AI coding agent + chat + image gen, zero cloud.
Run every open LLM locally — MLX, Transformers, VLM, Diffusion — with Ollama/OpenAI API compatibility.

🇰🇷 한국어 README

Native Ollama/OpenAI API compatibility, streaming responses, session recents, persona switching, file attachments (PDF / Excel / Word / images), voice input + TTS with auto language detection.

Monaco editor + file explorer + Git panel + PTY terminal + AI inline completion. The Agent Chat on the right gets file read/write/search/exec tools and MCP server integration — it can actually do the work, not just describe it.

Local text-to-image via diffusers. Sampler / steps / CFG / LoRA controls. Styled presets for the 90% case.

Curated notes + auto-captured session logs with BM25 + semantic search. Your local models can query the wiki to stay on-context across restarts.

Auto-detects ~/.cache/huggingface/hub/ + LM Studio cache so models you already have just show up. Tier badges (Supported / Experimental), tok/s benchmarks, vision/audio capability flags.

Scores every model against your RAM / GPU / context headroom. Sorts recommendations by real performance on your machine, not marketing claims.

An SVG owl that sits on your desktop and reacts to your coding state (idle / thinking / typing / happy). Double-click to summon the main window.

1. Download the latest OVO_x.y.z_aarch64.dmg from Releases.
2. Open the DMG and drag OVO.app onto the Applications shortcut.
3. Back in the DMG window, double-click Install OVO.command. It shows you exactly the one command it will run, you click Run, done.

That's it — no Terminal required.

xattr -rd com.apple.quarantine /Applications/OVO.app

xattr -rd com.apple.quarantine /Applications/OVO.app
open /Applications/OVO.app

First launch bootstraps a Python runtime into ~/Library/Application Support/com.ovoment.ovo/runtime/ (≈1.5 GB, ~3 min, one-time). Subsequent launches are instant.

• macOS 13+ on Apple Silicon (M1 / M2 / M3 / M4). Intel Macs are not supported.
• 16 GB RAM minimum (7B models); 32 GB+ recommended for 14B and above.
• 10 GB free disk for runtime + a couple of models.

1. Launch OVO.
2. Go to Models, pick a model (Qwen3, Llama 3.3, Gemma, Mistral, DeepSeek, …), click download.
3. Open Chat and send a message — the local model answers, no network calls.
4. Open a project folder in Code to use the IDE + Agent Chat.

OVO can read your local Claude Code config so the same context reaches your local model:

• CLAUDE.md — injected as system context
• .claude/settings.json — preferences honoured
• .claude/plugins/** — behaviour hints

Disabled by default. Flip it on in Settings → Claude Integration. OVO never touches claude.ai, API keys, session tokens, or anything that could affect your Claude account.

git clone https://github.com/ovoment/ovo-local-llm.git
cd ovo-local-llm

# frontend + Rust deps
npm install

# Python sidecar venv (dev uses $HOME cache, avoids SMB locks)
cd sidecar && uv sync && cd ..

# run the full stack in dev mode
npm run tauri dev

Release build: npm run tauri build — produces .app + .dmg under your Cargo target dir.

Deeper docs: docs/ARCHITECTURE.md · docs/ARCHITECTURE.en.md · docs/release/BUILD.md · docs/release/SECURITY.md · docs/release/PRIVACY.md

• Shell — Tauri 2 (Rust)
• Frontend — React 18 + TypeScript + Tailwind + shadcn/ui + Monaco
• Sidecar — Python 3.12 FastAPI, spawned by Rust, user-cached venv bootstrapped with a bundled uv
• Runtimes — mlx-lm, mlx-vlm, mlx-whisper, transformers, diffusers
• Storage — SQLite (chats + Wiki), local filesystem (attachments, models)

OVO is a solo-developer project. Every coffee funds one more model architecture I can patch and support.

MIT — use it, fork it, ship it.

Made with 🦉 by ben @ ovoment