#2222nd of 36 in Assistants

ods

Installer that sets up a local AI server stack on Linux, macOS and Windows

Stars
7.6k
License
Apache-2.0
Last commit
Oct 2026
Last release
Sep 2026
Language
Python
Stars, last 29 weeks+7,303
1 Apr 2026: 335 stars8 Apr 2026: 361 stars15 Apr 2026: 414 stars22 Apr 2026: 441 stars29 Apr 2026: 478 stars6 May 2026: 487 stars13 May 2026: 508 stars20 May 2026: 1,508 stars27 May 2026: 1,757 stars3 Jun 2026: 1,840 stars10 Jun 2026: 1,907 stars17 Jun 2026: 2,035 stars24 Jun 2026: 2,121 stars1 Jul 2026: 2,414 stars8 Jul 2026: 2,783 stars15 Jul 2026: 3,055 stars22 Jul 2026: 3,395 stars29 Jul 2026: 3,759 stars5 Aug 2026: 3,966 stars12 Aug 2026: 4,116 stars19 Aug 2026: 4,466 stars26 Aug 2026: 4,670 stars2 Sept 2026: 5,911 stars9 Sept 2026: 6,300 stars16 Sept 2026: 6,495 stars23 Sept 2026: 6,733 stars30 Sept 2026: 6,893 stars7 Oct 2026: 7,120 stars14 Oct 2026: 7,516 stars21 Oct 2026: 7,638 stars

335 on 1 Apr 20267,638 on 21 Oct 2026

From GitHub's daily star counts.

Checked on GitHub.

Overview

ODS installs and wires together llama-server inference, Open WebUI, a control dashboard, Whisper and Kokoro voice, n8n, Qdrant, SearXNG and ComfyUI, picking a model for the detected hardware. It runs on Linux, macOS Apple Silicon and Windows via WSL2, with an optional cloud mode using OpenAI, Anthropic or Together. The current release is a V3 pre-release installed from the main branch.

Who it is for: Self-hosters wanting a pre-wired private AI stack on a home PC or homelab

Strengths

  • One command installs inference, chat UI, dashboard, voice, workflows, RAG and image generation
  • Detects GPU and picks a model; bootstrap mode lets you chat while the full model downloads
  • Supports NVIDIA, AMD Strix Halo and Apple Silicon Metal; cloud mode for hosts without a GPU
  • States no telemetry; default outbound traffic limited to downloads, release checks and agent web searches

Weaknesses

  • V3 pre-release: installers pull current main, not a signed release
  • Requires Docker on Linux and macOS; Windows needs WSL2 and Docker Desktop
  • Intel Arc (SYCL) support is experimental
  • License is Apache 2.0 plus a Pixel ODS-only term; check LICENSING.md

What it needs

  • GPU optional
  • Needs Docker, WSL2 (Windows), Docker Desktop (Windows/macOS)
  • Models: GGUF, llama.cpp, OpenAI API, Anthropic API, Together API
  • port 3001

Also in Assistants

See all 36
Also in Assistants
RankProjectScore
1ai-job-searchClaude Code workflow that searches job boards and drafts tailored CVs and cover letters63.1k starsMIT92 out of 100
2OpenClawPersonal AI assistant reachable through Discord, Slack, Telegram, WhatsApp and more392.7k starsMIT85 out of 100
3nanobotSelf-hosted personal AI agent reachable from browser, terminal and chat apps49.3k starsMIT85 out of 100
#4openhumanRust agent harness with desktop app, built-in memory and embeddable library42.2k starsGPL-3.085 out of 100
#5ZeroClawSingle Rust binary agent runtime with 30+ channels and hardware access33k starsApache-2.080 out of 100