agentlas-meta-agent

Turn one rough agent idea into an installable Agentlas agent or team repository.

Build one specialist, assemble a multi-agent team, or package an existing Claude/Codex/OpenClaw/Hermes workspace into a public-safe Agentlas repo.

English · 한국어 · 中文 · 日本語 · हिन्दी

Quickstart · Where To Type · Visual Install Guide · What It Builds · Architecture · Compare · Desktop

_{Figure 1. Request shaping, three builders, generated package contracts, memory curation, skill lifecycle, runtime adapters, and sync boundaries.}

Quickstart

There are three install paths. Use 1 + 3 when you want the full Agentlas runtime. Use 2 only when you want this package installed directly into Claude Code, Codex, or a plain project folder.

1. Install Agentlas Terminal

Agentlas Terminal is installed from Agentlas Desktop. First install Desktop, then open:

Agentlas Desktop -> Settings -> Use from the terminal (`agentlas` CLI) -> Install CLI

After that, open your normal terminal and run agentlas.

macOS Terminal

arch=$([ "$(uname -m)" = "arm64" ] && echo arm64 || echo x64)
curl -fL "https://agentlas.cloud/api/desktop/download?arch=${arch}" -o Agentlas.dmg
open Agentlas.dmg

Windows PowerShell

$r = Invoke-RestMethod https://api.github.com/repos/agentlas-ai/agentlas-desktop/releases/latest
$u = ($r.assets | Where-Object { $_.name -like '*Windows-x64-Setup.exe' }).browser_download_url
Invoke-WebRequest $u -OutFile "$env:TEMP\AgentlasSetup.exe"
Start-Process "$env:TEMP\AgentlasSetup.exe"

Linux terminal, AppImage

url=$(curl -fsSL https://api.github.com/repos/agentlas-ai/agentlas-desktop/releases/latest \
  | grep -o 'https://[^"]*Linux-x64\.AppImage' | head -1)
curl -fL "$url" -o Agentlas.AppImage
chmod +x Agentlas.AppImage
./Agentlas.AppImage

Linux terminal, Debian/Ubuntu

url=$(curl -fsSL https://api.github.com/repos/agentlas-ai/agentlas-desktop/releases/latest \
  | grep -o 'https://[^"]*Linux-x64\.deb' | head -1)
curl -fL "$url" -o agentlas.deb
sudo dpkg -i agentlas.deb

After installing the CLI from Desktop Settings:

agentlas list
agentlas run agentlas-meta-agent "Package this workflow for Agentlas"
agentlas ontology

agentlas ontology activates a project-local knowledge vault in the current
folder. It creates .agentlas/ontology-inbox/, .agentlas/ontology-sources.json,
and .agentlas/ontology-runtime.sqlite. It never scans your home folder or
neighboring projects. Put approved txt, md, json, or csv files in the
inbox, or explicitly register a source:

agentlas ontology add /path/to/company-docs --kind company --scope private

Standalone Claude/Codex plugin installs include the public architecture and
verification files, but the normal user activation surface for ontology sync is
Agentlas Desktop or the agentlas terminal CLI.

2. Install agentlas-meta-agent standalone

Simple file install

Open macOS Terminal, Linux terminal, Windows Git Bash, or WSL in the project folder where you want the package files installed:

curl -fsSL https://raw.githubusercontent.com/agentlas-ai/Hephaestus/v0.1.6/scripts/install.sh | bash
scripts/verify-package.sh
scripts/public_safety_check.sh

Windows PowerShell:

$zip = "$env:TEMP\agentlas-meta-agent-v0.1.6.zip"
$extract = "$env:TEMP\agentlas-meta-agent-v0.1.6"
Invoke-WebRequest "https://github.com/agentlas-ai/Hephaestus/archive/refs/tags/v0.1.6.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

Claude Code plugin install

Marketplace registration and plugin installation are separate steps. The marketplace command only registers where Claude Code can find this repo. The install command actually installs the plugin. Reload after install.

Inside a Claude Code chat, type:

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

From your OS terminal with the claude CLI available:

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

Expected result after reload:

✓ Installed agentlas-meta-agent. Run /reload-plugins to apply.
Reloaded: 1 plugin · 0 skills · 9 agents · 0 hooks · 0 plugin MCP servers · 0 plugin LSP servers

Codex plugin install

Inside a Codex chat, type:

/plugin marketplace add agentlas-ai/Hephaestus --ref v0.1.6
/plugin install agentlas-meta-agent@agentlas-core-engine
/reload-plugins
/plugin list

From your OS terminal with the codex CLI available:

codex plugin marketplace add agentlas-ai/Hephaestus --ref v0.1.6
codex plugin list
codex plugin add agentlas-meta-agent@agentlas-core-engine
codex plugin list

If a Codex session was already open, run /reload-plugins or start a new session.

3. Install Agentlas Desktop

Open this page in your browser:

https://agentlas.cloud/desktop

Desktop gives you the visual Agentlas surface: local projects, agents, teams, Apps, vault references, runtime selection, built-in Core Engine Meta-Agent routing, and the agentlas CLI installer.
It also shows the per-project Ontology panel with inbox, source registration,
and the safe no-home-scan policy.

Visual Install Guide

Use the slash-command images when you are already inside a Claude Code or Codex chat. Use the CLI images when you are in macOS Terminal, Windows PowerShell, Linux terminal, Git Bash, or WSL.

Claude Code chat

Type these commands directly into Claude Code:

Claude CLI from your OS terminal

Use this path when the claude command is available in your shell:

Codex chat

Type these commands directly into Codex:

Codex Desktop or IDE Extension

Use this path when Codex shows a Plugins settings screen:

Codex CLI from your OS terminal

Use this path when the codex command is available in your shell:

What You Open And Where You Type

What It Builds

agentlas-meta-agent leaves behind a repository that another runtime can inspect, install, verify, and keep improving.

Generated or repaired packages can include:

AGENTS.md
CLAUDE.md
GEMINI.md
agent.md
agents/
skills/
modes/
.agentlas/
.agents/
.claude/
.gemini/
codex/
schemas/
templates/
scripts/verify-package.sh
scripts/public_safety_check.sh

Architecture

The public core is the architecture and foldering contract. Runtime-specific folders are adapters over the same core, not separate sources of truth.

The default export state is conservative. Generated skills are searchable candidate metadata, not automatically promoted runtime behavior. A local Curator must see execution evidence, sealed holdout or replay proof, rollback coverage, and workspace policy approval before a skill becomes first-class recall.

Production Ontology Runtime

For knowledge-heavy personal or company agents, Hephaestus now ships a real local-first ontology runtime under ontology/ with the executable CLI bin/ontology. It turns approved files into an agent-readable source archive, chunk store, full-text index, vector index, ontology graph, GraphRAG result, Memory Curator candidate ticket, and Agent Working Memory cache.

The Super Ontology files under .agentlas/ remain the safety/governance layer. They define the source-lineage, privacy, task-coverage, causal, consensus, and memory-write gates around the runtime. The runtime is the implementation layer.

Supported ingest formats:

The storage default is SQLite at .agentlas/ontology-runtime.sqlite, ignored by Git. The schema includes sources, source_lineage, chunks, chunk_fts, entities, entity_aliases, relations, memory_candidates, memory_candidate_events, working_memory, runtime_adapters, and schema_migrations.

Basic local run:

bin/ontology ingest examples/ontology-corpus --scope internal
bin/ontology query "Project Helios Memory Curator" --agent verifier
bin/ontology graph entity "Project Helios"
bin/ontology memory candidates
bin/ontology working-memory read --agent verifier
bin/ontology verify

The query response includes relevant chunks, related entities, relation edges, evidence refs, source spans, confidence, Memory Curator candidate suggestions, and optional Agent Working Memory writes. It is not a vector-only result.

The runtime stack is layered:

Memory Curator flow:

bin/ontology memory candidates
bin/ontology memory decide <ticket-id> approve --reason "Curator accepted source-backed fact"
bin/ontology memory decide <ticket-id> quarantine --reason "Needs source owner review"

Approval records review state but still does not write durable memory. The Memory Curator owns durable promotion. Agent Working Memory is intentionally a cache, not a source of truth.

See docs/ontology-runtime.md for the schema, adapter behavior, storage commands, and verification coverage.

Why Agentlas Desktop And Terminal Make It Better

Desktop and Terminal make this package useful beyond a static prompt:

• Desktop shows the agent/team structure, local projects, Apps, vault references, and runtime choices.
• Terminal runs the same package from a shell with agentlas.
• The built-in Core Engine Meta-Agent path means fresh Desktop/Terminal installs can create or package agents without a separate standalone plugin install.
• Standalone Claude/Codex install is still useful when you want this package directly inside those runtimes.

Compare

OpenAI and Claude are model/runtime surfaces. OpenClaw and Hermes are local-agent experiences. agentlas-meta-agent is the package layer that makes agents portable, inspectable, installable, and publishable.

Use It

Single agent:

/meta-agent Create a research agent for SEC filing analysis.
Package it for Codex, Claude Code, Gemini, and Agentlas Desktop.

Multi-agent team:

Use agentlas-meta-agent.
Build a customer-support operations team with PM Soul, Memory Curator, Policy Gate, QA, eval, and public-safe release checks.

Package an existing workspace:

Package this local OpenClaw/Hermes-style workspace into Agentlas architecture.
Keep private notes, machine paths, raw logs, and secrets out of the public repo.

Docs By Goal

Public Safety Boundary

This repo intentionally does not include hosted Agentlas billing/account logic, production credentials, customer data, raw private logs, raw transcripts, desktop keychain storage, local database implementation, or private deployment configuration.

Public output packages should not include local machine paths, API keys, tokens, private keys, service-account JSON, .env secrets, private research notes, raw chat transcripts, customer logs, hosted billing/account/OAuth internals, or desktop storage internals.

Contributing

Before opening a PR or publishing a release, run:

scripts/verify-package.sh
scripts/verify-ontology-runtime.sh
scripts/public_safety_check.sh

License

Apache-2.0. See LICENSE.