{"id":"1fd4fc55-faed-4910-b6d7-d18cf682866a","slug":"ezesubu-vera","kind":"mcp","name":"VERA","summary":"VERA — Virtual Engine Reasoning Agent: an AI co-pilot inside the Unreal Editor. Multi-provider, plugin-based, free & local.","owner":"ezesubu","repoUrl":"https://github.com/ezesubu/VERA","license":"MIT","licenseTier":"permissive","trust":"community","stars":21,"match":null,"fewStars":false,"format":"mcp","createdAt":"2026-06-14T05:23:52.000Z","addedAt":"2026-10-14T05:44:23.481Z","logoUrl":"https://avatars.githubusercontent.com/u/1958782?u=5f71404253cdbad51b79ac07312096cd386ed620&v=4","linkOnly":false,"collection":null,"skillPath":null,"categories":["utilities"],"tags":["ai-agent","copilot","gamedev","llm","unreal-engine"],"runtime":"python","local":true,"cloudCapable":false,"cloudCapability":"unknown","cloudReadyOnPlatform":false,"needsApiKey":false,"reviewed":false,"syncedAt":"2026-10-25T14:24:17.192Z","sample":false,"url":"https://conduits.dev/tools/ezesubu-vera","language":"Python","transports":["stdio"],"install":{"pypi":"vera-ue"},"requirements":{"env":[],"upstreamMayCharge":false},"tools":null,"readme":"<div align=\"center\">\n  <video src=\"https://github.com/user-attachments/assets/0ee66435-a6ca-45cf-848d-3dbe7a8d3c10\" width=\"800\" autoplay loop muted playsinline></video>\n</div>\n\n<div align=\"center\">\n\n# VERA — Virtual Engine Reasoning Agent\n\n**An AI co-pilot that lives inside the Unreal Editor.**\nChat with an LLM that inspects your level, runs editor tools, sees the viewport,\nand verifies its own work — powered by the brain *you* choose (cloud or fully local).\n\n[![Fab](https://img.shields.io/badge/Fab-Unreal_Marketplace-000000?style=for-the-badge&logo=epicgames&logoColor=white)](https://www.fab.com/listings/669e2b05-3ba0-4074-b9e5-220a4e87a598)\n[![Discord](https://img.shields.io/badge/Discord-Join-5865F2?style=for-the-badge&logo=discord&logoColor=white)](https://discord.gg/ZxG8wbRp)\n[![Patreon](https://img.shields.io/badge/Patreon-Support-FF424D?style=for-the-badge&logo=patreon&logoColor=white)](https://www.patreon.com/maVERAick)\n[![License: MIT](https://img.shields.io/badge/License-MIT-FFB02E?style=for-the-badge)](LICENSE)\n[![Unreal Engine](https://img.shields.io/badge/Unreal_Engine-5.7_|_5.8-313131?style=for-the-badge&logo=unrealengine)](https://www.unrealengine.com)\n[![Python](https://img.shields.io/badge/Python-3.11+-3776AB?style=for-the-badge&logo=python&logoColor=white)](https://www.python.org)\n\n</div>\n\n> _Why did we build it? Because pasting LLM snippets into Unreal and praying isn't a workflow — and because the Auto-Fixer turned out cheaper than a new keyboard. 🧱⌨️_\n\n<div align=\"center\">\n  <img src=\"docs/images/animated_vera_logo.gif\" alt=\"VERA in Action\" />\n</div>\n\n---\n\n## Table of contents\n\n- [Why VERA](#why-vera)\n- [Features](#features)\n- [The brain — bring your own LLM](#the-brain--bring-your-own-llm)\n- [How it works](#how-it-works)\n- [Built-in tools](#built-in-tools)\n- [Plugins](#plugins)\n- [MCP — drive the editor from your IDE](#mcp--drive-the-editor-from-your-ide)\n- [Install](#install)\n- [Configuration](#configuration)\n- [Usage](#usage)\n- [Architecture](#architecture)\n- [Contributing](#contributing)\n- [FAQ](#faq)\n- [Support — The Co-Pilot Pact](#support--the-co-pilot-pact)\n- [License](#license)\n\n---\n\n## Why VERA\n\nMost \"AI for Unreal\" tools are a chat box that hands you a snippet to paste. VERA is\nan **agent**: you ask in plain language, and it *plans*, *calls the tools it needs*,\n*looks at the result*, and *fixes things if something fails* — inside your editor.\n\n- **Your brain, your rules.** OpenAI, Anthropic, Gemini, DeepSeek, Groq, Hugging Face, NVIDIA NIM, or **any local\n  OpenAI-compatible server**. Run it 100% offline with a local model, or reach for a\n  frontier model when you want more power. Keys live in your `.env` and never leave\n  your machine.\n- **It actually sees.** VERA renders the viewport (via `SceneCapture2D`, even with\n  the editor minimized) and reasons over the image — to inspect an actor, judge an\n  animation, or critique a composition.\n- **It acts safely.** Read-only tools run freely; anything destructive asks for\n  your approval first. A **Read** mode lets it look without touching anything.\n- **Privacy & Studio Security.** Operations run 100% locally by default. No studio telemetry or code snippets leave your machine unless routed to a cloud LLM provider of your choice.\n- **It's extensible.** Capabilities ship as opt-in **plugins** — a folder with\n  `tools/` and a `SKILL.md`. Write your own in minutes.\n- **It's free & open.** MIT licensed, no studio, no lock-in.\n\n## Features\n\n| | |\n|---|---|\n| 🧠 **Multi-provider brain** | OpenAI · Anthropic · Gemini · DeepSeek · Groq · Hugging Face · NVIDIA NIM · any local OpenAI-compatible server (LM Studio, Ollama, llama.cpp, vLLM). Switch provider/model per tab, mid-conversation. |\n| ⚡ **Live Reasoning Stream** | Streams `<think>` blocks (Qwen 3, DeepSeek-R1) and `reasoning_content` fields live into the UI timeline before tool execution. |\n| 🛰️ **Agentic tool loop** | Plans → calls tools → observes → self-corrects → verifies. Not a one-shot snippet generator. |\n| 👁️ **Multimodal vision** | Captures the viewport / individual actors and feeds the image to the model. Paste, drag, or copy images into the chat too. |\n| 🎞️ **Animation pipeline** | Build an IK rig, set up a retargeter, batch-retarget animations, play/scrub them, and visually verify — all from chat. |\n| 🌍 **Procedural worlds** | Generate massive environments using PCG. VERA can wire graph nodes to spawn forests, cities, and scattered props automatically. |\n| ⚡ **Async execution** | Long-running operations run asynchronously with background task tracking (`bg-tasks-bar`) and live heartbeats, preventing socket timeouts and letting you monitor or cancel tasks. |\n| 🧩 **Plugin system** | Drop-in `tools/` + `SKILL.md`. Toggle per plugin. Per-plugin pip deps installed on demand. |\n| 🔌 **MCP server** | Expose the editor to Claude Code (or any MCP client): exec Python, screenshot, tail logs, status, run a VERA command. |\n| 🛡️ **Safety modes** | **Ask** (confirm destructive actions) · **Auto** (autopilot) · **Read** (inspect only). |\n| 💬 **Polished chat UI** | Tabs, markdown + syntax highlighting, inline screenshots, slash-command menu, live tool narration, stop button, conversation windowing. |\n| ⚙️ **Turnkey setup** | First launch auto-installs its Python deps. Configure providers, local URL, and request timeout right in the panel. |\n| 🖥️ **Cross-platform** | Windows, macOS, Linux. No hardcoded paths. |\n\n## The brain — bring your own LLM\n\n<div align=\"center\">\n  <img width=\"2123\" height=\"1010\" alt=\"VeraLiveLocalQwen25\" src=\"https://github.com/user-attachments/assets/cb1ae942-6101-4961-84fd-1cfd3f2e93c8\" />\n</div>\n\nVERA speaks the **OpenAI `/v1` standard**, so it works with essentially any backend.\n**8 providers** are supported out of the box — switch freely, even mid-conversation:\n\n| Provider | What you need | Flagship models |\n|---|---|---|\n| **Anthropic** | `ANTHROPIC_API_KEY` | `claude-opus-4-8`, `claude-sonnet-4-5`, `claude-3-5-sonnet-20241022` |\n| **OpenAI** | `OPENAI_API_KEY` | `gpt-4o`, `gpt-4o-mini`, `gpt-4.1`, `o3-mini` |\n| **Gemini** | `GEMINI_API_KEY` | `gemini-2.5-flash`, `gemini-2.0-flash`, `gemini-2.0-flash-lite` |\n| **Groq** | `GROQ_API_KEY` | `llama-3.3-70b-versatile`, `llama-3.2-11b-vision-preview`, `mixtral-8x7b` |\n| **Hugging Face** | `HF_TOKEN` | `DeepSeek-R1-Distill-Qwen-32B`, `Llama-3.3-70B-Instruct`, `Qwen2.5-Coder-32B`, `Phi-3.5-mini` |\n| **NVIDIA NIM** | `NVIDIA_API_KEY` | Dynamically discovered NIM models (Llama 3.1/3.2, Gemma 2, etc.) |\n| **DeepSeek** | `DEEPSEEK_API_KEY` | `deepseek-chat` (V3), `deepseek-coder`, `deepseek-reasoner` (R1) |\n| **Local** | `VERA_LOCAL_BASE_URL` | Any model on your server — **no key, no cloud, no cost** |\n\n> 💡 The local provider auto-discovers models from **any OpenAI-compatible server**\n> (LM Studio `:1234`, Ollama `:11434`, llama.cpp, vLLM…). For agentic tool-calling,\n> use a **30B+ coder model** (e.g. Qwen2.5/3-Coder-32B); small models ramble. The\n> first request to a cold local server loads the model — which can take minutes — so\n> the request **timeout is configurable** right in Setup.\n>\n> 🧠 **Live Reasoning & `<think>` Streams:** VERA automatically extracts and streams live `<think>` reasoning blocks (Qwen 3, DeepSeek-R1 distills) directly into the UI timeline before running tools, so you can observe the model's decision-making process in real time.\n\n## How it works\n\n```\nYou ──▶ VERA chat (Qt/WebEngine UI inside the editor)\n            │  command + selected provider/model/mode\n            ▼\n        AgentLoop  ─────────────────────────────────────┐\n            │  1. ask the LLM (your provider) for a plan │\n            │  2. LLM requests a tool                    │  repeat until done\n            │  3. run the tool (gate if destructive) ────┤\n            │  4. feed the result back to the LLM        │\n            └─▶ 5. final answer ─────────────────────────┘\n                         │\n                         ▼\n              Unreal Editor (Python bridge → the `unreal` API)\n```\n\nEvery turn streams to the UI: you see the plan, each tool call, and the result as\nit happens — and you can **Stop** at any point.\n\n## Built-in tools\n\nThe agent ships with a core toolset (read-only tools need no approval; ✋ = gated):\n\n| Tool | What it does |\n|---|---|\n| `inspect_level` | Read the open level: actor counts, classes, lights, static meshes. |\n| `inspect_actor_animability` | Check whether an actor has a skeleton and can be animated. |\n| `capture_actor` | Render an actor/viewport to an image so VERA can **see** it (works minimized). |\n| `animate_actor` | Apply or scrub an animation on a skeletal actor. ✋ |\n| `ensure_ik_rig` | Create/ensure an IK Rig for a skeleton. ✋ |\n| `ensure_retargeter` | Create/ensure an IK Retargeter between skeletons. ✋ |\n| `retarget_animations` | Batch-retarget animations between skeletons. ✋ |\n| `run_ue_python` | Run arbitrary Python against the `unreal` API — the universal escape hatch. ✋ (asks every call) |\n\nChained together, the animation tools are a full **rig → retarget → animate →\nvisually verify** pipeline, driven entirely from chat.\n\n## Plugins\n\n<div align=\"center\">\n\n<img width=\"1920\" height=\"1080\" alt=\"fab-02-plugins\" src=\"https://github.com/user-attachments/assets/621657bf-c451-44ae-81cb-30cfc45b0240\" />\n\n\n</div>\n\nCapabilities ship as **opt-in plugins** so the core stays lean — you enable only what\nyou want, and a plugin's pip dependencies are pulled in on demand. \n**All plugins below are bundled and included 100% for free out of the box:**\n\n| Plugin | What it adds |\n|---|---|\n| **Blueprint Forge** | Create Actor Blueprints via the Graph API (components, compile, save) — no clicking. |\n| **Computer Use** | Last-resort screen control for editor UI that has no Python API (click and capture). |\n| **Local IQ** | Raises a small local model's effective IQ with proven, reusable recipes. |\n| **Memory** | Persistent memory across conversations — facts, conventions, decisions. |\n| **Mobile / Performance Doctor** | Audits materials and mobile-compat issues; profiles the level. |\n| **PCG Forge** | Autonomously wire Procedural Content Generation (PCG) graphs to spawn vast, rule-based worlds and scatter props without manual placement. |\n| **Project Intelligence** | Read-only analysis of the on-disk project: engine, plugins, assets. |\n| **Project Playbook** | Loads this project's conventions, decisions and known traps into context. |\n| **Scene Vibe** | Instantly sets the cinematic MOOD of the open level (cyberpunk, noir, aztec, etc.). |\n| **Source Control** | Git source control for VERA: inspect diffs and create gated commits safely. |\n\n### Write your own plugin\n\n```\nVERA_Plugins/my-plugin/\n├── plugin.json        # {\"name\",\"version\",\"enabled\", optional \"deps\":[...]}\n├── tools/*.py         # Tool subclasses (name, description, input_schema, execute)\n└── SKILL.md           # when/how VERA should use it (injected into the system prompt)\n```\n\nA minimal tool:\n\n```python\nfrom vera.agent.tool import Tool, ToolResult\n\nclass HelloTool(Tool):\n    name = \"say_hello\"\n    description = \"Say hello. Use when the user greets VERA.\"\n    input_schema = {\"type\": \"object\", \"properties\": {\"to\": {\"type\": \"string\"}}}\n    def execute(self, args, ctx):\n        return ToolResult(f\"Hello, {args.get('to', 'world')}!\")\n```\n\nDrop the folder in `VERA_Plugins/`, toggle it on in the **Plugins** tab — done.\n\n## MCP — drive the editor from your IDE\n\n<div align=\"center\">\n <img width=\"2252\" height=\"946\" alt=\"ClaudeLive\" src=\"https://github.com/user-attachments/assets/2bb82085-699d-44e5-8113-99cedbeb0f7e\" />\n <img width=\"2254\" height=\"980\" alt=\"ClaudeLive2\" src=\"https://github.com/user-attachments/assets/654b925a-6db1-4b61-9241-9328b65338c9\" />\n <img width=\"2302\" height=\"1013\" alt=\"AngravityIDELive\" src=\"https://github.com/user-attachments/assets/0ea511b1-7c6c-432e-9dac-0a98e613c878\" />\n\n</div>\n\nVERA ships an [MCP](https://modelcontextprotocol.io) server, so the AI in **your\nfavorite IDE or agent** can drive your Unreal editor — write Python into it, read\nthe log, screenshot the viewport, or run a full VERA command — without leaving your\neditor.\n\nDrop this into your MCP client's config (e.g. `.mcp.json`):\n\n```json\n{\n  \"mcpServers\": {\n    \"vera-ue\": {\n      \"command\": \"python\",\n      \"args\": [\"-m\", \"vera.tools.mcp_server\"],\n      \"env\": {\n        \"PYTHONPATH\": \"C:/path/to/VERA\",\n        \"VERA_UE_PROJECT_DIR\": \"C:/path/to/YourProject\"\n      }\n    }\n  }\n}\n```\n\n> **`PYTHONPATH` must point at the VERA repo root** (the folder containing the\n> `vera/` package), so `python -m vera.tools.mcp_server` can find it. Some clients\n> (e.g. Claude Code) launch the server from the project root and work without it,\n> but most run from a different working directory — if you see\n> `ModuleNotFoundError: No module named 'vera'`, this is the fix. You can also\n> point `command` at a specific interpreter (e.g. a full `python.exe` path).\n\nWorks with any MCP-capable client — **Claude Code**, **Cursor**, **VS Code**\n(Cline / Continue / Copilot), **JetBrains Rider** (AI Assistant), **Windsurf**,\n**Zed**, and more:\n\n| MCP tool | Purpose |\n|---|---|\n| `ue_exec` | Execute Python in the editor and get the output back. |\n| `ue_screenshot` | Capture the viewport. |\n| `ue_log` | Tail the Unreal output log. |\n| `ue_status` | Check the bridge/editor status. |\n| `vera_command` | Run a full natural-language VERA command (the agent pipeline). |\n\n## Install\n\n### From source (developers)\n\n```bash\ngit clone https://github.com/ezesubu/VERA.git\ncd VERA\npython PackageVERA.py\n```\n\n1. Copy the assembled `Plugin/` folder into your own Unreal Engine project's `Plugins/VERA/` directory.\n2. Enable Unreal's **Python Editor Script Plugin**.\n3. Open **VERA** from the editor toolbar. (Dependencies are bundled inside the plugin, so it works completely offline out of the box — no `pip install` required).\n4. In **Setup ⚙**, pick a provider and paste a key (or a local server URL), then chat.\n\n### Build the distributable plugin (UE 5.7)\n\n```bash\npython PackageVERA.py --bundle  # assemble from source + bundle deps + RunUAT + zip → Packaged/\n```\n\nThe output is a **compiled, drag-and-drop plugin** ready for the Epic Games Launcher\n/ Fab. Want another engine version? Clone and build it yourself — the pipeline targets\nthe latest UE.\n\n### Requirements\n\n- Unreal Engine **5.7** or **5.8**\n- The **Python Editor Script Plugin** (bundled with UE)\n- Internet access **only** if you use a cloud provider (local models run fully offline)\n\n## Configuration\n\nVERA reads a `.env` at the repo root (and the Setup panel writes to it for you):\n\n| Variable | Meaning |\n|---|---|\n| `OPENAI_API_KEY` / `ANTHROPIC_API_KEY` / `GEMINI_API_KEY` | Cloud provider keys |\n| `GROQ_API_KEY` / `HF_TOKEN` / `NVIDIA_API_KEY` / `DEEPSEEK_API_KEY` | Groq, Hugging Face, NVIDIA NIM, and DeepSeek keys |\n| `VERA_LOCAL_BASE_URL` | Local server `/v1` URL (e.g. `http://localhost:1234/v1`) |\n| `VERA_LLM_TIMEOUT_S` | Request timeout in seconds (raise it for slow cold starts) |\n| `VERA_PLUGINS_DIR` | Override the plugins directory |\n| `VERA_AUTO_APPROVE` | Skip the destructive-action gate (autopilot/testing) |\n\n> 🔒 Keys are saved to your `.env` and **never** sent back to the frontend.\n\n## Usage\n\nOpen the VERA panel and just ask. A few things to try:\n\n- *\"How many actors are in this level, and how many are lights?\"*\n- *\"Create a `BP_SpikeTrap` Blueprint with a static mesh and a box collision.\"*\n- *\"Retarget these animations from the UE4 mannequin to my character, then show me the idle.\"*\n- *\"Audit this level for mobile performance issues.\"*\n- *\"Set a horror vibe on the scene for a screenshot.\"*\n- *\"Remember that this project uses the `SM_` prefix for static meshes.\"*\n\nSwitch **Ask / Auto / Read** in the composer to control how much freedom VERA has.\n\n## Architecture\n\n```\n┌─────────────────────────── Unreal Editor ───────────────────────────┐\n│                                                                      │\n│   VERA panel (Qt WebEngine UI)  ◀──┐                                 │\n│        │ command                   │ events (stream)                 │\n│        ▼                           │                                 │\n│   vera_server  ──▶  AgentLoop  ──▶ tools ──▶ Python bridge ──▶ unreal│\n│        │                │                                            │\n│        │                └─ plugins (VERA_Plugins/*)                  │\n│        ▼                                                             │\n│   MCP server  ◀── Claude Code / other MCP clients                   │\n└──────────────────────────────────────────────────────────────────────┘\n            ▲\n            └─ LLM provider (OpenAI / Anthropic / Gemini / DeepSeek / local)\n```\n\n- **`vera/agent/`** — the AgentLoop, tool registry, sessions, the multi-provider client.\n- **`vera/llm/`** — the OpenAI-compatible adapter (duck-types the Anthropic surface).\n- **`vera/tools/`** — the MCP server and the UE socket connection.\n- **`vera/core/`** — the editor server (`vera_server`) and the progress blackboard.\n- **`Content/Python/`** — the editor scripts (including the **Async Bridge** that prevents timeouts during heavy generations) + the chat UI (`vera_chat/`).\n- **`Content/Python/vera/vera_graph_utils.py`** — The universal graph standard library, resolving API differences across Blueprints, PCG, and Materials.\n- **`VERA_Plugins/`** — the studio plugins.\n\n## Contributing\n\nContributions are welcome — new tools, plugins, providers, fixes.\n\n```bash\n# run the test suite\npython -m pytest tests/ -q\n```\n\n- **Add a tool:** create a `Tool` subclass in `vera/agent/tools/` — the registry\n  discovers it automatically.\n- **Add a plugin:** see [Write your own plugin](#write-your-own-plugin).\n- **Add a provider:** extend the registry in `vera/agent/models.py`.\n\nThe codebase is 100% Python (using the Python Editor Script Plugin) + a local HTML/JS/CSS frontend. It is fully cross-platform and covered\nby a test suite. Open an issue or a PR, or come chat in\n[Discord](https://discord.gg/ZxG8wbRp).\n\n## FAQ\n\n**Do I need to know Unreal or Blueprints?**\nNo. You describe what you want in plain language and VERA builds it through the\nengine's code layer — assets, actors, components, properties, whole systems.\n\n**Does VERA wire the visual Blueprint nodes for me?**\nOut of the box it creates the Blueprint, its components and properties, then\ncompiles and saves it. Wiring the visual Event Graph (the \"spaghetti\") is one\n**plugin** away — a C++-backed plugin can reach the graph APIs that Python can't\nand generate the nodes too. That's the point of the plugin system: no ceiling.\n\n**Is it free? Does it phone home?**\nMIT, free, and it can run **100% local** with your own model — your keys and data\nnever leave your machine.\n\n**How do I manage \"thinking effort\" with reasoning models (DeepSeek-R1, o3-mini)?**\nRight now, VERA doesn't have a direct `--thinking-effort` slider in the UI, but here is how you can achieve that and avoid wasting thinking tokens:\n- **Use multiple tabs with different models/providers:** VERA supports tabs out of the box! You can open multiple chat tabs inside the Unreal Editor panel:\n  - **Tab 1:** Set to a fast/light model (e.g. gemini-2.5-flash, gpt-4o-mini, or a lightweight local model) for quick commands, level inspection, or simple property tweaks — zero token waste on long `<think>` streams.\n  - **Tab 2:** Set to a heavy reasoning model (e.g. deepseek-reasoner, o3-mini) for complex Blueprints, C++ debugging, or performance architecture.\n- **Use VERA's Plugin system (e.g., project-playbook):** VERA already includes plugins like Project Playbook or custom plugins (`VERA_Plugins/your-plugin/`). By adding a `SKILL.md` into a plugin with your project's conventions, actor naming rules, and architecture, VERA doesn't waste thinking tokens trying to figure out how your project is built.\n- **Build a custom VERA plugin for your specific needs:** You can easily write a dedicated VERA plugin (`plugin.json` + `tools/` + `SKILL.md`). You can instruct the agent in the `SKILL.md` to adopt a direct, concise execution style with zero fluff, cutting down on unnecessary reasoning steps before calling Unreal tools.\n\n## Support — The Co-Pilot Pact\n\n<div align=\"center\">\n\n<img width=\"1920\" height=\"1080\" alt=\"fab-03-support\" src=\"https://github.com/user-attachments/assets/574d9009-8baa-41a2-9934-6e149aea8cd5\" />\n\n\n</div>\n\nVERA is **independent and open** — no studio, no investors, no lock-in. It's free and\nruns on your own keys and hardware. If it earns its keep, you can keep it alive:\n\n- 🛒 **[Get it on Fab Marketplace](https://www.fab.com/listings/669e2b05-3ba0-4074-b9e5-220a4e87a598)** — Official Epic Games Store release\n- 💎 **[Support on Patreon](https://www.patreon.com/maVERAick/gift)** — monthly or a one-off gift\n- ☕ **[Tip on Ko-fi](https://ko-fi.com/maveraick)** · 🍺 **[Buy a Beer](https://buymeacoffee.com/maveraick)**\n- 💬 **[Join the Discord](https://discord.gg/ZxG8wbRp)** — free, come say hi\n- ⭐ **Star the repo** and tell another dev — it genuinely helps.\n\n## License\n\nMIT — use VERA in your commercial and AAA projects. See [LICENSE](LICENSE).\n\n## Credits\n\nConjured in the dark by **maVERAick** — Sith Lord of the Unreal Editor — mortal\nidentity [**@ezesubu**](https://github.com/ezesubu). ⚡🌑\n\n**Core AI Team & Contributors:**\n- **Claude** — Lead UI Architect\n- **Antigravity (Gemini)** — Lead Artist & Infrastructure\n\n> _Come to the dark side. We have agents._\n\n<img width=\"665\" height=\"706\" alt=\"VeraInitChat\" src=\"https://github.com/user-attachments/assets/de6c8cc9-a60f-4c8b-bf13-909c4912e6ed\" />\n\n<div align=\"center\">\n<sub>built by <b>maVERAick</b> · <i>the agents thank you ◇</i></sub>\n</div>\n"}