LocalAGI
LocalAGI is a self-hosted platform for creating local AI assistants, chatbots and agents that run entirely on your own hardware, with no cloud services or API…
Platform availability
Available on 1 of 10 platforms
- Unraid (not listed)
- TrueNAS (not listed)
- Umbrel (not listed)
- ZimaOS (not listed)
- Proxmox
- Helm (not listed)
- Mac (not listed)
- Windows (not listed)
- Linux (not listed)
- Any server (not listed)
Health score?A 0-100 score computed nightly from four factors: maintained (40%: recent commits and steady activity), popular (25%: GitHub stars, log scale), easy to install (20%: platforms, install notes, setup guides, Docker image) and light to run (15%: minimum RAM, ARM support). When the source code has been checked, a fifth factor, security check (20%: automated scan for committed secrets, unsafe desktop-app settings, known-vulnerable dependencies and project hygiene; any serious finding caps it at 20), is added. Factors without data are left out and the rest are rescaled.
62/100 Good
- Maintained
- 99last commit 36 days ago
- Popular
- 662,016 GitHub stars
- Easy to install
- 251 install platform, install notes
- Light to run
- No data
- Security check
- 201 serious finding, 6 minor, CI, tests
Based on 4 of 5 factors.
Security check: 1 serious finding
- Uses github.com/gofiber/utils v1.1.0, which has a known critical vulnerability (Go)
Automated checks on commit 7aa0c8f, 23 Oct 2026. Not an audit.
Availability: platform listings confirmed today
- GitHub stars
- 2,016
- Open issues
- 69
- Last commit
- 2026-10-16
- Latest release
- v2.9.0
- License
- MIT
- Activity
- stale
Checked 4 days ago - source: GitHub (mudler/LocalAGI)
Resources & Compatibility
Requirements not published yet.
First-install notes
- Start the server before using the app Run local-agi serve so LocalAGI is listening; without it, the UI or other tools have no backend to talk to. If the server is reachable from other machines, set API_KEYS (a list of access keys) so only people with your keys can call it. source
- Set MODEL_NAME for the model you installed If you are not using the default model, set MODEL_NAME (the name of the AI model to load) before running local-agi serve so the app loads the AI model you actually want. Using the wrong name can cause the app to fail when it tries to find or start the model. source
- Use --state-dir for a persistent data folder Use --state-dir to tell LocalAGI where to keep its stored data, such as settings and task information. If that folder is temporary, cleared, or lost, your saved LocalAGI data can disappear. source
Fetched 53 days ago - each note links to its source
Variants
Alternatives (12)
- AnythingLLM - AnythingLLM is a local, all-in-one AI app for self-hosters that works with any large language model, providing document chat, retrieval-aug…
- ChatGPT - ChatGPT is a generative artificial intelligence chatbot developed by OpenAI and launched in 2022.
- DeepSeek - DeepSeek is a state-of-the-art AI assistant designed to provide intelligent, conversational support across diverse tasks.
- Euria - Privacy-first AI assistant with chat, writing, transcription, summarization, email, and document tools, hosted in Switzerland and compliant…
- GPT4ALL - GPT4All runs open-source large language models (LLMs) privately on your own hardware, providing a local chat interface and server that need…
- Google Gemini - Gemini gives you direct access to Google AI.
- Hermes Agent - Hermes Agent is a self-improving AI agent by Nous Research that creates and refines skills from experience, builds a persistent model of yo…
- LM Studio - LM Studio is an application for running and experimenting with local large language models (LLMs) such as gpt-oss, Llama, Gemma, Qwen, and…
- Lumo by Proton - Privacy-first AI assistant with zero-access encryption, no logging or profiling, open-source code, and user-controlled conversations, subje…
- Microsoft Copilot - Microsoft Copilot, formerly known as Bing Chat, is an AI chat interface used to converse with Microsoft hosted OpenAI and Claude models wit…
- Ollama - Ollama is a local runtime for large language models (LLMs) that provides an application programming interface (API) and command-line interf…
- OpenClaw - OpenClaw is an open-source, self-hosted AI assistant gateway that connects large language models (LLMs) to Discord, Telegram, and WhatsApp,…
Checked 40 days ago - source: AlternativeTo
Common questions
What must be running before LocalAGI’s UI or other tools can work?
Run local-agi serve so LocalAGI is listening. Without that command, the UI and other tools have no backend to talk to.
How should I protect a LocalAGI server that other machines can reach?
Set API_KEYS to a list of access keys so only people with your keys can call it.
How do I make LocalAGI load a non-default model?
Set MODEL_NAME to the name of the AI model you installed before running local-agi serve. Using the wrong name can cause the app to fail when it tries to find or start the model.
Where do I point LocalAGI to store settings and task data?
Use --state-dir to tell LocalAGI where to keep its stored data, such as settings and task information. If that folder is temporary, cleared, or lost, your saved LocalAGI data can disappear.
Why can a LocalAGI container fail to reach LocalAI on Docker Desktop?
On Docker Desktop, localhost inside the LocalAGI container is not your host. Use host.docker.internal, or put both containers on one Compose network and use the service name.
Answers sourced from github.com, wrkode.github.io
Community
Collected 48 days ago - public community threads