8 repository-uri
Running and testing agents with a locally hosted vector database as a knowledge store for document retrieval.
Distinct from Vector Stores: Distinct from Vector Stores: focuses on local-file-based vector persistence (e.g., ChromaDB) for agent knowledge, not general vector storage.
Explore 8 awesome GitHub repositories matching data & databases · Local Vector Store Backends. Refine with filters or upvote what's useful.
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
Uses a locally hosted vector database as a knowledge store for document embedding and similarity retrieval.
PraisonAI is an autonomous AI agent platform that coordinates multiple LLM-powered agents for research, planning, and execution of complex workflows. It functions as a multi-agent orchestration framework, a workflow builder, and a Model Context Protocol server, while also providing retrieval-augmented generation through vector knowledge bases. Agents can interact via CLI, web, or standardized protocols with sandboxed code execution. The platform distinguishes itself with a rich set of agent communication protocols, including A2A, REST, WebSocket, voice and telephony integration, and MCP, allo
Provides a local ChromaDB-based vector knowledge store for retrieving document context during agent execution.
zvec is an embedded vector database engine and indexing library designed for high-dimensional similarity search. It functions as a hybrid search engine and a retrieval-augmented generation knowledge base, allowing for the storage and retrieval of dense and sparse vectors. The system is distinguished by its hybrid retrieval pipeline, which fuses vector similarity, full-text keyword matching, and scalar metadata filtering into single query operations. It supports a plugin-based model integration system for registering custom embedding models and rerankers, as well as language bindings for nativ
Manages isolated local data stores for organizing different sets of vector embeddings with local persistence.
MineContext is a context management system designed to collect, store, and retrieve multimodal data to build targeted context windows for large language models. It functions as an orchestration tool and retrieval augmented generation framework that utilizes a local vector data store to index documents and enable similarity searches. The system differentiates itself through a multimodal context collector that gathers information from screen captures, files, and version control systems. It provides mechanisms for proactive information retrieval, extracting summaries and activity records from ca
Utilizes a locally hosted vector database as a private knowledge store for document retrieval.
Langroid is a multi-agent orchestration framework and tool integration suite designed for building complex AI applications. It serves as a multi-modal integration layer that connects diverse local and remote language models with an agentic retrieval-augmented generation system. The project distinguishes itself through a collaborative message-exchange paradigm, allowing specialized agents to delegate tasks hierarchically and coordinate via structured communication. It features an advanced state management system for conversational AI, including the ability to rewind and prune conversation hist
Manages vector embeddings using a persistent local directory or in-memory collection.
Agency Swarm is a multi-agent orchestration framework and development kit designed to coordinate specialized AI agents through defined communication patterns and handoffs. It functions as a system for managing agent swarms, providing an API gateway to expose these coordinated collectives as production-ready HTTP endpoints. The project distinguishes itself through its Model Context Protocol integration layer, which connects agents to external data sources and capabilities. It implements specialized orchestration patterns, such as the orchestrator-worker model and role-based delegation, to tran
Implements local vector store backends for document retrieval to enrich agent knowledge.
Acest proiect este un instrument privat de analiză a documentelor care permite interacțiunea conversațională cu fișiere PDF prin executarea întregii inferențe și procesări a modelului de limbaj în întregime pe mașina locală. Prin rularea modelelor direct în browser sau în mediul local, asigură că datele sensibile ale utilizatorului rămân offline și inaccesibile serverelor externe sau furnizorilor de cloud terți. Sistemul utilizează RAG (Retrieval Augmented Generation) pentru a oferi răspunsuri conștiente de context, susținute de extracția textului din documentele locale și indexarea vector embedding. Această arhitectură permite căutarea semantică și regăsirea informațiilor fără a se baza pe servicii de baze de date externe sau conectivitate la internet. Dincolo de capabilitățile conversaționale de bază, instrumentul include funcționalități de observabilitate care loghează pașii interni ai raționamentului modelului și ai lanțurilor de regăsire. Acest tracing al execuției permite depanarea problemelor de performanță și optimizarea calității răspunsurilor în timpul procesului de analiză a documentelor.
Stores document embeddings in a local database to enable semantic search without external cloud services.
Easy Local RAG este un sistem pentru construirea și operarea pipeline-urilor de tip retrieval-augmented generation (RAG) private și offline. Permite utilizatorilor să efectueze căutări semantice, interogări de documente și analize conversaționale pe surse de date locale, fără a transmite informații sensibile către furnizori de cloud externi. Proiectul se distinge prin integrarea unor utilitare specializate pentru arhivarea comunicațiilor prin email personal, alături de procesarea standard a documentelor. Prin utilizarea modelelor de limbaj găzduite local și a unei baze de date vectoriale locale, menține controlul deplin asupra ingestiei datelor, indexării și inferenței modelului, asigurându-se că toată procesarea are loc în întregime pe hardware-ul utilizatorului. Sistemul suportă ingestia și normalizarea diverselor formate de fișiere, inclusiv text, PDF și JSON, pentru a facilita analiza completă a datelor. Gestionează istoricul dialogurilor multi-turn prin gestionarea stării bazată pe sesiune, permițând modelului de limbaj să mențină contextul și să ofere răspunsuri coerente în timpul interogărilor interactive.
Converts unstructured text into numerical embeddings stored in a local database to enable fast semantic similarity searches without external APIs.