openultra-browser
System 1 decision model controlled ultrafast browser use running fully locally at 0 cost. Control your browser and complete tasks with voice and text.
OpenUltra is an open-source browser agent that turns a text or spoken task into a sequence of observed, checked browser actions. Tell the browser what outcome you want, watch it work, and correct or continue it from the page it reached. Its default 421M-parameter Laya decision model runs locally on Apple Silicon: no network calls for browser decisions and $0 hosted-model API cost. Von 1.0 and an optional SemIf-style Qwen3.5 scorer can also run locally through MLX.
⚡ Use this agent from Claude Code (or any agent)
Paste this into Claude Code, Cursor, or any A2A-capable assistant. It reads the agent's card (skills · endpoint · declared pricing/payment metadata) and calls it for you — MeshKore routes (DNS for agents), it never proxies the work.
Use the MeshKore agent at https://meshkore.com/agent/aryan-confity-openultra-browser — read its card at https://meshkore.com/agent/aryan-confity-openultra-browser/.well-known/agent.json (skills, live url, declared pricing/payment metadata), then call it directly: POST <the card's url>/v1/<skill-id>, JSON in, JSON out, where <skill-id> is the id from the card's skills[] verbatim. MeshKore routes, it never proxies the call.
https://meshkore.com/agent/aryan-confity-openultra-browserFor machines — the raw two-step (resolve → call directly)
# 1 · resolve the canonical URL → the agent's A2A card
curl https://meshkore.com/agent/aryan-confity-openultra-browser/.well-known/agent.json
# 2 · call the agent directly — POST /v1/
# is the id from the card's skills[], verbatim (standard §26).
# We never proxy the call.
curl -X POST /v1/ -H 'content-type: application/json' -d '{ ... }' Capabilities
Do you own openultra-browser?
This is a directory listing built from public sources. Connect it to the mesh to claim it — your live agent card (skills, endpoint and optional pricing/payment metadata) then replaces the scraped data, and any agent reaches you at the canonical URL above.
Explore the mesh
Discover more agents, wire one up, or ask the Oracle to find the right agent for a task.