RUST + TAURI V2 DESKTOP AGENT IDE

OXIDE STUDIO

An autonomous, local-first AI software engineering studio. Manage multiple project folders, save persistent conversations, 1-click install Coding & Uncensored AI models from Ollama & HuggingFace auto-matched to your PC specs, and orchestrate a Lead Architect AI with hardware-governed Subagents.

1-Click AI Model Hub with Auto PC Spec Detection & Uncensored Filters

Oxide automatically detects your CPU, Total/Free RAM, and GPU VRAM to tell you which AI models your PC can run before you click install. Filter by Coding, Uncensored / Abliterated, Reasoning (R1), or search HuggingFace Hub Live to pull any GGUF repository in one click.

Qwen 2.5 Coder 7B (Abliterated) 8GB+ RAM / 6GB VRAM
hf.co/bartowski/Qwen2.5-Coder-7B-Instruct-abliterated-GGUF
Coding Uncensored

Refusal-abliterated Qwen 2.5 Coder 7B for autonomous software engineering, reverse engineering, binary analysis, and security research.

Qwen 2.5 Coder 14B (Abliterated) 16GB+ RAM / 10GB VRAM
hf.co/bartowski/Qwen2.5-Coder-14B-Instruct-abliterated-GGUF
Coding Uncensored

High-precision 14B Uncensored Lead Architect for multi-file C++, Rust, and TypeScript systems engineering workflows.

DeepSeek-R1 7B / 14B Abliterated 8-16GB RAM
hf.co/huihui-ai/DeepSeek-R1-Distill-Qwen-7B-abliterated-GGUF
Coding Uncensored Reasoning

Combines visible <think> chain-of-thought reasoning with refusal abliteration for unrestricted problem solving.

Qwen 2.5 Coder (1.5B / 3B / 7B / 14B / 32B) 4GB-32GB RAM
qwen2.5-coder:7b | qwen2.5-coder:14b
Coding Fast Subagents

Run 14B/32B as your Lead Architect and 1.5B/3B as ultra-fast parallel Subagents for file search and edits.

Dolphin 2.9 Llama-3 8B & Mistral 7B 8GB RAM / 6GB VRAM
dolphin-llama3:8b | dolphin-mistral:7b
Coding Uncensored

Eric Hartford's uncensored Dolphin models trained on coding, tool calling, and unfiltered instruction datasets.

DeepSeek-R1 (1.5B / 7B / 14B) 4GB-16GB RAM
deepseek-r1:7b | deepseek-r1:14b
Coding Reasoning

Streams deep step-by-step architectural reasoning directly into Oxide's collapsible Thought for Xs > drawer.

Built for Full-Stack Autonomous Engineering

Every subsystem in Oxide Studio is engineered in Rust + TypeScript to give local AI models the same capabilities as cloud-hosted autonomous coding agents.

[AI]

Hierarchical Lead AI + Fast Subagents

Assign a large reasoning model as your Lead Architect to plan tasks and delegate file searches, code edits, and test runs to parallel Coder, Research, and Tester Subagents running faster 1.5B-7B models.

[SEC]

PC Hardware Resource Governor

Continuously monitors live CPU load, free System RAM, and GPU VRAM via sysinfo and nvidia-smi. Enforces a strict hardware semaphore so subagents never freeze or overload your machine.

[MCP]

Model Context Protocol (MCP) Hub

Full JSON-RPC 2.0 client supporting builtin knowledge graphs, stdio servers (npx, uvx, python), and http endpoints with 1-click tools/list discovery.

[DIR]

Multi-Project Tree & Native Folder Picker

Click + Folder to open any directory using the native Windows folder dialog. Switch between projects and saved conversations effortlessly with automatic disk persistence.

[JAIL]

Silent Execution & Path Sandbox

All background tools (git, ollama, cargo, npm) run inside a canonical path sandbox with Win32 CREATE_NO_WINDOW so sketchy terminal windows never pop up.

[UPD]

1-Click GitHub Self-Updater

Checks Hanzkii/Oxide for new releases or commits on main and installs updates silently in the background with a single click.

[FAST]

Hybrid Split Inference & GPU Offloading

Run heavyweight 14B, 32B, and 70B models exceeding physical VRAM by partitioning transformer tensor layers between GPU VRAM and System RAM with real-time layer allocation dials and visual split tracking.

[CHAT]

Slash Commands & Side-Queries (/btw)

Type / for an auto-completing command palette including /btw (ask side-questions without file edits), /plan, /subagents, /fix, and /test.

Connect Any External MCP Tool Server to Your Local AI

Oxide Studio includes a native Rust JSON-RPC 2.0 MCP client (src-tauri/src/mcp.rs) that lets your local Ollama and HuggingFace models discover and execute tools from any Model Context Protocol server in one click.

BUILTIN TRANSPORT

Built-in Knowledge Graph (oxide-memory)

Ships ready out of the box with zero external dependencies. Provides store_memory and recall_memories tools so your Lead Architect AI can persist architectural notes and project context across tasks.

STDIO TRANSPORT

Local Stdio Servers (npx / uvx / python)

Spawns local command-line MCP servers silently in the background (using Win32 CREATE_NO_WINDOW) and communicates over JSON-RPC 2.0 stdin/stdout pipes with automatic initialize and tools/list discovery.

HTTP JSON-RPC 2.0

Remote & Localhost HTTP Endpoints

Connects to any HTTP JSON-RPC 2.0 MCP endpoint (such as local reverse-engineering bridges, database inspectors, or custom internal APIs) and exposes their schemas to the autonomous agent loop.

How to Add & Use MCP Servers in Oxide Studio

1. Click Customizations (MCP) in the left sidebar.
2. Enter a Server ID (e.g. filesystem or memory) and command (e.g. npx -y @modelcontextprotocol/server-memory).
3. Click Discover Tools to run the JSON-RPC 2.0 initialize -> tools/list handshake.
4. Toggle the server to Enabled - the Lead Architect AI and Subagents can now invoke its tools automatically via call_mcp_tool.

JSON-RPC 2.0 Handshake & Tool Invocation

{
  "action": "call_mcp_tool",
  "server_id": "oxide-memory",
  "tool_name": "store_memory",
  "mcp_args": {
    "key": "architecture_notes",
    "value": "Lead Architect uses Qwen 14B; Subagents use 7B"
  }
}

How to Install & Open Oxide Studio

A. Standalone Windows Installer (`.exe`)

1. Visit GitHub Releases and download Oxide_0.1.0_x64-setup.exe or Oxide-Portable.exe.
2. Launch Oxide Studio.
3. Open AI Model Hub (1-Click) in the left sidebar to install your preferred Coding or Uncensored AI model, and click Update anytime to pull new releases.

B. Local Repository Clone (`start-oxide.bat`)

1. Clone the repository:
git clone https://github.com/Hanzkii/Oxide.git
2. Double-click start-oxide.bat (or run npm install && npm run dev) to launch the studio immediately.