Best self-hosted AI tools on GitHub
This page is built for teams that want control. Instead of browsing generic AI repositories, you can use this shortlist to compare self-hosted AI tools that are actually earning developer attention across local LLM workflows, agent runtimes, RAG stacks, and deployable inference layers.
Why Teams Care
Self-hosted AI tools matter when you need more control over data handling, compliance, model choice, deployment topology, and cost.
What To Look For
Prioritize active maintenance, clear deployment docs, practical architecture, and evidence that teams are adopting the project beyond demos.
Best For
Platform teams, AI product teams, privacy-sensitive organizations, and builders who want to run AI infrastructure on their own stack.
Top Self-Hosted AI Tools
A practical shortlist of open source AI repositories for teams that care about deployment control and infrastructure ownership.
langgenius/dify
TypeScript AIBuild Agentic workflows, RAG pipelines, with rich AI model and tool support on one collaborative workspace. Deploy on cloud, VPC, or self-hosted, so teams move from prototype to production without rebuilding the stack.
Fresh pushes are keeping momentum high.
HKUDS/nanobot
Python AIUltra-lightweight, open-source, self-hosted personal AI agent framework in Python with WebUI, tools, memory, MCP, multi-agent workflows, automation, and chat apps
Fresh pushes are keeping momentum high.
moeru-ai/airi
TypeScript AI💖🧸 Self hosted, you-owned Grok Companion, a container of souls of waifu, cyber livings to bring them into our worlds, wishing to achieve Neuro-sama's altitude. Capable of realtime voice chat, Minecraft, Factorio playing. Web / macOS / Windows supported.
Fresh pushes are keeping momentum high.
siyuan-note/siyuan
TypeScript AIAn open-source, privacy-first, self-hosted knowledge workspace where humans and AI agents work together 开源、隐私优先、自托管的知识工作空间，让人与智能体在此协作
Fresh pushes are keeping momentum high.
odysseus-dev/odysseus
Python AISelf-hosted AI workspace.
Fresh pushes are keeping momentum high.
khoj-ai/khoj
Python AIYour AI second brain. Self-hostable. Get answers from the web or your docs. Build custom agents, schedule automations, do deep research. Turn any online or local LLM into your personal, autonomous AI (gpt, claude, gemini, llama, qwen, mistral). Get started - free.
Fresh pushes are keeping momentum high.
Anil-matcha/Open-Generative-AI
JavaScript AIUnrestricted Open-source alternative to AI video platforms — Free AI image & video generation studio with 500+ models (Flux, Midjourney, Kling, Sora, Veo). No content filters. Self-hosted, MIT licensed.
Fresh pushes are keeping momentum high.
topoteretes/cognee
Python AICognee is the open-source AI memory platform for agents. Give your AI agents persistent long-term memory across sessions with a self-hosted knowledge graph engine.
Fresh pushes are keeping momentum high.
airbytehq/airbyte
Python AIOpen-source data movement for ELT pipelines and AI agents — from APIs, databases & files to warehouses, lakes, and AI applications. Both self-hosted and Cloud.
Fresh pushes are keeping momentum high.
TabbyML/tabby
Rust AISelf-hosted AI coding assistant
Fresh pushes are keeping momentum high.
n8n-io/self-hosted-ai-starter-kit
AIThe Self-hosted AI Starter Kit is an open-source template that quickly sets up a local AI environment. Curated by n8n, it provides essential tools for creating secure, self-hosted AI workflows.
Fresh pushes are keeping momentum high.
blinkospace/blinko
TypeScript AIAn open-source, self-hosted personal AI note tool prioritizing privacy, built using TypeScript .
Fresh pushes are keeping momentum high.
How To Evaluate Self-Hosted AI Tools
The best self-hosted AI tool is not always the largest repository. In practice, teams care more about deployment clarity, control surfaces, maintainability, and whether the project can fit into a real operating environment.
A good evaluation flow is simple: shortlist by momentum, inspect the repository detail page, review recent updates, and compare alternatives. That is the fastest way to narrow a noisy category into a usable shortlist.
Common Categories On This Page
You will usually see self-hosted copilots, local LLM runtimes, agent frameworks, RAG stacks, inference gateways, and private AI development platforms.
If you want broader discovery, open Best Open Source AI Tools or the live AI tools board to compare this niche against the wider AI ecosystem.
FAQ
What counts as a self-hosted AI tool?
In practice this includes open source AI agents, local LLM runtimes, RAG stacks, model gateways, inference layers, and developer tools that teams can deploy and operate on their own infrastructure.
Why use a self-hosted AI tool instead of a hosted API product?
Teams often choose self-hosted AI tools for more control over data, infrastructure, deployment patterns, customization, and long-term cost structure.
How does GHTrending rank self-hosted AI tools?
The ranking emphasizes recent momentum, activity, and developer interest so teams can discover self-hosted AI projects that are actively moving now, not only the oldest or biggest repositories.
Who is this page for?
It is useful for engineering teams, platform teams, AI builders, indie hackers, and technical evaluators comparing self-hosted AI software they may deploy themselves.