AI 工具AI TOOLS· IMAGE-VIDEO
gufo-org/gufo
在AMD Strix Halo芯片上本地跑大模型、语音、图像和视频的引擎。Gufo is an open-source AI engine that runs text, speech, image, and video models on AMD Strix Halo hardware.
根据公开文档整理,未运行实测;费用以项目官网为准。Based on public documentation, without runtime testing. Check the project site for pricing.
能力CAPABILITIES
用一条命令下载并安装Qwen3.8等大语言模型扩展
用curl命令向本地模型提问并获取回答
在Linux和Windows上把模型跑成一个后台服务
Serve text, speech, image, and video models from a single binary
Connect any OpenAI-compatible client to the local server
Cache model outputs to speed up coding helpers interactions
Install model extensions with a single command
Run benchmarks on Strix Halo hardware to measure performance
上手GET STARTED
文档里没有找到可识别的安装命令。这类项目按发布规则不会进入榜单,只能在这里查看。No recognisable install command was found in the docs. Projects like this never enter the ranked list under our publishing rules — they are viewable here only.
通过 Podman 运行容器:`podman run --rm -it --network host ... ghcr.io/gufo-org/toolboxes/gufo-runtime:latest gufo serve llm ...`,具体命令见 README。To install, download a GGUF model from Hugging Face, then run Gufo in a Podman container with GPU access and the models folder mounted.
使用限制LIMITATIONS
以下要求与风险来自文档静态检查,未执行项目代码;扫描没有命中,不代表使用安全。Risk here is evidence, not an alarm. These findings come from static scanning of the docs; we never execute a project’s code.
限制LIMITS
未知Unknown
静态扫描STATIC SCAN
在 README、SKILL.md 和依赖清单中没有匹配到已知风险模式。No known risk patterns matched in the README, SKILL.md or dependency list.
静态扫描未发现明显风险,但不代表安全。The static scan did not find any known risk patterns in the documentation, but this does not guarantee the project is completely safe. Always review the code and dependencies before use.
项目动态PROJECT ACTIVITY
首次发现FIRST SEEN
17 NOV 202617 NOV 2026
增长GROWTH
+2.1%+2.1%
1.2k → 1.2k stars · 4 个快照1.2k → 1.2k stars · 4 snapshots
状态STATUS
持续活跃Active
AMD Strix Halo 用户现在可以用一个二进制文件运行文本、语音、图像和视频模型,且兼容 OpenAI 接口,能直接对接现有客户端。Gufo is open source under the MIT license and actively maintained with 66 commits in the last week.
{
"agents": [
{
"agent": "claude-code",
"evidence": "tree: .claude/"
}
],
"apiKey": null,
"docker": null,
"taxonomy": {
"scores": {
"design": 0,
"ai-tools": 7,
"dev-tools": 0,
"indie-web": 0,
"skill-agent": 0,
"productivity": 0
},
"primary": "ai-tools",
"secondary": "image-video"
},
"localRuntime": "un in the container, with the GPU and the models folder: ```sh gufo() {",
"skillMdTotal": 2,
"skillMdErrors": [],
"treeTruncated": false,
"categoryScores": {
"data": 1,
"agent": 0,
"media": 14,
"design": 0,
"browser": 0,
"devtool": 0,
"security": 0,
"marketing": 0,
"productivity": 0
},
"classification": [
{
"signal": "2 SKILL.md with name + description",
"weight": 0.95
},
{
"signal": "description mentions AI",
"weight": 0.2
}
],
"scannedSources": [
"readme",
".agents/skills/benchmark-model/SKILL.md",
".agents/skills/optimize-kernel/SKILL.md"
],
"skillMdFetched": 2
}