AgentIndex icon
AgentIndex
ToolsMCP ServersHOTCategoriesTrendingNewBest ListsCompareGuides
Submit Tool
ToolsMCP ServersHOTCategoriesTrendingNewBest ListsCompareGuides
Home/
LLM Infra/
ODS
ODS logo

ODS

Active·★ 7.9k·Apache-2.0·Updated 2026-11-19

ODS (Osmantic Deployment System) installs and wires together the pieces of a local AI stack so you do not assemble Ollama, Open WebUI, n8n, ComfyUI and privacy tools by hand. You get local model inference, a ChatGPT-style web UI, a dashboard for models, services, GPU status and extensions, voice, agents and workflows, RAG and private search, and local image generation. The installer picks a model for your hardware and starts the services.

On Linux and macOS it is one curl command with Docker required; on Windows a guided PowerShell script enables WSL2, installs Docker Desktop and Ubuntu, and asks before each change. ODS collects no telemetry and only goes online to fetch models and images, check releases and run searches you trigger, each of which can be turned off. It is Apache-2.0, but V3 is a pre-release installed from the main branch, not a signed release.

This write-up is based on the project's README and public repository data. We have not hand-tested the tool. Data as of 2026-11-20.

License
Apache-2.0
Latest release
v3.0.0 · 2026-09-24
Last commit
2026-11-19
Contributors
87
Forks
1,120
Open issues and PRs
803
First published
2026-02-09

Source: GitHub, npm and PyPI public APIs.

#local-ai#self-hosted#homelab#ollama#open-webui#comfyui#docker
↗ Visit site★ GitHub
01

Features

01One-command installer for Linux and macOS, guided WSL2 setup on Windows
02Local inference with a hardware-matched default model
03Dashboard for models, services, GPU status and extensions
04Bundled RAG, private search, voice, workflows and image generation
05No telemetry; optional cloud and hybrid API modes
02

Why choose it

+One command installs inference, chat UI, RAG, voice, workflows and image generation together
+Picks a model for your hardware and manages it from one dashboard
+No telemetry, with each outbound connection documented and switchable
03

Trade-offs

!V3 is a pre-release installed from main, not a signed release.
!Needs Docker and about 40 GB of free disk on Windows.
!Piping a remote script to bash is the default install path.
04

Maintenance check

ActiveChecked: 2026-11-05
Last commit
2026-11-03
Commits, last 90 days
100+
Releases, last 90 days
1
Latest release
v3.0.0 (2026-09-24)
Open issues
776
Recent issues with at least one comment
1/17
Commits per week, last 12 weeks
Commits per week, last 12 weeks: 11, 111, 225, 548, 353, 505, 368, 473, 180, 221, 198, 1

Oldest week on the left; the latest four weeks are orange. Source: GitHub commit activity.

Status rule: archived on GitHub = Archived; last commit within 90 days = Active; 91 to 365 days = Slowing; older = Stale. All figures come from the GitHub API on the date shown.

Most discussed open issues

  • #7961 dashboard-api cannot read .env when the owner's uid is not 1000, so live settings silently fall back (Open WebUI shown as critical)7 comments · 2026-10-22
  • #7968 RFC: ODS Windows Desktop — run the real dashboard and model natively on Windows (no Docker, no WSL)6 comments · 2026-10-22

Issue titles are quoted from GitHub. Open the link to check whether a problem still applies to the version you use.

05

Use cases

↳Setting up a private home AI server without assembling each service by hand
↳Keeping chat history and documents off hosted AI services
06

Alternatives

⚡Top VS:
VSboxlite★2.7k→VSyomo★1.9k→VSollaya★1.5k→VSaskimo★552→
boxlite logo
boxlite★ 2.7k
The micro-VM for AI agents — light enough to embed on your laptop, elastic enough to power an agentic cloud.
VSCompare→
yomo logo
yomo★ 1.9k
🦖 Serverless AI Agent Framework with Geo-distributed Edge AI Infra.
VSCompare→
ollaya logo
ollaya★ 1.5k
Jev-compatible API server for open decision models. Ollama for decision models: pull and serve 25 model families (Laya, pplx-decider, Clef, Winnow, coba...) locally or self-hosted behind /v1/systemone. The TypeSafe SDK works unchanged: set its base URL and pick an open model. CLI, desktop app, Docker, MCP server, public bench.
VSCompare→
askimo logo
askimo★ 552
AI desktop app for chat, RAG, Skills, MCP tools, and agents. Support multiple LLMs (Anthropic, OpenAI, VertexAI, vLLM, Nvidia NIM, Gemini, OpenRouter)
VSCompare→
whodb logo
whodb★ 5.1k
Where data access meets operational intelligence
VSCompare→
ArcReel logo
ArcReel★ 6.7k
AI Agent 驱动的开源可自部署视频工作台:将小说与剧本转为角色、场景、道具资产、分镜、视频和剪映草稿,支持跨镜头一致性、多供应商与费用追踪 | Self-hosted AI video workspace for stories, storyboards and short-form video production
VSCompare→
vexa logo
vexa★ 3.0k
Open-source meeting transcription API for Google Meet, Microsoft Teams & Zoom. Auto-join bots, real-time WebSocket transcripts, MCP server for AI agents. Self-host or use hosted SaaS.
VSCompare→
skillhub logo
skillhub★ 5.4k
Self-hosted, open-source agent skill registry for enterprises. Publish & version skill packages, govern with RBAC and audit logs, deploy on-premise with Docker or Kubernetes.
VSCompare→
See all alternatives →

Comments

Log in to leave a comment

No comments yet. Be the first!

On this page
01Features02Why choose it03Trade-offs04Maintenance check05Use cases06Alternatives
Osmantic /
ODS
↗

One installer that turns a PC, Mac or Linux box into a private local AI server

7.9k1.1kApache-2.0
Last commit3d ago
StatusActive
CategoryLLM Infra
Contributors87
Latest releasev3.0.0
Links
Documentation↗Discussion↗Issues↗Releases↗
Cloud Infrastructure
Ad

Deploy on DigitalOcean

Host your MCP servers, Docker containers, and AI agents with $200 free credit over 60 days.

Claim $200 Free Credit
© 2026 AgentIndex.app|Built by a 10-year iOS Developer.
Best by use caseAboutContactAdvertisePrivacy PolicyTerms of UseQYSGitHubBuy me a coffee ☕

Browse by Category

MCP ServersCode AssistantWorkflow AutomationRAG / Knowledge BaseMulti-AgentBrowser AutomationLLM InfraDev ToolingObservability

Not affiliated with Anthropic, OpenAI or Microsoft.