Open-source alternatives to Fireplexity

Riot is a Go-based distributed search engine and indexing server designed for full-text indexing and retrieval. It functions as a retrieval system that sorts documents by relevance using BM25 ranking algorithms, term frequency, and inverse document frequency. The engine provides specialized support for the Chinese language, featuring concurrent text segmentation and phonetic Pinyin mapping to match romanized input with characters. It utilizes a distributed architecture that employs hash-based index sharding to balance data load and throughput across multiple server nodes. The system covers a

Danswer is an LLM application framework and RAG engine that provides a self-hosted interface for connecting large language models to private data. It serves as an enterprise AI chat interface and agent orchestrator, enabling the creation of specialized assistants with custom instructions and knowledge bases. The platform differentiates itself through an observability dashboard for tracking query history and token consumption, as well as a white-labeled interface for customized branding. It includes a multi-step research workflow for producing long-form reports and a sandboxed environment for

FreeAskInternet is a self-hosted AI search aggregator and answer generation platform. It uses a language model to synthesize results from multiple web search engines into a single, comprehensive response, integrating with SearXNG to gather raw web data. The system is designed for local deployment through Docker containerization, allowing the search aggregator and user interface to run in isolated environments. It supports local language model integration and provides a provider-agnostic interface to switch between different local or remote model backends. The platform handles search and synt

This project is an HTTP request forwarder designed to act as a middle layer for routing traffic to OpenAI services. It functions as a proxy that manages network connectivity, allowing users to bypass restrictions while centralizing API access and request handling. The service distinguishes itself by supporting real-time stream forwarding, which delivers incremental data chunks to clients as they are generated. It also incorporates middleware for content moderation, enabling the inspection and filtering of data streams to enforce safety guidelines before content reaches the end user. The arch

vue-meta is a metadata manager for Vue.js applications that coordinates the injection, deduplication, and merging of HTML head and body tags. It serves as a document head controller, allowing developers to define and update titles, meta tags, link tags, styles, and scripts within a component architecture across both client-side and server-side environments. The library distinguishes itself through a hierarchical merging system where child components can override metadata defined by parent components. It ensures document integrity using identifier-based deduplication to prevent duplicate tags

Hono is a minimal JavaScript HTTP framework designed for building web servers across multiple runtimes, including Node.js, edge runtimes, and serverless platforms. It functions as a cross-runtime web server and a web standard API wrapper, normalizing various runtime request and response objects into standard Web API signatures. The project serves as an HTTP middleware orchestrator and request handler, utilizing a middleware-based request pipeline and hierarchical route mounting to create modular server structures. It distinguishes itself through a runtime-agnostic event wrapper that ensures c

Onyx is an enterprise-grade AI platform designed for knowledge management, search, and autonomous agent orchestration. It functions as a centralized system that aggregates unstructured organizational data, enabling secure, context-aware retrieval and interaction across internal documents and communication history. By integrating retrieval-augmented generation with multi-model orchestration, the platform provides a unified interface for teams to query internal knowledge bases and execute complex, multi-step business processes. The platform distinguishes itself through a focus on private infras

This project provides a programmatic client for interacting with AI-powered search services. It is designed to automate research tasks by facilitating batch query processing, real-time response streaming, and document content analysis through both synchronous and asynchronous interfaces. To ensure continuous service access and high throughput, the system includes an automated account provisioning and lifecycle management framework. This allows for the rotation of authenticated sessions and the automatic renewal of credentials, which helps maintain access during high-volume operations. The pr

Perplexica is an AI-powered search engine that synthesizes real-time web results into coherent, cited summaries. By utilizing large language models and retrieval augmentation, the platform gathers information from the live internet to provide accurate answers to complex user queries, ensuring that all generated content includes verifiable source citations. The project functions as a search orchestration platform that aggregates data from multiple sources and exposes these capabilities through standard endpoints. This allows for automated data integration, enabling external software to retriev

Vespa is a distributed search engine, vector database, and machine learning ranking engine. It serves as an AI search platform designed to handle large-scale document indexing and complex query processing across a cluster of nodes, combining keyword retrieval with high-dimensional embedding storage for semantic similarity search. The platform distinguishes itself by integrating machine learning models directly into the search pipeline to perform real-time inference and ranking. It converts these models into ranking expressions to score and order results based on relevance, while providing a s

This project is an on-device AI SDK providing a framework for running large language models, vision models, and speech models locally. It serves as an orchestration layer for local LLM execution, ensuring data privacy and offline availability by utilizing hardware acceleration on the device. The SDK is distinguished by its comprehensive voice and multimodal capabilities, including a coordinated voice pipeline for activity detection, speech-to-text, and text-to-speech synthesis. It also provides a dedicated implementation kit for local retrieval-augmented generation and tools for processing co

OpenGpt is an agent orchestration platform and multimodal interface designed for building and deploying specialized AI personas. It allows users to create task-oriented agents with custom system prompts and behavioral constraints to automate professional, creative, and technical workflows. The project features a prompt engineering workflow that transforms simple user inputs into structured instructions to improve model accuracy. It integrates retrieval-augmented generation by connecting vector databases to the chat interface, enabling context-aware responses from private datasets. The platfo

OpenDeepSearch is an autonomous research platform and search orchestration engine that connects large language models with live web data. It functions as an agentic information retrieval tool designed to automate the gathering, structuring, and synthesis of web information to resolve complex queries. The system differentiates itself through iterative multi-hop querying, which allows the agent to execute sequences of dependent searches where previous results refine subsequent requests. It features a semantic reranking pipeline that uses embedding models to prioritize the most relevant content

OpenSquilla is an LLM agent orchestration framework designed to coordinate multi-step AI workflows and tool execution using directed acyclic graphs. It functions as a centralized system for managing specialized skill packages and executing complex reasoning sequences. The project distinguishes itself through a routing gateway that directs tasks to different AI providers based on complexity, cost, and performance. It utilizes a multi-tier AI memory system that organizes working, episodic, and semantic knowledge using local embeddings and SQLite, alongside a secure execution sandbox that isolat

Search-R1 is a distributed training system and reinforcement learning framework designed to create search-augmented language models. It provides an architecture for scaling model workloads across head and worker nodes while optimizing how models interleave internal reasoning with external tool calls. The system focuses on refining model behavior through custom reward signals and reinforcement learning to improve tool-use formatting and information retrieval. It implements an interleaved reasoning-search loop that allows models to alternate between internal thought generation and external data

This project is a framework for building custom AI chatbots capable of PDF document analysis. It implements Retrieval Augmented Generation to connect a large language model to private document data. The system utilizes graph-based agent orchestration to control conversation flow and decision logic. It maintains context across interactions through thread-based state management and delivers AI responses to the user interface via real-time streaming. The project covers PDF document ingestion through chunk-based processing and vector-store retrieval. It includes mechanisms for query-based data r

AdalFlow is an autonomous AI agent framework and LLM application library designed for building modular workflows. It serves as a model-agnostic interface and RAG pipeline orchestrator, allowing users to develop ReAct agents that utilize iterative reasoning and external tool execution to solve complex tasks. The project distinguishes itself through a prompt optimization system that uses textual gradient descent to automatically refine prompt templates and few-shot examples. It treats model feedback as a differentiable signal, enabling a form of LLM backpropagation to iteratively improve output

This project is a browser extension and toolset designed to integrate real-time web search results and extracted page content into large language model prompts. It functions as a web search integrator and content parser that feeds current internet data into conversational AI interfaces to ensure responses are grounded in evidence. The system includes a prompt template manager for storing and executing pre-defined structures that trigger automated web crawls. It enables deep research workflows by performing comprehensive searches to generate detailed responses supported by citations and links

GPTCache is a semantic caching layer and response optimizer for large language models. It functions as pluggable middleware for orchestration frameworks, utilizing vector database caching to store and retrieve model responses based on the semantic similarity of prompts rather than exact text matches. The system uses embeddings to determine cache hits by comparing the distance between new queries and stored vectors. It employs a hybrid storage model that persists original prompts in relational databases while maintaining high-dimensional embeddings in vector stores. The project covers a broad

Presenton is an AI-powered presentation engine and API designed to transform natural language prompts, uploaded documents, and structured data into professional slide decks. It functions as a generation service that leverages large language models to automate the creation of outlines, slide content, and visual assets. The system is distinguished by its support for both cloud-based and self-hosted infrastructure, allowing for the integration of local language models and image generators to ensure data privacy. It implements a Model Context Protocol server, enabling external AI agents to trigge

This project is a Model Context Protocol server that provides large language models with neural web search and webpage content extraction capabilities. It implements a standardized interface to expose research tools and resources to compatible clients. The server integrates a neural search engine to retrieve real-time internet data using semantic embeddings rather than keyword matching. It includes specialized utilities for company intelligence and reasoning-based deep research, enabling the collection and synthesis of organizational data and professional profiles. The system covers a broad

Qbot is a multi-purpose platform designed to support automated recruitment, quantitative trading, and distributed service orchestration. It functions as a comprehensive framework that integrates artificial intelligence into specialized workflows, enabling users to build and deploy systems for candidate screening, financial strategy execution, and context-aware knowledge retrieval. The platform distinguishes itself through a modular architecture that combines high-performance distributed communication with domain-specific automation. It provides a robust foundation for managing microservices t

This project serves as an educational resource and technical guide for building production-ready intelligent systems. It provides a collection of hands-on tutorials, blueprints, and documentation focused on the development of applications powered by large language models, autonomous agentic workflows, and retrieval-augmented generation. The repository distinguishes itself by offering structured implementations for multi-agent orchestration and standardized communication protocols. It enables developers to integrate external tools and data sources into their systems, ensuring interoperability

MechanicalSoup is a Python web automation library and scraping framework designed to simulate browser sessions and navigate websites without requiring JavaScript execution. It functions as an HTML parsing tool and HTTP session manager, allowing for the programmatic retrieval of page content and the automation of web interactions. The library distinguishes itself by combining session persistence with automated form interaction. It maps user data to HTML input fields and selection boxes for programmatic submission and maintains authenticated states by managing cookies and user-agent headers acr

Mercure is an HTTP-based message broker and real-time pub/sub server that routes asynchronous data updates to authorized subscribers. It functions as a centralized hub that receives data via standard HTTP requests and broadcasts it to web clients using the Server-Sent Events protocol. The project distinguishes itself by replacing WebSockets with a unidirectional HTTP connection, leveraging HTTP/2 and HTTP/3 for multiplexed, low-latency delivery. It implements a secure access control layer using JSON Web Tokens and JSON Web Signatures to validate the identity of publishers and subscribers, and

Chatbox is a cross-platform desktop application that provides a unified interface for interacting with a wide range of artificial intelligence models. It functions as a model-agnostic client, allowing users to connect to various third-party AI providers or execute open-source models directly on their own hardware. By centralizing these diverse services into a single workspace, the application enables users to manage multiple chat sessions, adjust model parameters, and switch between different AI backends with ease. The project distinguishes itself through a local-first architecture that prior