OSSEAN

llama-gpt

getumbrel/llama-gpt

A self-hosted, offline, ChatGPT-like chatbot. Powered by Llama 2. 100% private, with no data leaving your device. New: Code Llama support!

AI apps and agentsFor consumersAlternative to ChatGPTSelf-hostable
View on GitHubVisit apps.umbrel.com

Ship status

Gone silent

No push in over 120 days. A quiet repo may also be a finished one.

Last push
Apr 23, 2024
892 days ago
Ship score
8/100
How it is calculated →
Stars, last 7 weeks
Stars, weekly: 10,937 → 10,936 (Aug 18 – Sep 29, 2026)
−2 stars in the 28 days to 2026-09-29

Shipping: pushed in the last 30 days · slowed: quiet for 31–120 days · silent: no push in over 120 days.

Repo facts

What GitHub reports.

Stars
10.9K
Forks
704
Open issues
97
Watchers
77
Primary language
TypeScript
License
MIT License
Created
Jul 22, 2023
Owner
getumbrel · Organization

Open issues are the issues and pull requests GitHub reports as open; watchers are the accounts subscribed to the repository. OSI-approved license — GitHub’s own license field, not legal advice. 208 startups in the directory ship primarily in TypeScript.

Topics

#ai#chatgpt#code-llama#codellama#gpt#gpt-4#gpt4all#llama#llama-2#llama-cpp#llama2#llamacpp#llm#localai#openai#self-hosted

How it got here

What the classifier decided, and when.

Classified as an open-source startup by Jev, TypeSafe’s classifier, on Sep 22, 2026 — os_startup 90%, self-hostable 97%, hosted offering 15%. The classifier reads only the repository’s name, description and homepage; it can be wrong, and a probability under 0.5 puts a listing in the review queue rather than out of the directory.

Listed since the 2025-09 crawl. Answered by jev-1.13.0. How the classification works →

Embed your status

Put this badge on your README.

OSSEAN ship status: silent — last push 2024-04-23This is the badge for getumbrel/llama-gpt, as served from the URL below.
[![OSSEAN: silent](https://ossean.com/badge/getumbrel/llama-gpt.svg)](https://ossean.com/getumbrel/llama-gpt)

Updates daily, from the last push GitHub saw.

Honest caveat: GitHub proxies README images through Camo and rewrites the anchor with rel=“nofollow”, so a README embed sends you referral traffic and brand, not link equity. The link is dofollow wherever you control the markup — your docs, your landing page, your blog. The snippet uses your frozen OSSEAN slug, so it survives a repo rename.

Related projects

More in the same current.

botpressbotpress/botpressStars: 14.9KThe open-source hub to build & deploy GPT/LLM Agents ⚡️Still shippingTypeScriptpushed todayAgentGPTreworkd/AgentGPTStars: 36.3K🤖 Assemble, configure, and deploy autonomous AI Agents in your browser.Gone silentTypeScriptpushed 17mo agodifylanggenius/difyStars: 157.7KBuild 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.Still shippingTypeScriptpushed todayOpenHandsOpenHands/OpenHandsStars: 89.8K🙌 OpenHands: AI-Driven DevelopmentStill shippingTypeScriptpushed todaylobehublobehub/lobehubStars: 83K🤯 LobeHub is your Chief Agent Operator, organizing your agents into 7×24 operations by hiring, scheduling, and reporting on your entire AI team.Still shippingTypeScriptpushed todayLibreChatLibreChat-AI/LibreChatStars: 45.2KEnhanced ChatGPT Clone: Features Agents, MCP, Skills, DeepSeek, Anthropic, AWS, OpenAI, Responses API, Azure, Groq, o1, GPT-5, Mistral, OpenRouter, Vertex AI, Gemini, Artifacts, AI model switching, message search, Code Interpreter, langchain, DALL-E-3, OpenAPI Actions, Functions, Secure Multi-User Auth, Presets, open-source for self-hosting. ActiveStill shippingTypeScriptpushed today
Explore all 725 →