vibehacker
News
GitHub (anomalyco/opencode) ·

OpenCode 2.2.4 lets agents publish HTML artifacts and keeps desktop terminals alive across restarts

Released Oct 30, setting "experimental": { "artifacts": true } in opencode.json lets agents create, update and serve HTML or static artifacts locally or via plugin storage, while desktop terminals now belong to the session and keep their scrollback through server restarts. It also adds a guided Claude Agent provider setup, and same-day v2.2.5 adds percentage compaction buffers like "20%" (changelog).

Read at github.com
OpenCode
Open source AI coding agent for terminal, IDE, and desktop

More news

View all

agent-desktop moves to Vercel Labs: computer use for agents through OS accessibility trees, not pixels

Now under Vercel Labs with v1.0.2 (Oct 30), the Apache 2.0 Rust CLI ( npm install g agent desktop ) lets any coding agent snapshot a macOS, Windows or Linux app as JSON with a ref per element, act on a ref, and re snapshot to verify, headless by default so it doesn't steal your pointer or focus. Snapshots can include private screen content, so keep them out of public logs (releases)…

GitHub (vercel-labs/agent-desktop)

Claude API gets a Usage and Cost Analytics API in beta and a 4x bigger 128 MB request limit

Since Oct 29, GET /v1/organizations/analytics/usage and /cost (beta header analytics usage cost 2026 08 24 , Admin or read:analytics key) break down tokens and USD by model, workspace, API key or user, though data lags 4–24 hours and the old Usage and Cost API is now legacy. Separately, since Oct 28 Messages and Token Counting requests can be 128 MB instead of 32 MB on the first party API only, while Bedrock, Vertex and Foundry keep lower caps (release notes)…

Claude Platform Docs

Lody 0.109 puts several repos, submodules and folders into one project so agents can work across them

Released Oct 30, multi repository projects let one Claude Code, Codex or other agent conversation span several Git repos, submodules and local folders, with a per repo switcher for PRs and CI status (add them in Settings → Projects). It also adds one click scheduling of a continue message for after a Claude quota reset, and local MCP sign in that keeps credentials in your system keychain…

Lody Changelog

Gemini API's Computer Use tool is now generally available for browser, mobile and desktop agents

Since Oct 30, the computer use tool is GA in both the Interactions and GenerateContent APIs: your loop sends a screenshot, gets back a UI action with an intent explaining it, executes it (e.g. with Playwright) and repeats. Responses can carry a safety decision of require confirmation or blocked, and Google still says to run it in a sandboxed VM or container (docs)…

Gemini API Release Notes

Hugging Face's safeagents is a local proxy that blocks risky coding-agent tool calls before they run

Released this week under Apache 2.0, it sits between your agent and its model server on 127.0.0.1:8787 , blocking calls to undeclared tools or to hosts nobody mentioned in the conversation and running about 110 atif scan detectors for things like reading /proc/1/environ or curl noproxy , with Claude Code, OpenCode, Pi and three other harnesses tested in CI. Start with log only , and note it can't see URLs a script builds at runtime, so keep default deny egress in your sandbox (Tensor Journal)…

GitHub (huggingface/safeagents)

Spotted something we missed? Start a thread.