Zero-install browser coding
Run a Linux-like sandbox in the browser — terminal, files, git, and app preview. First use downloads the WASM Linux image.
Screenshots from the real Glixo Code UI — GIF upgrades ship when recorded.
Run a Linux-like sandbox in the browser — terminal, files, git, and app preview. First use downloads the WASM Linux image.
Start on desktop, monitor from phone, return to the same agent session — messages, stream state, and permissions stay in sync.
Describe or fork an app — the agent scaffolds it on the faux desktop and you run it immediately.
Switch OpenAI OAuth, API keys, Anthropic, Ollama, or your own compatible endpoint per task.
/loop, /goal, and /subagent drive multi-step runs instead of stopping after one reply.
Save a known-good point around edits and tests — revert code and agent state when something breaks.
Declarative workflows pause at human-in-the-loop gates — you approve, then execution continues.
A supervisor delegates to specialized agents, coordinates plans, and recovers from stalls.
Windows desktop, Android APK, and browser/web are portal-ready. Linux runtime exists — desktop Linux downloads ship when release packaging is public.
Code without installing a daemon — terminal, git, and preview in a cached WASM Linux environment.
Connect a machine and let agents read files, edit code, run commands, and inspect diffs in the actual workspace.
Docker/OCI/gVisor-style isolation is in progress — marketed as preview until the release path is polished.
Preview — not a production guarantee yet.
Reads your repo, edits files, runs commands, and checks results — not copy-paste suggestions.
Sessions, messages, stream state, permissions, and machine status follow you across phone, web, and desktop.
Encrypted session history and checkpoints let you pick up elsewhere — not live process migration when a target dies.
Anthropic API key, OpenAI API key, OpenAI OAuth, and Ollama built in; CLIProxy and OpenAI-compatible endpoints installable.
Ollama for private or cheap tasks; cloud models when you need stronger reasoning.
Add adapters, manifests, secrets, and model discovery through the extension system.
Save conventions, decisions, and environment notes — retrieve them in later sessions and workflows.
Multiple agents reason together in a shared thread over one coding task.
A manager agent delegates to specialists, coordinates plans, and recovers from stalls.
Steps, gates, approvals, checkpoints, and resumable execution — great for demos and production guardrails.
Extension-contributed tools and MCP integrations for GitLab, Playwright, search, and more.
/loop, /goal, and /subagent have full runtime handling. /schedule, /handoff, and /btw capture intent — phrase scheduling carefully until full automation ships.
Install IDE extensions and Agxos apps from the marketplace.
Same agent, two shells — switch whenever the job suits.
Editor, terminal, git, and agent in one place — approve the changes that matter.
Embedded agentic OS: terminal, browser, files, editor, diff viewer, App Creator, marketplace, and native app windows.
Pick a provider per session or use automatic model and reasoning selection where enabled in the UI.
Verify live auto-routing in a demo before treating it as a hard marketing claim.