Skip to content

LiveContext CE v0.1.8

Choose a tag to compare

View all tags
@livecontext-ai livecontext-ai released this 03 Jul 20:27
v0.1.8
01e4d90

What is new

Highlights

Interface screenshots + PDF (opt-in renderer profile)

Workflow interface nodes can now render a screenshot (PNG) or a PDF of the page into your Files (generateScreenshot / generatePdf). Enable it with:
docker compose --env-file docker/.env.ce.renderer up -d
Stays light: a default up starts no browser; the headless-Chromium renderer (~1 GB) runs only when you opt in.

Web search for the browser agent (opt-in browser-agent profile)

The web_search tool now returns results locally: the browser-agent profile bundles a SearXNG metasearch sidecar. Enable with:
docker compose --env-file docker/.env.ce.browser-agent up -d

Browser agent over cloud-connect (no local Chromium)

A cloud-linked CE can now run the browser agent (the agent_browse tool and the workflow browser-agent node) on the linked cloud, including the live browser view (CDP), without running the heavy local browser container. It is executed and billed on the linked cloud account.

Models

Added Qwen and Moonshot providers. OpenRouter and Cohere are hidden on CE (use the native providers).

All additions are opt-in and additive: a default docker compose up -d stays lightweight.

Update an existing install

git pull
docker compose pull
docker compose up -d

The compose file pins this release's image tag, so run git pull first. Your data lives in Docker volumes and is kept across updates.

Fresh install

git clone https://github.com/livecontext-ai/livecontext-ce
cd livecontext-ce
docker compose up -d

Then open http://localhost:3000

Images

  • ghcr.io/livecontext-ai/livecontext-ce:v0.1.8
  • ghcr.io/livecontext-ai/livecontext-ce-frontend:v0.1.8
  • ghcr.io/livecontext-ai/livecontext-ce-bridge:v0.1.8
  • ghcr.io/livecontext-ai/livecontext-ce-screenshot-renderer:v0.1.8 (opt-in renderer profile)
Assets 2
Loading