AI-FanGe / OpenAIglasses_for_NavigationLinks
a open framework for blind navigation based on esp32
☆938Updated 3 weeks ago
Alternatives and similar repositories for OpenAIglasses_for_Navigation
Users that are interested in OpenAIglasses_for_Navigation are comparing it to the libraries listed below
Sorting:
- 本项目通过将 MCP 协议转换为 MQTT 协议，我们能 够利用强大的大型语言模型（LLMs），就能轻松操控您的智能家居、机器人或其他硬件设备。☆338Updated 11 months ago
- 小智AI MCP功能扩充，包含Onvif摄像头画面截取识别，PC软件控制等☆109Updated last month
- 小智AI客户端，目前主要用于MCP的对接☆214Updated this week
- Xiaozhi MCP sample program☆288Updated 3 weeks ago
- Desk-Emoji is a truly open-source AI desktop robot featuring an emoji screen, a two-axis console, and LLM capabilities for voice chat.☆513Updated last month
- ☆236Updated this week
- Build your own AI friend☆702Updated 5 months ago
- 如果想体验小智项目，或者开发server端测试的同志，可以使用这个web端damo 体验下。 语音端已经完成，文字端完成，可以语音加文字输出。 等迭代慢慢完善。欢迎PR☆162Updated 5 months ago
- 百聆 是一个类似GPT-4o的语音对话机器人，通过ASR+LLM+TTS实现，集成DeepSeek R1等优秀大模型，时延低至800ms，Mac等低配置也可运行，支持打断☆1,525Updated 4 months ago
- Fogsight is an AI agent and animation engine powered by Large Language Models.☆1,768Updated 3 weeks ago
- 基于小智AI智能体 实现的流浪地球MOSS版本☆165Updated 2 weeks ago
- a framework combining abilities of QwenVL and Deepseek Apis to enable a visual interaction using deepseek model.☆108Updated 8 months ago
- Sample Repository for the AlibabaCloud Bailian Speech SDK☆318Updated 3 weeks ago
- A Python-based Xiaozhi AI for users who want the full Xiaozhi experience without owning specialized hardware.☆2,935Updated 2 weeks ago
- RTC AIGC Demo☆226Updated last week
- 终极愿景：目标是创造一个全方位服务于用户全场景的 AI 全能管家AGI—“小粒”。除了不具备物理形态外，“小粒”将提供与远程视频通话中的真人几乎无异的体验，具备思考、情感交流、视觉、听觉以及模拟触觉反馈等能力，并能够游走在任何家庭、车辆等场景显示设备上自由与人交互。功能覆盖…☆139Updated 3 months ago
- VoiceCanvas，支持Stripe支付的文本转语音系统，支持声音克隆，支持50+语言，支持选择音色，代码100%开源☆399Updated 3 months ago
- ☆23Updated 7 months ago
- MultiAgentPPT 是一个集成了 A2A（Agent2Agent）+ MCP（Model Context Protocol）+ ADK（Agent Development Kit） 架构的智能化演示文稿生成系统，支持通过多智能体协作和流式并发机制☆1,415Updated 2 months ago
- AI virtual human bot framework(public)☆272Updated 4 months ago
- 帮助视觉障碍者识别物品，障碍物提醒☆86Updated 8 months ago
- 实时STT，连接OpenAI接口/智谱AI（流式LLM）和GPT-SOVITS/Edge-TTS，通过网页的方式，进行跨网络的服务调用，实现实时对话的效果☆425Updated 11 months ago
- The fastest digital human algorithm, now on your desktop.☆558Updated 2 months ago
- 一个基于小智、xiaozhi-server的Android、IOS语音对话应用,支持实时语音交互和文字对话。现在是flutter版本，打通IOS、Android端。请同志们动动小手，点点小星星，予以鼓励。☆1,220Updated 2 months ago
- Speech to Text but with all the bells and whistles and most importantly AI! AI will clean up your filler words, edit and will refine what…☆326Updated 9 months ago
- [NeurIPS 2025] OmniTalker: Real-Time Text-Driven Talking Head Generation with In-Context Audio-Visual Style Replication☆395Updated 2 months ago
- 使用esp32+ollama实现本地模型的对话以及联网+工具调用☆152Updated 4 months ago
- An common framework for voice and text interactions with LLMs☆98Updated last year
- ☆289Updated last year
- 虾哥的小智 AI 聊天机器人（XiaoZhi AI Chatbot）- python客户端☆104Updated 6 months ago