Unity-Technologies/unity-agent-plugin

Unity plugin for third-party agent platforms

Unity‑Agent‑Plugin – AI‑assisted Unity development

What it is – A plugin that adds a Unity skill to Anthropic’s Claude Code and Codex agents. Once installed, the agents can understand natural‑language requests and automatically generate or modify Unity project assets (scripts, UI, ads, IAP, rendering settings, etc.) on behalf of the developer.

How it works – The repository ships a skill package (unity@unity‑agent‑plugin) that the Claude Code or Codex runtime loads. When you ask the agent to “add in‑app purchases” or “fix blurry pixel art”, the skill translates the request into Unity‑specific API calls, creates the necessary C# files, scene objects, or project settings, and applies them to the open Unity project.

Installation

  • Via the built‑in marketplace commands inside a Claude Code session:
    /plugin marketplace add Unity-Technologies/unity-agent-plugin
/plugin install unity@unity-agent-plugin
  • Or from a terminal with the claude CLI (or the analogous codex CLI for Codex).
  • Manual install: clone the repo and symlink it into ~/.claude/skills/unity.

Verification – In Claude Code type /unity: to see the skill list; in Codex run codex plugin list and you should see unity@unity-agent-plugin marked as installed and enabled.

Typical usage – After installation, simply describe what you need in plain English, e.g.:

  • Add a rewarded video ad that grants coins.
  • Create a hex‑tile palette for level design.
  • Fix TextMeshPro Chinese characters showing as empty boxes. The agent will generate the appropriate Unity assets and code without you writing them manually.

Supported Unity versions – Unity 6 and newer.

Support & feedback – Bugs or feature requests are handled through the official Unity Discussions forum linked in the README.

License – Distributed under the Unity Companion License (see LICENSE.md).

All details are taken directly from the repository’s README.

Related

  • Project
    miracodeai/mira

    Mira is an open‑source, self‑hosted AI code‑review service. It works with any LLM (OpenRouter, Ollama, AWS Bedrock, Codex CLI, etc.), stores diffs, embeddings, CVE data and usage logs in your own SQLite/Postgres, and presents results through a private dashboard. Features include noise‑filtered comments, a learning loop that turns rejected feedback into custom rules, full‑repo indexing, vulnerability alerts, and support for GitHub, GitLab and Forgejo. Deploy via Docker (one‑click Railway, Fly.io, Render) and configure per‑repo with `mira.yaml`/`.mira.yaml`. Licensed under Apache 2.0.

  • Project
    gendigitalinc/sage

    Sage is a security plug‑in for AI coding assistants (Claude Code, Cursor, VS Code, OpenClaw, OpenCode). It intercepts tool calls—shell commands, URL fetches, file writes, package installs—and runs multiple threat checks (cloud URL reputation, 300+ local YAML heuristics, a prompt‑injection ML model, supply‑chain analysis, and Windows AMSI). If a request looks unsafe, Sage blocks it and logs the decision. Installation is done via the respective assistant’s marketplace or npm, and the project is open‑source under Apache 2.0.

  • Project
    danium/lateral-thinking

    A skill‑bundle for AI coding agents that adds classic lateral‑thinking methods (random stimulus, SCAMPER, Six Hats, etc.) with built‑in “abandonment” rules, letting the agent diagnose why ideas feel stale and generate structured, non‑obvious product directions.

  • Project
    strands-labs/ai-functions

    Strands AI Functions is a Python library that turns ordinary‑looking functions into LLM‑backed agents. Using the `@ai_function` decorator you write a normal function with a docstring prompt; the library builds the prompt, calls a model (Bedrock, OpenAI, Claude, etc.), parses the typed result, and can automatically re‑prompt until user‑defined post‑conditions pass. Functions can return real Python objects (e.g., pandas DataFrames), run asynchronously, keep state in *AI Threads*, and be orchestrated as a team of threads via a coordinator that works locally or over WebSockets. Features include self‑correcting loops, economics‑aware model selection, memory‑backed optimisation, and a CLI/TUI for managing distributed agents. Install with `pip install strands-ai-functions` (optional extras for Claude, Kiro, Codex).