Back to directory

OVO

A private, Claude-Code-style coding agent for Apple Silicon that runs chat, code editing and local model workflows entirely on-device, compatible with Ollama and OpenAI APIs.

OVO

OVO is a local AI workspace for Apple Silicon Macs, built to keep code and conversations on-device instead of sending them to the cloud. Its Code view combines an editor, a file explorer, a git panel and a terminal with an agent chat that has file read, write, search and execution tools and Model Context Protocol integration, so it can act on a project rather than only describe changes.

Also included are a chat interface compatible with the Ollama and OpenAI APIs with streaming, personas and file attachments; local text-to-image generation through a diffusion pipeline; a wiki that combines curated notes with automatically captured session logs, searchable by keyword and by meaning; document parsing and retrieval-augmented generation for formats such as PPTX, HWP and scanned PDFs; and a local option for fine-tuning models with LoRA, including dataset creation, training and adapter merging.

It auto-detects models already downloaded through Hugging Face's cache or LM Studio, is model-agnostic across model families such as Llama, Gemma, Mistral, Qwen and DeepSeek, and scores each model against the Mac's memory, GPU and context headroom before running it.

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.