Awesome GitHub RepositoriesSemantic Query Routing

This project provides a dockerized AI workflow stack and orchestration templates for deploying a self-hosted AI environment. It establishes a localized infrastructure for building autonomous agents and model chains that process private data on-premises without external cloud dependencies. The environment is designed to support autonomous agent development, allowing models to dynamically select tools, execute shell commands, and interact with local file systems. It includes integrated vector database support to enable retrieval augmented generation and private document analysis. The stack cov

Omi is an open-source wearable AI platform that captures audio and screen data to provide real-time conversational assistance and memory. It integrates a wearable hardware development kit with a vector memory database and large language model capabilities to create a persistent digital record of user interactions. The platform is distinguished by its BLE audio streaming pipeline, which transmits raw audio from wearable hardware for real-time transcription and speaker identification. It utilizes a plugin-based agent tool framework that allows AI assistants to autonomously invoke custom functio

LanceDB is a vector database and columnar data store designed to function as a versioned dataset manager and vector search engine. It serves as a high-performance backend for indexing and retrieving high-dimensional embeddings, providing the foundation for machine learning data pipelines. The system distinguishes itself through a combination of cloud-native object storage and immutable version tracking, allowing for data time-travel and reproducible AI experiments. It integrates hybrid search capabilities, merging dense vector similarity with BM25 full-text search and SQL-like scalar filters

XianyuAutoAgent is a multi-agent orchestration framework and large language model chatbot designed to automate customer service and sales interactions on a marketplace platform. It functions as a system of specialized AI entities, including context-aware conversational agents and automated price negotiation bots, to manage peer-to-peer conversational commerce. The framework distinguishes itself through an intent-based routing mechanism that dispatches queries to specialized agents and utilizes a multi-expert collaborative decision process to determine response strategies. It features dedicate

Agent Squad is a multi-agent system orchestrator and language model agent orchestration framework. It serves as an AI workflow automation engine and tool integration layer designed to coordinate teams of specialized agents to solve complex tasks through routing, parallel execution, and state management. The project is distinguished by its ability to dynamically compose purpose-specific agents on-demand and route requests based on intent, language, or domain expertise. It supports advanced coordination patterns, including parallel subtask distribution, sequential task pipelines, and the abilit

Pixie is an open-source observability platform for Kubernetes that uses eBPF to automatically capture telemetry data from clusters without requiring any manual instrumentation or code changes. It functions as an eBPF telemetry collector, a continuous application profiler, a network traffic analyzer, and a scriptable telemetry query engine, all within a single Kubernetes-native tool. The platform distinguishes itself through several integrated capabilities. It continuously samples stack traces from compiled-language code to identify CPU performance bottlenecks, visualizing the results as inter

Genkit este un framework pentru aplicații LLM și un toolkit pentru dezvoltatori de AI generativ, conceput pentru construirea de aplicații AI de producție. Acesta servește drept orchestrator de fluxuri de lucru AI care coordonează apelurile către modele și utilizarea instrumentelor agentice prin fluxuri de execuție type-safe. Proiectul oferă o interfață unificată pentru modele și o arhitectură de plugin-uri pentru a standardiza accesul la diverse modele de limbaj mari (LLM), vector stores și backend-uri de telemetrie. Se distinge printr-o suită dedicată de observabilitate pentru trasarea pașilor de execuție și un toolkit pentru dezvoltatori pentru prompting, debugging și evaluarea logicii AI printr-o interfață locală. Framework-ul acoperă o suprafață largă de capabilități, inclusiv orchestrarea agenților cu tool-calling și delegarea către sub-agenți, retrieval-augmented generation (RAG) prin integrarea bazelor de date vectoriale și generarea de output structurat folosind validarea bazată pe schemă. Include, de asemenea, sisteme pentru gestionarea stării sesiunilor, streaming de răspunsuri bazat pe evenimente și capacitatea de a expune fluxurile AI ca endpoint-uri HTTP scalabile. Dezvoltarea este susținută de o interfață în linie de comandă (CLI) pentru rularea funcțiilor și gestionarea log-urilor.

Plano is an AI agent orchestrator and LLM gateway proxy that unifies access to multiple AI providers through a single interoperable interface. It functions as a model routing engine that decouples applications from specific vendors using semantic aliases, allowing traffic to be shifted between providers without modifying application code. The system distinguishes itself with intent-based agent routing, which directs prompts to specialized agents based on semantic analysis. It features an interceptor-based filter chain system that acts as guardrail middleware to enforce safety policies, rewrit

ruvector este un vector store și o bază de date graf bazată pe Rust, concepută pentru inferență locală și căutări de tip nearest neighbor. Utilizează o arhitectură de bază de date graf vectorială și un index de rețele neuronale grafice pentru a rafina clasamentele de căutare prin atenție structurală. Sistemul include un simulator de circuite cuantice accelerat hardware pentru execuția simulărilor de tip state-vector și a modelelor complexe de căutare, alături de un motor de inferență WebAssembly pentru rularea căutărilor vectoriale și execuția modelelor direct în browserele web. Proiectul folosește un format de container cognitiv care grupează modelele, datele și un microkernel bootabil într-un singur binar pentru deployment. Acesta dispune de instrumente specializate de configurare a modelelor, inclusiv o metodă de consolidare a ponderilor pentru a preveni uitarea catastrofală și un mecanism de adaptare ușor pentru ajustarea instantanee a ponderilor. Sistemul acoperă o gamă largă de capabilități, inclusiv căutarea vectorială accelerată hardware, interogarea relațiilor grafice și parsarea documentelor științifice pentru extragerea LaTeX și MathML. De asemenea, oferă înlănțuire de dovezi criptografice pentru verificarea modificărilor de date, sincronizarea metadatelor bazată pe Raft pentru disponibilitate ridicată și compresia datelor cu rezoluție pe niveluri pentru gestionarea costurilor de stocare.

bRAG-langchain is a framework for building retrieval augmented generation pipelines using LangChain to connect documents with language models. It functions as a vector store orchestrator that manages document indexing and retrieval strategies to improve context accuracy. The system implements an advanced retrieval pipeline featuring a semantic query router that directs natural language inputs to specific data sources or prompts. It includes a metadata filtering engine that translates natural language queries into structured schemas to narrow search results. The project covers hybrid search o

Koog is an LLM agent framework used to build autonomous entities that execute tool-based workflows. It utilizes a graph-based workflow engine to define agent behaviors and decision paths as a directed graph of nodes and edges. The framework distinguishes itself through a model provider orchestrator that enables dynamic switching, load balancing, and automatic fallbacks between different AI backends. It implements the Model Context Protocol to connect agents to remote tool servers and features a RAG memory system using vector embeddings to maintain long-term conversation context. The project