AgentEvolver ships a browser workbench that talks to the Python Gateway over a WebSocket. Eleven short clips below, one per feature — the layout, each of the four workspaces in turn, the capability catalogue, the session panels, the machines, and the model registry.
Projects and navigation on the left, the task surface in the middle, session state on the right. The header carries the gateway status — this workbench is a thin client over a running Python process, not a mock.
ws://…/wsThe same session, seen four ways. Switching a view does not start a new run — the workspace, the files, and the agent history stay put underneath.
The Canvas is a node editor for the times a picture beats a paragraph. Components are dragged in from a categorised palette and joined into a flow you can save and reuse — a human-facing library, separate from the agent-facing workflows.
Code opens an OpenVSCode server rooted at the session workspace — the same /workspace the agent writes into. The first launch boots the editor container, so it takes a moment; after that it is just VS Code in a tab.
Science attaches a Jupyter kernel to the very files the agent is working on. You can poke at a result the moment it lands, and the agent can run a cell whenever it needs one — the first boot takes about ten seconds, then cells run in milliseconds.
.ipynbEach registry in the framework surfaces here as a browsable, searchable list, and what you tick is what the session is handed. The counts beside each entry are live — they grow as the evolution loop registers new components.
Four starting points cover the usual asks — review, plan, explain, investigate — and the composer underneath takes anything else. Files can be attached to the session before the run begins.
The right pane answers "what is it actually doing". Each session gets its own initially empty workspace — only staged inputs and files produced during that session appear there, never a copy of your checkout.
Some work needs a GUI rather than a shell. Local environments ship their own VNC-capable runtime and open as a live view in the browser; remote machines are reached over SSH instead.
Providers are registered centrally, and every model declares what it can do — so the orchestrator can pick a model that actually supports the call it is about to make.
The theme is remembered across sessions, and the endpoint is not baked in: point the workbench at a gateway on another host, or supply a token when the gateway requires one.
AGENTEVOLVER_GATEWAY_TOKEN for protected gatewaysBoth halves — the Python Gateway and the Vite dev server — start together inside the base sandbox. One container, two processes.
Then open http://127.0.0.1:5173. The sandbox runs with --network host, so the container loopback is the host loopback; the UI connects to ws://127.0.0.1:9876/ws by default.