AI use cases Local AI
Local AI
Software to run open AI models on your own computer or server, plus chat interfaces on top.
- Tracked tools
- 5
- Highest score
- 73
- Caution labels
- 5
- Use cases
- 3
- 1Ollama#2 overall · AI tool73Caution
- 2LobeHub#7 overall · AI tool69Caution
- 3Open WebUI#8 overall · AI tool68Caution
- 4llama.cpp#9 overall · AI tool68Caution
- 5vLLM#24 overall · AI tool54Caution
What you can do
Software to run open AI models on your own computer or server, plus chat interfaces on top. For people who want privacy, offline use or lower costs, and for teams self-hosting models.
- Run AI models locally3 toolsollama 73
- A private AI chat for your team3 toolsollama 73
- An offline AI coding assistant4 toolsollama 73
Pick by situation
Based only on measured data for the 5 tracked tools here.
- OllamaFits if you want the highest overall score (score 73, #2 of 52 overall)
- LobeHubFits if active maintenance matters most (last push 2 Nov 2026, maintenance 78)
- OllamaFits if you want the most widely adopted option (185,623 stars, 18,859 forks)
- OllamaFits if you want the most thorough README docs (docs score 69, 19,345-character README)
What to watch out for
Scores are relative public signals; none of these tools were tested hands-on.
- CautionOllama2 critical-severity known vulnerabilities in runtime dependencies (OSV)
- CautionLobeHub3 critical-severity known vulnerabilities in runtime dependencies (OSV)
- CautionOpen WebUI13 critical-severity known vulnerabilities in runtime dependencies (OSV)
- Cautionllama.cpp12 critical-severity known vulnerabilities in runtime dependencies (OSV)
- CautionvLLMSkill/agent file instructs piping a remote script into a shell: AGENTS.md
- License to check before commercial use: LobeHub (LobeHub Community License), Open WebUI (Open WebUI License).
All scan reasons
- Ollama: 2 critical-severity known vulnerabilities in runtime dependencies (OSV)
- LobeHub: 3 critical-severity known vulnerabilities in runtime dependencies (OSV)
- Open WebUI: 13 critical-severity known vulnerabilities in runtime dependencies (OSV)
- llama.cpp: 12 critical-severity known vulnerabilities in runtime dependencies (OSV)
- vLLM: Skill/agent file instructs piping a remote script into a shell: AGENTS.md — curl -LsSf https://astral.sh/uv/install.sh | sh
Full table
Open the sortable table
| Tool (overall rank) | Use case | Score | Safety | Last push | Stars |
|---|---|---|---|---|---|
| 2 Ollamaollama/ollamaRun open models like Qwen, DeepSeek, Gemma and gpt-oss locally with one command. | Local AI | 73 | Caution | ★ 185,623 | |
| 7 LobeHublobehub/lobehubOpen-source AI chat and agent workspace for organising and running your AI agents. | Local AI | 69 | Caution | ★ 83,689 | |
| 8 Open WebUIopen-webui/open-webuiSelf-hosted ChatGPT-style web interface for Ollama and OpenAI-compatible APIs. | Local AI | 68 | Caution | ★ 157,502 | |
| 9 llama.cppggml-org/llama.cppFast LLM inference in C/C++, the engine behind many local AI apps. | Local AI | 68 | Caution | ★ 133,105 | |
| 24 vLLMvllm-project/vllmHigh-throughput, memory-efficient engine for serving LLMs. | Local AI | 54 | Caution | ★ 96,100 |
Score = relative rank (percentile) among all 52 tracked tools on maintenance, adoption and docs. Community signal is not measured yet. How we score.
Get the board every Monday
One email a week: the new top 10, the biggest score changes and every safety label that changed.
Free. Double opt-in: you confirm by email first, unsubscribe in one click.