Back to directory

OpenCode++

A Windows-first reliability plugin for the OpenCode desktop agent that adds edit boundaries, command evidence, and verification gates around its AI-generated diffs.

OpenCode++

OpenCode++ is a plugin for the official OpenCode Desktop application that makes the work behind an AI-generated diff visible and reviewable: what the model inspected, what it was blocked from doing, what commands it asked to run, and what evidence actually verified its claim of success. It targets the failure mode where a plausible-looking diff comes from reading the wrong files, editing outside the intended scope, running an unrelated command, or declaring success without fresh test evidence.

It works as a user-level observer and controller around the tools OpenCode already exposes, rather than a separate chat application or a replacement model: a context registry selects relevant files and symbols before a blind search and explains what was included or rejected, a guard and policy layer checks commands and protected paths against required checks, an evidence layer matches command or CI results to the current working-tree hash, and an intervention ledger records observed, prevented, requested, repaired, and unresolved states before a final repair, human-review, or finalize decision.

It is written in TypeScript, documented in both English and Chinese, and is a Windows-first plugin for OpenCode Desktop.

More in Coding agents

See all 793
  • The City

    github.com

    A native macOS app that shows Claude Code runs as a city, with each project as a building, each team as a floor of robots, and every animation driven by a real event from the claude CLI's stream.

  • rig

    tryrig.ai

    A small, single-binary agent runtime that points at any OpenAI-compatible model, local or hosted, reads and edits a repository's code, runs its tests and remembers what it learned, with a loop implemented in a few hundred lines.

  • Jauvex

    jauvex.reindent.com

    An Electron desktop app that puts Claude Code, Codex and Grok coding-agent sessions side by side and lets you steer them by voice, with a small model handling fast routing decisions.