📈 Github Trending
1. chopratejas/headroom
在工具输出、日志、文件和 RAG 块到达 LLM 之前对其进行压缩。减少 60-95% 的标记，答案相同。库、代理、MCP 服务器。
Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 60-95% fewer tokens, same answers. Library, proxy, MCP server.
2. Open-LLM-VTuber/Open-LLM-VTuber
通过免提语音交互、语音中断和跨平台本地运行的 Live2D 面部识别功能与任何法学硕士交谈
Talk to any LLM with hands-free voice interaction, voice interruption, and Live2D taking face running locally across platforms
1. chopratejas/headroom
在工具输出、日志、文件和 RAG 块到达 LLM 之前对其进行压缩。减少 60-95% 的标记，答案相同。库、代理、MCP 服务器。
Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 60-95% fewer tokens, same answers. Library, proxy, MCP server.
2. Open-LLM-VTuber/Open-LLM-VTuber
通过免提语音交互、语音中断和跨平台本地运行的 Live2D 面部识别功能与任何法学硕士交谈
Talk to any LLM with hands-free voice interaction, voice interruption, and Live2D taking face running locally across platforms
