Gufo
Gufo is an open-source inference engine built for AMD Strix Halo machines that runs text, vision and speech models locally, with tuned kernels and published benchmarks for each supported model. It serves models through an API so local agents can use them, and image and video generation support is in progress.
Updated
✨ Try AgentScout's free AI image generator →Good for: building voice agents, evaluating agents, images and design
Use cases
About Gufo
Gufo is listed in our models & local runtimes category and is aimed at builders. Gufo is an open-source inference engine built for AMD Strix Halo machines that runs text, vision and speech models locally, with tuned kernels and published benchmarks for each supported model. It serves models through an API so local agents can use them, and image and video generation support is in progress. Pricing, as the maker states it: Open source. Maturity: Active. We last checked the official link on 2026-10-25.
Gufo at a glance
- Category: Models & local runtimes
- Built for: Developers and teams building with AI agents
- Pricing: Open source (as the maker states it)
- GitHub: gufo-org/gufo · 918 stars (as of Oct 25, 2026)
- Official site: gufo.blog
- Listed on AgentScout: Oct 25, 2026
Gufo FAQ
What is Gufo?
Gufo is an open-source inference engine built for AMD Strix Halo machines that runs text, vision and speech models locally, with tuned kernels and published benchmarks for each supported model. It serves models through an API so local agents can use them, and image and video generation support is in progress.
How much does Gufo cost?
Gufo's pricing, as the maker states it: Open source. Open-source tools are free to use, though you may still pay for model API usage or a hosted plan. Check the official site for current plans.
Where can I find Gufo's source code?
On GitHub at gufo-org/gufo, which had 918 stars as of Oct 25, 2026.
What are alternatives to Gufo?
Similar tools include LocalAI, MiroThinker, Meta Muse Wonder, LM Studio, Mercury 3 and Strands Decider.
Facts from our link-checked listing, the GitHub repository and the official site. See something wrong? Suggest an edit.
Gufo ratings and reviews
Be the first to rate Gufo: tap 1 to 5 stars below. A written review is optional.
Gufo alternatives
Other models & local runtimes tools in our directory. See all models & local runtimes tools →
LocalAI
Self-hosted engine with an OpenAI-compatible API for running LLM, vision, voice and image models on your own hardware, including agents.
MiroThinker
Deep research agent and open models tuned for complex research and forecasting tasks.
Meta Muse Wonder
Meta's new models for personal and professional agent tasks, available via Meta Model API and Muse Code.
LM Studio
Desktop app for running local and open models, with Bionic, its agent for work and code that creates documents, slides, PDFs and software.
Mercury 3
Mercury 3 is Inception's diffusion language model, which writes many tokens in parallel rather than one at a time, reaching over 1,000 tokens per second on NVIDIA GPUs with a 1M-token context, tool calling and structured outputs. It has an OpenAI-compatible API and is also offered on OpenRouter, Baseten and Vercel, which makes it a fit for voice bots, support agents and browser agents where response speed matters. Pricing is per million input and output tokens.
Strands Decider
Strands Decider is a small, fast decision model from Strands Labs for agent workflows. Rather than asking a full LLM every time, an agent can use it to choose between options or score something on a scale in a fraction of the time, with calibrated confidence so the workflow knows when to fall back to a bigger model.
Popular searches with this tool
🏆 Ranked in: LocalAI alternatives
🔁 Listed in: LocalAI alternatives
💲 Estimate API cost: compare per-request and monthly costs for GPT, Claude, Gemini and Grok models.
Badge for makers
Built Gufo? Add this badge to your README or site. It links back to this page. About badges
