5 个仓库
Architectural patterns that intercept and process specific tool requests locally to prioritize privacy and reduce latency.
Distinct from Local-First Architectures: Distinct from general local-first data persistence; focuses on local execution of AI tools.
Explore 5 awesome GitHub repositories matching software engineering & architecture · Local-First Tool Processing. Refine with filters or upvote what's useful.
This project is a multi-provider AI gateway and proxy server that intercepts and routes requests between AI clients and various large language model providers. It functions as an API protocol translator and model router, mapping incoming requests to specific upstream providers or local runners to provide a unified interface for multiple models. The system distinguishes itself by bridging chat platforms and command line interfaces, converting messages from chat services into managed command line sessions. It further optimizes traffic by executing certain web search and fetch requests locally a
Intercepts web search and fetch requests to process them locally instead of forwarding traffic to upstream providers.
Runs all core AI functions on-device without internet, using local models for privacy and independence.
llama-fs 是一个自动化目录管理器和文件系统整理工具,使用大语言模型对文件进行分类、重命名并将其排序到结构化目录中。它作为一个本地数据流水线,分析文件内容以确定合适的文件夹层级和命名模式。 该项目强调隐私,将数据处理路由到本地模型实例,确保敏感文件信息保留在设备上,而不是发送给云服务商。它利用多模态分析来处理图像、音频和文本,使系统能够识别并分类多种媒体类型以实现自动整理。 该系统包含实时文件系统监控功能,以检测目录更改并触发自动清理任务。它支持批量处理以在单次操作中重组整个目录树,并支持递归目录合成以自动创建嵌套文件夹层级。
Utilizes local-first tool processing to route AI requests to local model instances for data privacy.
ChatLab is a self-hosted chat database and data pipeline designed to normalize, store, and analyze large-scale social conversation histories. It functions as an analytics platform that uses large language models to extract patterns and insights from messaging data imported from multiple platforms. The system distinguishes itself through an AI-powered analysis engine that utilizes vector-based history analysis and agent-based function calling to summarize conversation trends. It further identifies behavioral patterns by generating visual analytics, including heatmaps, word clouds, and activity
Provides a local-first data pipeline with stream parsing and multi-worker processing for chat history analysis.
Short video factory is a local AI content generator and automated video editing tool. It provides a production pipeline that uses large language models to transform text prompts into marketing scripts and rendered short-form videos. The system is designed for local-first execution, running all processing and asset management on the host machine to maintain data privacy. It distinguishes itself through a batch-processing workflow that can sequentially execute copywriting and rendering for multiple items using predefined presets. The software covers a broad range of media capabilities, includi
Runs all AI processing and asset management on the host machine to ensure data privacy.