agentlas-browser

English · 한국어 · 中文 · 日本語 · हिन्दी

Agentlas OS

An open-source AI agent OS inspired by OpenAI Dots, Meta Muse, Claude Duet, Nous Hermes, and Mem0.

Built to lead entire projects rather than isolated prompts. Model-agnostic (BYOM) and native to Claude Code, Codex, Cursor, Antigravity, and Agentlas Desktop.

Most agent products take one of two approaches. Some are prompt loops that report a task as done without checking the result. Others run each agent in a virtual machine, in the cloud or on your computer, apart from your files, credentials, and tools; a local VM also holds memory and disk while it runs. Agentlas OS takes neither approach. It runs no VM: agents work in the terminal, files, and tools already on your machine, and a task is complete only after an independent verifier accepts its execution receipt.

Install Agentlas Desktop via the button below for the full runtime and mobile pairing (One), or attach this repository's runtime packs directly to Claude Code, Codex, or Cursor.

macOS · Windows · Linux · Android · iOS coming soon 12,000+ desktop downloads · Free to download, runs on your own AI plan or key · Apache-2.0

Website · Agent Hub · Discord · Developers ↓

Architectural Foundations

Instead of stitching together single-purpose wrappers, Agentlas OS combines five agent patterns in one local-first runtime.

• Persistent autonomous execution (inspired by OpenAI Dots): Goals survive across sessions. Work resumes from the last checkpoint, and a step counts as complete only after an independent verifier checks its execution receipt.
• Domain-complete workflows (inspired by Meta Muse): Work runs to a finished deliverable across personal operations (One), investment research that keeps the inputs behind each calculation (Finance), and literature and molecular research (Science).
• Desktop execution, mobile decisions (inspired by Claude Duet): Execution stays on your computer, where your files and tools are. Decision points reach your phone as question cards, and the desktop continues after you answer.
• Portable skills and A2A packaging (inspired by Nous Hermes): 40-session-agent-builder compiles the procedure and checks from a working session into a package, and 30-agentlas-packager packages existing agents. Every package carries an A2A Agent Card and installs on any supported host.
• Scoped memory governance (inspired by Mem0): memory-hooks, context maps, and project indexes are scoped per project. Workers emit memory events; a Memory Curator validates, redacts, and deduplicates them, and a Policy Gate approves promotion to shared team memory.

Elsewhere, a split task is a prompt. Here, it is a job opening.

Elsewhere, an agent that splits a task writes sub-prompts to itself. In Agentlas OS, each part of the work becomes a job opening filled by a specialist agent, and the work runs on your own machine.

Give Agentlas OS one objective. The Hephaestus engine decomposes it, searches for specialists on your computer, in your private Agent Cloud, and on the public Hub, and does not mark the work complete until an independent verifier checks the execution receipt.

Hephaestus: decompose, recruit, verify

1. Decompose

A goal becomes a task graph. Each task states its inputs and outputs, the tools and permissions it needs, and its pass/fail criteria. Long goals become a tree of strategic goals and sub-goals that can be re-planned mid-run.

2. Recruit

For each task, Hephaestus searches three tiers:

• Local: agents, scripts, and CLI tools already on your machine, run directly without a VM.
• Agent Cloud: your private library of personal or team agents.
• Public Hub: community agents. Publishing and using them is free, and nothing is ranked by payment.

The model you chose makes each selection and records the reason and the exact release. A selection pins the release, package hash, and content digest.

3. Verify

Completion requires distinct worker invocations, artifact handoffs, synthesis, and a passing independent verifier. The host-produced execution receipt is validated locally. A selection or a prepared bundle is not a receipt.

Three environments, one runtime

One, Finance, and Science run in Agentlas Desktop on top of this runtime.

Names and figures on screen are examples.

On your phone, the conversation is the same one running on your paired computer. The work happens on the desktop; the phone shows the results and answers question cards. Android app

Bring your own model

Sign in with Claude Code, Codex, Antigravity, Grok, Kimi, Cursor or GitHub Copilot CLI, add an API key, or run a free local model with Ollama, LM Studio or MLX. When one plan runs out of quota, chats move to the next.

What stays on your computer

• Your files, agents and memory live on your machine.
• You choose how much it may do on its own. Every step is logged, and you can stop it from your phone.
• The phone app sends requests to your desktop and shows the results; the work happens on your computer.
• The engine is open source under Apache-2.0.

Download Agentlas · Android app · Join the Discord Star the repository so the next person finds it · Tell us what broke

Use the engine inside Claude Code, Codex, Cursor or Antigravity

Or just give your coding agent this repository's address and ask it to install Agentlas.

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

The default installer prepares the isolated runtime under ~/.agentlas/os-runtime and the dedicated launcher ~/.agentlas/os-bin/agentlas-os. Optional features are OFF. It does not permanently register plugins or MCP in detected hosts, create global ~/.local/bin wrappers, or enable the global router.

After a successful install, run:

~/.agentlas/os-bin/agentlas-os features status

Report the runtime result separately from host connection. Use host status and the host session instructions below. Restarting an app does not establish readiness. OS updater readiness also requires its own verification.

Prefer a GUI? Agentlas Desktop is a separate application with its own installation and update flow.

Paste to Install

Already inside an LLM? Paste this into Claude Code, Codex, Antigravity or Cursor. It is written so the model can verify what it is running before it runs it, rather than being asked to trust it blindly: