Awesome GitHub RepositoriesAI Query Routing

localGPT is a private AI knowledge base and retrieval-augmented generation application. It provides a local document indexer, a hybrid search engine, and an inference interface to enable chatting with private documents and managing a self-hosted information repository without sending data to external servers. The system distinguishes itself through a dual-pass verification pipeline that ensures generated answers are grounded in retrieved sources, accompanied by explicit source attribution. It employs a hybrid retrieval approach combining semantic vector search with keyword matching and rerank

Redis is a high-performance in-memory key-value store that functions as a distributed cache, message broker, and NoSQL database. It provides sub-millisecond read and write access to data stored in RAM and can operate as a vector database for indexing high-dimensional embeddings. The system supports a wide range of data storage and synchronization primitives, including the management of strings, hashes, lists, sets, and JSON documents. It enables real-time data operations through atomic transactions, hybrid persistence using snapshots and append-only logs, and high-availability configurations

Manifest is a language model provider unification system that standardizes access to multiple AI backends through a single interface. It functions as a centralized management layer for integrating various cloud-based and local model providers to simplify how applications request completions. The system provides intelligent model routing and high availability infrastructure by directing queries based on complexity and automatically triggering model fallbacks when a primary provider fails. It distinguishes itself through multi-tenant AI management, organizing agents into isolated groups with de

Promptbase es un framework de ingeniería de prompts diseñado para diseñar, probar y optimizar prompts para modelos de lenguaje de gran tamaño. Proporciona un sistema para medir la precisión y el rendimiento del modelo a través de un kit de herramientas de evaluación que compara las salidas con conjuntos de datos de verdad fundamental (ground-truth). El proyecto también incluye un pipeline de orquestación para automatizar tareas de machine learning de múltiples componentes a través de endpoints basados en la nube y una utilidad para preparar conjuntos de datos de generación aumentada por recuperación (RAG). El framework destaca por la optimización avanzada de la calidad de respuesta, utilizando generadores de cadena de pensamiento (chain-of-thought) para producir pasos de razonamiento intermedios y recuperación dinámica de ejemplos few-shot utilizando búsqueda semántica basada en embeddings. Implementa métodos de conjunto para aumentar la precisión predictiva, empleando enrutamiento de consultas basado en complejidad y agregación de voto mayoritario de múltiples variaciones de modelos. El sistema cubre capacidades más amplias en gestión de datos y automatización, incluyendo el formateo de datos externos en archivos estructurados para entrenamiento y la orquestación de pipelines de ejecución de modelos a través de utilidades de línea de comandos.

how2 is a terminal-based tool that translates plain-English questions into shell commands using AI and StackOverflow data. It functions as a command-line interface where users describe what they want to do in natural language, and the tool returns the appropriate Unix shell or PowerShell command, with support for generating multi-line Bash scripts from natural language prompts. The tool distinguishes itself through its interactive answer browsing mode, which lets users select and copy from multiple StackOverflow answers directly in the terminal. It includes a fallback search mechanism that qu