agentlas

AGENTLAS MODEL 01 · AGENT OS

HEPHAESTUS

Agent OS inside Agentlas

Open Agent OS for Claude Code, Codex, and Cursor.

Meta-agent builder, A2A Hub router, Stormbreaker execution gates, project ontology, and memory/security gates in one local-first engine. Hephaestus builds agents, routes them across runtimes, gives them governed project context, and lets them improve only through verified memory and skill promotion.

GitHubSee how it works
curl -fsSL https://raw.githubusercontent.com/agentlas-ai/Hephaestus/v0.7.2/scripts/install-all-runtimes.sh | bash
Meta-agent builderA2A Hub routingStormbreaker gatesLocal ontologyMemory + security gates

Hephaestus is not a prompt generator. It is an operating layer for agents that have to build, route, verify, remember, and evolve inside real developer workspaces.

“An agent OS is the control plane around what agents may build, call, remember, and ship.”

HOW THE ENGINE WORKS

Five operating layers for developer-owned agents.

Hephaestus combines a meta-agent builder, A2A routing, Stormbreaker, local ontology, and governed memory/security gates so agent creation becomes an inspectable operating system instead of a one-off prompt.

Diagram: an intent moving through classification and clarification into an agent architecture.
01 · Meta-agent builderintent → agent architecture
01 · Meta-agent builder

Turn intent into an agent architecture.

Hephaestus classifies the request, asks the missing setup questions, and emits the right shape: one agent, a multi-agent team, or a clean package with runtime adapters.

02 · A2A Hub router

Route work across local agents and the Hub.

Hephaestus Network reads routing cards, prefers local agents, falls back to Agentlas Hub with redacted keywords when allowed, and writes receipts so every agent-to-agent handoff is traceable.

03 · Project ontology

Give agents a working map of the project.

The ontology runtime indexes approved project sources into local graph and search state, so agents can query context, memory, and source lineage without sweeping unrelated folders.

04 · Stormbreaker

Make serious agent work auditable.

Stormbreaker adds scope locks, failure-memory checks, verifier-first plans, bounded evidence loops, review gates, outcome ledgers, and final proof before substantial work can be called done.

05 · Memory and gates

Let agents evolve under control.

Memory admission, skill trials, security scans, and verification gates decide what an agent is allowed to keep, learn, call, or publish across Claude Code, Codex, Gemini CLI, Agentlas Desktop, and AGENTS.md.

WHAT'S INSIDE

The agent OS, exposed as files, gates, and receipts.

01

Meta-agent builder

Classifies the request and builds the right agent, team, or package shape

02

A2A Hub router

Routes requests through local cards first, then approved Agentlas Hub fallback

03

Stormbreaker

Hardens execution with scope locks, failure memory, verifier-first plans, and final proof

04

Ontology runtime

Turns approved project sources into local graph, search, and source-lineage context

05

Memory and self-evolution

Controls which memories, skills, and habits agents are allowed to keep

06

Security and release gates

Runs scans, verification, and publish checks before anything ships

STORMBREAKER RESULTS

Operational stability, shown as a control layer.

Stormbreaker is not a model replacement. It wraps the coding agent with scope locks, failure memory, verifier-first planning, evidence loops, review gates, and final proof so the run is harder to abandon halfway through.

Macro operational stability99.26

Macro operational stability

GPT 5.5
76.48
Network
92.22
Stormbreaker
99.26

Micro operational stability

GPT 5.5
76.67
Network
91.85
Stormbreaker
98.52

Holdout stability

GPT 5.5
80.00
Network
91.67
Stormbreaker
100.00

Stress stability

GPT 5.5
73.33
Network
93.33
Stormbreaker
100.00
  1. 01Scope lock
  2. 02Failure memory
  3. 03Verifier-first plan
  4. 04Evidence loop
  5. 05Review gate
  6. 06Final proof
6/6process-aware metric variants kept the ladder
9/9paired local task units over GPT 5.5
8/9paired local task units over the network baseline

WHY IT MATTERS

What makes it useful is control over the agent lifecycle.

Architecture is visible

Agents, skills, memory contracts, and runtime adapters stay in plain files you can inspect, review, and change.

Routing is accountable

Agent-to-agent routing uses cards, approval boundaries, and receipts instead of silent black-box handoffs.

Execution is hardened

Stormbreaker turns scope, verification, failures, review, and final evidence into an operating contract.

Memory is governed

Project context is admitted through local ontology and memory rules, not by letting agents wander through every folder.

Evolution has gates

New skills, durable memory, and publishable packages have to pass trials, security scans, and verification before they stick.

VISION

An Agent OS for local-first AI work.

Agentlas is not only about creating agents. Hephaestus keeps the agent architecture, A2A routing, Stormbreaker execution gates, ontology, memory, and safety gates in plain structures you can inspect, change, and run on GitHub and on your own computer.

See the public code on GitHub
Hephaestus - Open Agent OS for Claude Code, Codex, and Cursor