Search Results for "document search engine" - Page 6
Sort By:
Showing 1175 open source projects for "document search engine"
View related business solutions-
Go From AI Idea to AI App FastAccess Gemini 3 and 200+ models. Build chatbots, agents, or custom models with built-in monitoring and scaling.
-
AI-generated apps that pass security reviewRetool lets you generate dashboards, admin panels, and workflows directly on your data. Type something like “Build me a revenue dashboard on my Stripe data” and get a working app with security, permissions, and compliance built in from day one. Whether on our cloud or self-hosted, create the internal software your team needs without compromising enterprise standards or control.
-
1
HarfBuzz
Open source text shaping engine
HarfBuzz is an open source text-shaping engine with a C API that turns fonts and strings of character codes into a form that is correctly arranged for the corresponding language and writing system. This is essentially the process of text shaping: translating a string of character codes into a properly arranged sequence of glyphs that can be rendered onto a screen or into final output form for inclusion in a document. -
2
SimpleMem
SimpleMem: Efficient Lifelong Memory for LLM Agents
SimpleMem is a lightweight memory-augmented model framework that helps developers build AI applications that retain long-term context and recall relevant information without overloading model context windows. It provides easy-to-use APIs for storing structured memory entries, querying those memories using semantic search, and retrieving context to augment prompt inputs for downstream processing. Unlike monolithic systems where memory management is ad-hoc, SimpleMem formalizes a memory lifecycle—write, index, retrieve, refine—so applications can handle user history, document collections, or dynamic contextual state systematically. It supports customizable embedding models, efficient vector indexes, and relevance weighting, making it practical for building assistants, personal agents, or domain-specific retrieval systems that need persistent knowledge. -
3
compodoc
The missing documentation tool for your Angular, Nest & Stencil apps
...No server needed, no sources uploaded online. 7 themes are available from famous documentation tools like Gitbook, Read the Docs or projects like Vagrant, Laravel, Postmark and Stripe. Compodoc includes a powerful search engine (lunr.js) for easily finding your information. The generated pages display very well on mobile, tablet and desktop. Compodoc is a documentation tool for Angular applications. It generates static documentation of your application. Compodoc helps Angular developers provide clear and helpful documentation of their application. -
4
Curator Engine
Curator is an open-source, self-hosted ecommerce engine
Curator Engine is an open-source, self-hosted ecommerce core built for high-performance, search-driven marketplaces. Unlike traditional ecommerce platforms that treat search as an afterthought, Curator is designed around discovery first: fast search, structured browsing, and scalable catalog experiences. The platform includes a digital commerce core with customer accounts, purchases, secure downloads, SMTP support, and admin tools for managing products, builds, and content. ... -
MongoDB Atlas runs apps anywhereMongoDB Atlas gives you the freedom to build and run modern applications anywhere—across AWS, Azure, and Google Cloud. With global availability in over 115 regions, Atlas lets you deploy close to your users, meet compliance needs, and scale with confidence across any geography.
-
5
ChatGPT Retrieval Plugin
The ChatGPT Retrieval Plugin lets you easily find personal documents
The chatgpt-retrieval-plugin repository implements a semantic retrieval backend that lets ChatGPT (or GPT-powered tools) access private or organizational documents in natural language by combining vector search, embedding models, and plugin infrastructure. It can serve as a custom GPT plugin or function-calling backend so that a chat session can “look up” relevant documents based on user queries, inject those results into context, and respond more knowledgeably about a private knowledge... -
6
All-in-RAG
Big Model Application Development Practice 1
All-in-RAG is an open-source educational project designed to teach developers how to build applications using retrieval-augmented generation techniques. The repository provides a structured learning path that covers both theoretical foundations and practical implementation steps for RAG systems. It explains the full development pipeline required to create knowledge-aware AI assistants, including data preparation, document indexing, vector embedding generation, and retrieval strategies. The... -
7
UFONet
UFONet - Denial of Service Toolkit
UFONet is a powerful and controversial Python-based toolkit for testing and conducting Distributed Denial of Service (DDoS) attacks using unconventional methods, such as leveraging third-party web applications as attack vectors. It automates the discovery of vulnerable targets and enables attackers or researchers to launch large-scale amplification attacks without directly using botnets. While primarily intended for penetration testing and educational purposes, UFONet emphasizes anonymity... -
8
Booble Search
Local search engine for your personal computer
This is a desktop search tool, similar to a well-known search engine, that you can use on your Debian/Linux-based computer. It allows you to perform local searches by indexing all memory units connected to your computer. Currently, it only supports Turkish, but dynamic multi-language support will be added in the future. Bu, debian/linux tabanlı bilgisayarınızda kullanabileceğiniz, bilinen arama motoruna benzetilmiş bir masaüstü arama aracıdır. -
9
Datacap
DataCap is integrated software for data transformation
Datacap is an open-source data catalog and governance tool that helps organizations manage and document their data assets. It provides metadata management, lineage tracking, and collaboration features to ensure data transparency and quality. Datacap is designed for teams that need a lightweight, self-hosted solution to organize and govern their data ecosystems. -
Try Google Cloud Risk-Free With $300 in CreditUse your credit across every product. Compute, storage, AI, analytics. When it runs out, 20+ products stay free. You only pay when you choose to.
-
10
Project NOMAD
Self-contained, offline survival computer with tools, knowledge, & AI
Project N.O.M.A.D. (Node for Offline Media, Archives, and Data) is a self-contained, offline-first knowledge and education server designed to run on local hardware. It combines AI, educational resources, and critical information tools into a single platform accessible through a web browser. Built as a containerized system managed via Docker, it orchestrates multiple applications through a centralized “Command Center” interface. NOMAD enables users to access offline Wikipedia, AI chat, maps,... -
11
JS Analyzer
Burp Suite extension for JavaScript static analysis
...The extension is designed to reduce manual effort when analyzing large or obfuscated JavaScript assets, helping testers find security vulnerabilities and sensitive information faster and more reliably. It also includes UI features such as live search, result filtering, and the ability to export findings in JSON format for further processing. The underlying engine can be used independently in Python, enabling integration into custom workflows or automated pipelines outside Burp Suite. -
12
Glow
Render markdown on the CLI, with pizzazz!
Glow is a terminal-based markdown reader designed from the ground up to bring out the beauty and power of the CLI. Use it to discover markdown files, read documentation directly on the command line and stash markdown files to your own private collection so you can read them anywhere. Glow will find local markdown files in subdirectories or a local Git repository. By the way, all data stashed is encrypted end-to-end: only you can decrypt it. Simply run glow without arguments to start the... -
13
org-ql
An Org-mode query language, including search commands and saved views
This package provides a query language for Org files. It offers two syntax styles: Lisp-like sexps and search engine-like keywords. It includes three libraries: The org-ql library is flexible and may be used as a backend for other tools. The libraries org-ql-search and helm-org-ql (a separate package) provide interactive search commands and saved views. The package org-ql may be installed directly from MELPA or with other tools like Quelpa. -
14
LLocalSearch
LLocalSearch is a completely locally running search aggregator
LLocalSearch is an open-source search engine framework designed to run entirely on local infrastructure using large language model agents to gather and synthesize information from the web. The system allows users to submit natural language questions, after which a chain of LLM-driven agents recursively searches for relevant information and compiles a response. Unlike many AI search tools, LLocalSearch operates without requiring external cloud APIs or proprietary services, making it suitable for privacy-focused or offline environments. ... -
15
Purelog Theme for Jekyll
A responsive sidebar Jekyll theme, created with the Pure.css framework
...Purelog is a responsive, sidebar theme for the popular JAMstack generator Jekyll that only uses the minimal Pure.css framework (hence the name!), while still following the best practices possible for accessibility and search engine optimization. This project is aimed at those looking for an interesting theme for Jekyll that has features that aren't found commonly elsewhere, specifically having separate sections dedicated towards blogging, note-taking, and daily journal entries. -
16
Elgg
A social networking engine in PHP/MySQL
Introducing a powerful open-source social networking engine. Providing you with the core components needed to build a socially aware web application. Elgg is an award-winning open source social networking engine that provides a robust framework on which to build all kinds of social environments, from a campus-wide social network for your university, school or college or an internal collaborative platform for your organization to a brand-building communications tool for your company and its clients. ... -
17
Smile
Statistical machine intelligence and learning engine
Smile is a fast and comprehensive machine learning engine. With advanced data structures and algorithms, Smile delivers the state-of-art performance. Compared to this third-party benchmark, Smile outperforms R, Python, Spark, H2O, xgboost significantly. Smile is a couple of times faster than the closest competitor. The memory usage is also very efficient. If we can train advanced machine learning models on a PC, why buy a cluster? Write applications quickly in Java, Scala, or any JVM... -
18
geo-seo-claude
GEO-first SEO skill for Claude Code
geo-seo-claude is an AI-powered tool designed to automate the creation of geographically optimized SEO content using large language models, helping businesses improve their visibility in local search results. It leverages AI to generate location-specific content tailored to different regions, allowing users to scale SEO efforts across multiple cities or markets without manual content creation. The system focuses on producing structured and keyword-optimized pages that align with search engine ranking factors, including localized relevance and semantic context. ... -
19
RTP-LLM
Alibaba's high-performance LLM inference engine for diverse apps
...The framework is designed for large-scale AI services and is already used internally across several Alibaba platforms such as Taobao, Amap, and other business systems that rely on conversational or search-related AI services. RTP-LLM supports a wide variety of modern model architectures, including Qwen, DeepSeek, and Llama-based models, making it a flexible engine for deploying many different open-source LLMs. -
20
HeadlessX
The undetected self-hosted browser automation platform
...The system provides a centralized service that allows developers to programmatically control browser sessions and extract data from websites through a structured API. It is built using modern technologies including Node.js, Next.js, TypeScript, and Playwright, and uses a specialized browser engine called Camoufox based on Firefox. One of the platform’s goals is to bypass common bot-detection systems by implementing advanced fingerprint spoofing and stealth techniques. The tool can perform tasks such as HTML extraction, screenshot generation, content parsing, and search result scraping while appearing like a normal user browser. ... -
21
Raglite
RAGLite is a Python toolkit for Retrieval-Augmented Generation
Raglite is a lightweight framework for building Retrieval-Augmented Generation (RAG) pipelines with minimal configuration. It connects large language models to vector databases for context-aware responses, enabling developers to prototype and deploy RAG systems quickly. Raglite focuses on simplicity and modularity for fast experimentation. -
22
Relaticle
The Next-Generation Open-Source CRM Platform written with Laravel
...It blends the simplicity of a note-taking system with the power of a graph database, allowing users to create nodes for concepts, link them through relationships, and navigate their thoughts like a map instead of a linear document. The interface lets you write plain text notes and tag or connect them dynamically, making it easier to uncover patterns and connections over time instead of losing insights in a long, unstructured list. Because it’s built with productivity and exploration in mind, Relaticle offers fast search, semantic context awareness, and the ability to zoom from high-level overviews down to specific node details. ... -
23
Canopy
Retrieval Augmented Generation (RAG) framework
Canopy is an open-source retrieval-augmented generation (RAG) framework developed by Pinecone to simplify the process of building applications that combine large language models with external knowledge sources. The system provides a complete pipeline for transforming raw text data into searchable embeddings, storing them in a vector database, and retrieving relevant context for language model responses. It is designed to handle many of the complex components required for a RAG workflow,... -
24
The Minimal Light Theme
A simple and elegant Jekyll theme for an academic personal homepage
A simple and elegant Jekyll theme for an academic personal homepage. The compiled HTML files are available in the html_source_file folder. If you don't like Jekyll, you may directly edit and use the HTML version. -
25
CyberStrikeAI
CyberStrikeAI is an AI-native security testing platform built in Go
...Through comprehensive lifecycle management, results are tracked, aggregated, and visualized, with support for versioned persistence, search, and risk severity scoring.
