Radar / AI coding tools / OpenCode 2.3.0
OpenCode 2.3.0: background subagents become the default
The open-source coding agent's 2.3.0 release makes subagents return immediately and keep working in the background, reporting back when idle.
Why it matters
Turns a single coding session into a parallel workforce by default: subagents run in the background while the TUI folds each run into one collapsible activity row.
What you could build with it
An indie developer maintaining a large codebase could let OpenCode's background subagents run test suites and lint checks in parallel while the main session keeps editing, turning one coding session into a small review pipeline.
Does it hold up?
Shipped 13 Nov; the background-subagent change is a default flip in a mature tool with 226,000 stars, so existing users get it on upgrade — too early for field reports on the new default, but the base tool is already used daily by a large community.
Built with OpenCode 2.3.0
- Agent Tools Today (14 Nov 2026): OpenCode 2.3 makes background subagents the defaultarticle · Lead launch item: subagents return immediately and continue in the background, the TUI folds runs into collapsible rows, and MCP events sit behind an experimental flag.
- Trending AI GitHub repos: OpenCode v2.3.0article · Hand-checked trending list noting the 2.3.0 release alongside other agent-capability releases from the same window.
- OpenCode 2.3.0 makes background subagents the only modeautomater · Walkthrough of the 2.3.0 contract change: subagents return a session ID immediately, run in the background, and report on idle — with the foreground path deleted outright.
- OpenCode background subagents: what v2.3.0 changesdevelopersdigest · Explainer on background-by-default subagents plus the quieter-transcript default, and the third-party plugin it replaces.
Learn more
First spotted on article: source.
More AI coding tools
Chrome DevTools MCP: give your coding agent a real browserOfficial MCP server from the Chrome team that lets coding agents drive a live Chrome — console, network, traces…coding · JEV 0.82Orca: the agent development environment for running coding-agent fleetsStably AI's open-source desktop app for running many CLI coding agents side by side — Claude Code, Codex, Cursor and…coding · JEV 0.78Open Code Review: Alibaba's hybrid AI code reviewer, now past 50,000 starsAlibaba's open-source code review CLI (Apache 2.0) pairs deterministic rules with an LLM agent to review git diffs…coding · JEV 0.77Astryx: Meta's agent-ready design system, open sourceMeta open-sourced the React 19 + StyleX design system behind 13,000 internal apps: 150+ accessible components, themes…coding · JEV 0.76GitHub Spec Kit — spec-driven development for coding agentsGitHub's open-source toolkit that gives any coding agent a structured spec, plan, tasks, implement workflow, so specs…coding · JEV 0.75shadcn/improve: audit with your best model, execute with your cheapestAn MIT-licensed Agent Skill that audits any codebase across nine categories with parallel subagents, vets its own…coding · JEV 0.75
Get the week's best AI launches, plus 3 ideas worth building
One email every Saturday. Ranked by traction, not hype. Free.