Hephaestus

Name: Hephaestus
Author: agentlas-ai

Verified

Agent OS: keep specialist agents in a hub, spin up a temporary orchestrator per task. Local-first, works with any model.

99stars

17forks

Python

Installation

# Add to your Claude Code skills
git clone https://github.com/agentlas-ai/Hephaestus

Getting Started

Guides for using ai agents skills like Hephaestus.

Caveman: Cut Claude Token Use by 65%
How agent-side prompt compression works, when to use it, and when not to.
What is an AI Skills Marketplace?
Definitions, how marketplaces work, and how to choose between them in 2026.
Getting Started with AI Skills

Security ReportVerified

Last scanned: 6/22/2026

{
  "issues": [
    {
      "file": ".agents/skills/hephaestus-cloud/SKILL.md",
      "line": 46,
      "type": "remote-install",
      "message": "Install command (remote install script piped to a shell — review the source before running): \"curl -fsSL https://raw.githubusercontent.com/agentlas-ai/Hephaestus/main/scripts\"",
      "severity": "medium"
    },
    {
      "file": ".agents/skills/hephaestus-network/SKILL.md",
      "line": 49,
      "type": "remote-install",
      "message": "Install command (remote install script piped to a shell — review the source before running): \"curl -fsSL https://raw.githubusercontent.com/agentlas-ai/Hephaestus/main/scripts\"",
      "severity": "medium"
    }
  ],
  "status": "PASSED",
  "scannedAt": "2026-06-22T09:51:13.974Z",
  "npmAuditRan": true,
  "pipAuditRan": true,
  "promptInjectionRan": true
}

README.md

Frequently Asked Questions

What is Hephaestus?

Hephaestus is an open-source ai agents skill for AI coding assistants such as Claude Code, Codex CLI, and ChatGPT, built by agentlas-ai. Agent OS: keep specialist agents in a hub, spin up a temporary orchestrator per task. Local-first, works with any model. It has 99 GitHub stars.

Is Hephaestus safe to use?

Yes. Hephaestus passed SkillsLLM's automated security scan — a dependency vulnerability audit plus prompt-injection heuristics — with no high-severity issues. You can read the full report in the Security Report section on this page.

How do I install Hephaestus?

Clone the repository with "git clone https://github.com/agentlas-ai/Hephaestus" and add it to your Claude Code skills directory (see the Installation section above).

What programming language is Hephaestus written in?

Hephaestus is primarily written in Python. It is open-source under agentlas-ai on GitHub, so you can review or fork the full source.

Are there alternatives to Hephaestus?

Yes. SkillsLLM lists many other AI Agents skills you can browse and compare side by side. Open the AI Agents category from the badge at the top of this page, or use the Related Skills and comparison links further down to weigh Hephaestus against similar tools.

Agentic AI for Beginners

Build your first AI agent from scratch - tool use, ReAct pattern, memory, deployment

41 minBeginner

Comments (0)

to leave a comment.

No comments yet. Be the first to share your thoughts!

Related Skills

superpowers

by obra

An agentic skills framework & software development methodology that works.

234,966

zexus Anti-Autoresearch

Quickstart

curl -fsSL https://raw.githubusercontent.com/agentlas-ai/Hephaestus/main/scripts/install-all-runtimes.sh | bash

This installs the neutral runner and registers command adapters for Claude Code, Codex, Gemini CLI, Antigravity, and Cursor. Prefer a plugin, a manual copy, or letting your AI install it for you? See All Install Methods.

The Agent OS Era

The industry has evolved past stateless, ad-hoc "chatbots with tools". With Google and major AI labs reframing developer strategies around Agent Operating Systems (such as the Antigravity orchestration platform and Gemini Spark daemon processes), AI agents have officially become first-class operating-system primitives—long-lived, stateful processes with distinct identities, relational memory systems, security permissions, and native tool-calling environments.

This shifts the critical engineering question for teams: Whose operating system does your workforce run on?

If your agents are tightly coupled to a single model provider's proprietary API, your organizational memory, custom tools, and task-specific logic are effectively locked into that vendor's ecosystem.

Hephaestus is the independent, model-agnostic kernel. It is not an agent framework or an API wrapper. It is a local-first Agent Operating System—a unified execution substrate that compiles, schedules, and governs portable agent processes across any host runtime. Swap the underlying reasoning engine; preserve the entire workforce.

Hephaestus maps directly to classical operating system concepts:

OS Abstraction	Implementation in Hephaestus
Kernel / Policy Gate	Deterministic router + security gates. Every routing action yields an auditable receipt; tool execution permissions are strictly sandboxed and enforced by the host runtime.
Processes / Threads	Independent agents and multi-agent teams compiled as packages with explicit, typed contracts (Routing Cards, anti-scopes, memory boundaries, and verification shims).
Process Scheduler	Network 2.0 routing (local-first, quality-gated, and benchmark-gated dispatch) combined with Stormbreaker's parallel execution fabric and append-only run journals.
Memory Management (MMU)	Two-boundary governed memory: local project memory remains isolated on the machine, while durable promotions are gated by a local Memory Curator.
Virtual File System	Production Ontology Runtime: local-first source ingestion, CJK trigram FTS5 search, hybrid Reciprocal Rank Fusion, and GraphRAG retrieval.
Inter-Process Call (IPC)	A2A Agent Card Boundary (cryptographic import/export and caller-gating) + Model Context Protocol (MCP) tool registrations.
Package Manager	Agentlas Hub & Cloud: compile, publish, version, and share agents with built-in quality gates.
Shell Interface	A small, unified six-command CLI in external client runtimes; plain-language intent routing in native Agentlas shells.
Process Initialization	Meta-Agent Factory with an integrated Briefing Interview Gate—specifying agent parameters before compiling code.

New In v1.1.0 — The Briefing Interview Engine

Agents generated from vague, single-sentence prompts fail under real-world edge cases. Hephaestus v1.1.0 positions task specification as a first-class OS service through the Briefing Interview Engine:

Quantitative Ambiguity Gates: The compilation scheduler evaluates prompt clarity across four key vectors (Goal, Constraints, Scope, Context). The build process is strictly gated until the ambiguity score passes a numeric threshold (ambiguity score $\le 0.2$, with per-dimension safety floors). Clear prompts bypass the interview loop entirely via a budget system that caps questions for trivial tasks.
Lens-Driven System Analysis: Clarifying questions are dynamically sourced from a structured lens table (Scope, Intent, Challenge, System Architecture) focusing on critical routing indicators: anti-scope bounds (what the agent must NOT do), verifiable acceptance criteria, and exit conditions.
The Work Brief: Resolved details are frozen into .agentlas/work-brief.json—recording the validated goal, concrete constraints, an assumption ledger with source tags, and the metadata ambiguity score.
Contextual In-Flight Briefs: The CLI tool cards migrate automatically maps brief details directly to triggers and anti-triggers on the agent's routing card. Running route --brief propagates this brief to all Stormbreaker execution packets, ensuring constraints and exit conditions govern parallel subprocesses across the entire lifecycle.
Enhanced Routing Discrimination: Prevents same-topic/different-intent collision (e.g., a security agent intercepting a deployment prompt) via double-sided gating: interview-validated anti-triggers on the routing card, and low-confidence LLM re-ranking escalation inside the router.

All Install Methods

Paste to Boot (Let Your AI Do It)

Paste this into Claude Code, Codex, Gemini CLI, Antigravity, or Cursor:

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:
- Agentlas Terminal / Desktop route plain language natively.
- External LLM hosts expose exactly six commands: build, network, cloud,
  search, call, upload.

Fresh macOS Check

xcode-select --install   # Command line tools (skip if already installed)
git --version            # Confirm git is available

One Terminal Command for All Runtimes

curl -fsSL https://raw.githubusercontent.com/agentlas-ai/Hephaestus/main/scripts/install-all-runtimes.sh | bash

This installs the neutral runner at ~/.agentlas/runtime/current/bin/hephaestus and registers the command adapters for Claude Code, Codex, Gemini CLI, Antigravity, and Cursor. The installer verifies each runtime surface after registration.

Per-Runtime Plugin Drivers

From your OS terminal:

claude plugin marketplace add https://github.com/agentlas-ai/Hephaestus --sparse .claude-plugin claude/plugins
claude plugin install hephaestus@agentlas-core-engine

Note: Claude Code also supports claude plugins ... as an alias, but this README uses the singular claude plugin ... for consistency.

From your OS terminal:

codex plugin marketplace add agentlas-ai/Hephaestus --ref v1.1.0
codex plugin add hephaestus@agentlas-core-engine

Note: Codex does not accept /plugin marketplace add inside the app — run the two commands above in your OS terminal. The OS-terminal CLI command is singular (codex plugin); inside the Codex app, the plugin browser slash command is plural (/plugins). After install, /prompts:hep-build is the in-app entry.

Clone the repo and copy AGENTS.md, agent.md, agents/, skills/, modes/, schemas/, templates/, and .agentlas/ into your workspace. Runtime folders (.claude/, codex/, .gemini/, .agents/) function as adapters over the same canonical core.

Just talk: After ins