracts, runtime adapters, and verification |
| "Make a team/company for this workflow" | 20-multi-agent-team-builder | A multi-role operating team with HQ, PM Soul, Memory Curator, Policy Gate, eval, QA, and handoffs |
| "Package this existing agent/repo/workspace" | 30-agentlas-packager | A cleaned Agentlas package for Desktop import, terminal use, Codex, Claude, Gemini, or public GitHub release |
All three modes must create .agentlas/global-commands.json and report the exact global command after generation. The user should not have to infer how to run the new agent.
Generated or repaired packages can include:
AGENTS.md
CLAUDE.md
GEMINI.md
agent.md
agents/
skills/
modes/
.agentlas/
.agentlas/global-commands.json
.agents/
.claude/
.gemini/
.gemini/commands/
codex/
schemas/
templates/
scripts/verify-package.sh
scripts/public_safety_check.sh
Paste this into Claude Code, Codex, Gemini CLI, Antigravity, or Cursor. Let the AI install Hephaestus and tell you which command surface is active in that tool.
Install Hephaestus Agentlas for this workspace from this GitHub repo:
https://github.com/agentlas-ai/Hephaestus
Use the latest release/instructions. If anything errors, diagnose and fix it, retry, and confirm which command surface is active in this tool.
After it finishes, tell me the command boundary:
- Agentlas Terminal and the Agentlas app should work from plain language through native Agentlas/Hephaestus tools.
- External LLM hosts such as Claude Code, Codex, Gemini CLI, Antigravity,
Cursor, and OpenCode expose exactly six explicit commands: build, network,
cloud, search, call, and upload.
- Stormbreaker, research loadouts, and lower-level options are attached
automatically from context.
If anything fails, read the error, fix it, retry, and confirm Claude Code,
Codex, Gemini CLI, Antigravity, and Cursor registration status.
Use one of these paths on a new computer. Start with a Claude Code or Codex plugin install unless you only want the package files copied into a normal project folder.
Open your normal OS terminal, not the Claude chat box, and run:
claude plugin marketplace add https://github.com/agentlas-ai/Hephaestus --sparse .claude-plugin claude/plugins
claude plugin install hephaestus@agentlas-core-engine
Then open or restart Claude Code in the project you want to work on and type:
/reload-plugins
/hep-build ontology
If you already installed the old agentlas-meta-agent plugin and Claude says hephaestus is not found, refresh the marketplace and replace the old plugin:
curl -fsSL https://raw.githubusercontent.com/agentlas-ai/Hephaestus/main/scripts/install-all-runtimes.sh | bash
/hep-build ontology is now the Knowledge/Memory panel, not the main Agent OS surface. Use it when you want to inspect project sources, memory candidates, and reusable playbook material that routed agents may later reference. The dashboard has a left navigation rail, an Obsidian-style knowledge graph, source search, a GraphRAG query builder, a Memory Candidate Queue, and copyable commands. It creates these files in that project only:
.agentlas/ontology-inbox/
.agentlas/ontology-sources.json
.agentlas/ontology-runtime.sqlite
.agentlas/ontology-gui/index.html
It does not scan your home folder or sibling projects. Put approved company docs inside .agentlas/ontology-inbox/, then run /hep-build ontology again to refresh the dashboard.
To create agents or teams after install:
/hep-build create a research agent for SEC filing analysis
/hep-build create a customer support operations team
/hep-build package this existing Claude agent into Agentlas architecture
Claude also supports claude plugins ... as an alias, but this README uses claude plugin ... everywhere so the command shape stays consistent.
Open your normal OS terminal, not the Codex chat box, and run:
codex plugin marketplace add agentlas-ai/Hephaestus --ref v0.7.32
codex plugin add hephaestus@agentlas-core-engine
Then open or restart Codex in the project you want to work on and type:
/prompts:hep-build ontology
If Codex still shows agentlas-meta-agent or internal support names like mode-classification, refresh the marketplace and replace the old plugin:
curl -fsSL https://raw.githubusercontent.com/agentlas-ai/Hephaestus/main/scripts/install-all-runtimes.sh | bash
The Codex OS-terminal CLI command is singular: codex plugin, not codex plugins. Inside the Codex app, the slash command for the plugin browser is plural: /plugins. After plugin install, /prompts:hep-build ontology creates and opens the same project-local dashboard with graph, sources, query, memory queue, and command views:
.agentlas/ontology-gui/index.html
To create agents or teams after install:
text /hep-build create a self-evolving research agent /hep-build create a finance analyst team /hep-build package this existing Codex workspace into Agentlas architecture ```
Every generated or packaged Agentlas agent receives a global command during creation. The final handoff must include global_commands for Claude Code, Codex, Gemini CLI, generic AGENTS.md tools, and terminal use. For a team, that public command routes to the orchestrator/HQ.
Use this if you are not installing the Claude/Codex plugin and just want the repo package files in your current project. Open macOS Terminal, Linux terminal, Windows Git Bash, or WSL in that project folder and run:
curl -fsSL https://raw.githubusercontent.com/agentlas-ai/Hephaestus/main/scripts/install.sh | bash
scripts/verify-package.sh
scripts/public_safety_check.sh
Windows PowerShell:
$zip = "$env:TEMP\hephaestus-main.zip"
$extract = "$env:TEMP\hephaestus-main"
Invoke-WebRequest "https://github.com/agentlas-ai/Hephaestus/archive/refs/heads/main.zip" -OutFile $zip
Remove-Item $extract -Recurse -Force -ErrorAction SilentlyContinue
Expand-Archive $zip -DestinationPath $extract -Force
$src = Get-ChildItem $extract -Directory | Select-Object -First 1
Get-ChildItem $src.FullName -Force | Copy-Item -Destination (Get-Location) -Recurse -Force
After file install, run the ontology GUI directly:
bin/hephaestus ontology
Use this path when the claude command is available in your shell:
Use this path when the codex command is available in your shell:
Use this only after the OS-terminal codex plugin ... install:
Use this path when Codex shows a Plugins settings screen:
| Compared with | Their strength | What Hephaestus adds |
|---|---|---|
| OpenAI / Codex | Strong models and coding terminal | Portable repo contracts, .agentlas memory/package files, skills, schemas, runtime adapters, and public verification |
| Claude / Claude Code | Strong reasoning and Claude-native workflows | Claude support without becoming Claude-only; Codex, Gemini, Desktop, terminal, and AGENTS.md stay aligned |
| OpenClaw | Local identity and workspace agent loop | Visible role folders, Agentlas package contracts, public-safety checks, Desktop import, vault references, and install surfaces |
| Hermes | Persona and memory-centered local agent runtime | PM Soul, Memory Tickets, sitemap/task-bias, policy/eval/QA, and skill lifecycle evidence as files |
OpenAI and Claude are model/runtime surfaces. OpenClaw and Hermes are local-agent experiences. Hephaestus is the package layer that makes agents portable, inspectable, installable, and publishable.
高质量的开源AI工作流框架
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。
✅ Apache 2.0 — 宽松开源协议,可商用,需保留版权声明和 NOTICE 文件,含专利授权条款。
经综合评估,赫菲斯托斯 在Agent工作流赛道中表现稳健,质量优秀。如果你已有明确的使用需求,可以直接上手体验;如果还在评估阶段,建议对比同类工具后再做决策。
| 原始名称 | Hephaestus |
| Topics | AI工作流agent |
| GitHub | https://github.com/agentlas-ai/Hephaestus |
| License | Apache-2.0 |
| 语言 | Python |
收录时间:2026-06-28 · 更新时间:2026-06-28 · License:Apache-2.0 · 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