Open Source Artificial Intelligence Software - Page 13
Sort By:
Artificial Intelligence Software
View 13598 business solutions-
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.
-
Custom VMs From 1 to 96 vCPUs With 99.95% UptimeLive migration and automatic failover keep workloads online through maintenance. One free e2-micro VM every month.
-
1
WrenAI
Open-source SQL AI Agent for Text-to-SQL. Make Text2SQL Easy
Wren AI is a SQL AI Agent for data teams to get results and insights faster by asking business questions without writing SQL, and it's open-source. Wren AI has implemented a semantic engine architecture to provide the LLM context of your business; you can easily establish a logical presentation layer on your data schema that helps LLM learn more about your business context. With Wren AI, you can process metadata, schema, terminology, data relationships, and the logic behind calculations and aggregations with “Modeling Definition Language”, to generate accurate SQL queries with semantic context. When starting a new conversation in Wren AI, your question is used to find the most relevant tables. From these, LLM generates three relevant questions for the user to choose from. You can also ask follow-up questions to get deeper insights. -
2
grepai
Semantic Search & Call Graphs for AI Agents
grepai is a privacy-first, semantic code search CLI designed to replace traditional keyword-based search with meaning-aware queries, letting developers and code tools find relevant code by what it does rather than just text matches. It builds a semantic index of a project using vector embeddings, enabling natural language queries like “authentication logic” to return contextually relevant functions and modules even when naming differs dramatically, making code exploration far more intuitive. In addition to semantic search, grepai offers call graph tracing so developers can understand which functions call or are called by others, aiding impact analysis and confident refactoring. Because it runs 100 % locally, your codebase never leaves your machine, preserving privacy and security while supporting AI agents and custom integrations. -
3
Stake Crash Predictor
Stake Crash Predictor is a toolkit for stake mines predictor & Plinko.
The Stake Crash Predictor is a focused toolkit that combines statistical analysis, optional server fairness seed hash decrypt helpers, and AI-assisted summaries to help you study rounds on Stake.us. This project centers on the stake mines predictor and stake predictor workflows Demo-focused stake crash predictor app — seed-inspection helpers (SHA-512 / SHA-256), AI-assisted summaries, and demo bot templates for stake mines predictor too, Start in demo mode to test safely. Disclaimer: For educational and testing purposes only. No predictive or gameplay guarantees. -
4
5ire
5ire is a cross-platform desktop AI assistant, MCP client
5ire is a sleek, cross‑platform desktop AI assistant and MCP client that connects to major service providers, supports a local knowledge base and tool integration via MCP servers, enabling robust RAG and assistant features. These components are required as they constitute the runtime environment for the MCP Server. If you don't anticipate using the tools feature immediately, you may choose to skip this installation step and complete it later when the need arises. MCP is an open protocol that standardizes how applications provide context to LLMs. Think of MCP like a USB-C port for AI applications. Just as USB-C provides a standardized way to connect your devices to various peripherals and accessories, MCP provides a standardized way to connect AI models to different data sources and tools. -
AI-powered service management for IT and enterprise teamsGive your IT, operations, and business teams the ability to deliver exceptional services—without the complexity. Maximize operational efficiency with refreshingly simple, AI-powered Freshservice.
-
5
AIMET
AIMET is a library that provides advanced quantization and compression
Qualcomm Innovation Center (QuIC) is at the forefront of enabling low-power inference at the edge through its pioneering model-efficiency research. QuIC has a mission to help migrate the ecosystem toward fixed-point inference. With this goal, QuIC presents the AI Model Efficiency Toolkit (AIMET) - a library that provides advanced quantization and compression techniques for trained neural network models. AIMET enables neural networks to run more efficiently on fixed-point AI hardware accelerators. Quantized inference is significantly faster than floating point inference. For example, models that we’ve run on the Qualcomm® Hexagon™ DSP rather than on the Qualcomm® Kryo™ CPU have resulted in a 5x to 15x speedup. Plus, an 8-bit model also has a 4x smaller memory footprint relative to a 32-bit model. However, often when quantizing a machine learning model (e.g., from 32-bit floating point to an 8-bit fixed point value), the model accuracy is sacrificed. -
6
Defang
Defang CLI and sample projects
Defang is a developer-centric platform that simplifies the process of developing, deploying, and debugging cloud applications. By leveraging AI-assisted tooling, Defang enables developers to swiftly transition from an idea to a deployed application on their preferred cloud provider. The platform supports multiple programming languages, including Go, JavaScript, and Python, allowing developers to start with sample projects or generate project outlines using natural language prompts. With a single command, Defang builds and deploys applications, handling configurations for computing, storage, load balancing, networking, logging, and security. The Defang Command Line Interface (CLI) facilitates interactions with the platform, offering installation options via shell scripts, Homebrew, Winget, Nix, or direct download. Developers can define services using compose.yaml files, which Defang utilizes to deploy applications to the cloud. -
7
Final2x
2^x Image Super-Resolution
The tool is available for Windows x64/arm64, MacOS x64/arm64, and Linux x64, allowing users to enjoy the benefits of super-resolution regardless of their operating system. It offers a wide range of models that can be used to achieve different levels of super-resolution, allowing users to choose the one that best suits their specific needs. Users have the flexibility to specify the desired output size for their images, ranging from small enhancements to large-scale super-resolution. The tool is available in English, Chinese, and Japanese, allowing users from different countries to enjoy the benefits of super-resolution. The tool is available for Windows x64/arm64, MacOS x64/arm64, and Linux x64, allowing users to enjoy the benefits of super-resolution regardless of their operating system. -
8
Hunyuan3D 2.0
High-Resolution 3D Assets Generation with Large Scale Diffusion Models
The Hunyuan3D-2 model, developed by Tencent, is designed for generating high-resolution 3D assets using large-scale diffusion models. This model offers advanced capabilities for creating detailed 3D models, including texture enhancements, multi-view shape generation, and rapid inference for real-time applications. It is particularly useful for industries requiring high-quality 3D content, such as gaming, film, and virtual reality. Hunyuan3D-2 supports various enhancements and is available for deployment through tools like Blender and Hugging Face. Includes a user-friendly production/studio tool (Hunyuan3D-Studio) to manipulate/animate meshes. Condition-aligned shape generation via the DiT model, so generated mesh is influenced by input images or prompts. -
9
Hunyuan3D-2.1
From Images to High-Fidelity 3D Assets
Hunyuan3D-2.1 is Tencent Hunyuan’s advanced 3D asset generation system that produces high-fidelity 3D models with Physically Based Rendering (PBR) textures. It is fully open-source with released model weights, training, and inference code. It improves on prior versions by using a PBR texture pipeline (enabling realistic material effects like reflections and subsurface scattering) and allowing community fine-tuning and extension. It supports both shape generation (mesh geometry) and texture generation modules. Physically Based Rendering texture synthesis to model realistic material effects, including reflections, subsurface scattering, etc. Cross-platform support (MacOS, Windows, Linux) via Python / PyTorch, including diffusers-style APIs. -
Full-stack observability with actually useful AI | Grafana CloudBuilt on open standards like Prometheus and OpenTelemetry, Grafana Cloud includes Kubernetes Monitoring, Application Observability, Incident Response, plus the AI-powered Grafana Assistant. Get started with our generous free tier today.
-
10
MCPTools
A command-line interface for interacting with MCP
mcptools is a command-line interface designed for interacting with Model Context Protocol (MCP) servers using both standard input/output and HTTP transport methods. It allows users to discover and call tools, list resources, and interact with MCP-compatible servers. The tool supports various output formats and includes features like an interactive shell, project scaffolding, and server alias management. -
11
MTEB
MTEB: Massive Text Embedding Benchmark
Text embeddings are commonly evaluated on a small set of datasets from a single task not covering their possible applications to other tasks. It is unclear whether state-of-the-art embeddings on semantic textual similarity (STS) can be equally well applied to other tasks like clustering or reranking. This makes progress in the field difficult to track, as various models are constantly being proposed without proper evaluation. To solve this problem, we introduce the Massive Text Embedding Benchmark (MTEB). MTEB spans 8 embedding tasks covering a total of 58 datasets and 112 languages. Through the benchmarking of 33 models on MTEB, we establish the most comprehensive benchmark of text embeddings to date. We find that no particular text embedding method dominates across all tasks. This suggests that the field has yet to converge on a universal text embedding method and scale it up sufficiently to provide state-of-the-art results on all embedding tasks. -
12
Meetily
Privacy first, AI meeting assistant with 4x faster Parakeet/Whisper
This project is a privacy-first AI meeting assistant that captures meeting audio, produces real-time transcripts, and generates summaries while keeping processing entirely on your own machine or infrastructure. It’s built for organizations that want meeting intelligence without sending recordings or transcripts to third-party cloud services, which helps address compliance and data sovereignty requirements. The app supports live transcription with local model options (including Whisper- and Parakeet-based workflows) and presents the transcript as the meeting happens, making it useful both for note-taking and accessibility. After or during the session, it can produce structured, AI-generated summaries, and it’s designed to be flexible about where that summarization comes from, supporting local providers as well as external endpoints when allowed by policy. -
13
MinerU
A high-quality tool for convert PDF to Markdown and JSON
MinerU is an open-source, high-quality document extraction toolkit focused on converting PDFs (and other document formats) into structured Markdown and JSON. It leverages OCR and layout analysis to preserve semantic structure and metadata, ideal for research and data science workflows. -
14
Mooncake
Mooncake is the serving platform for Kimi
Mooncake is an open-source infrastructure platform designed to optimize large language model serving by focusing on efficient management and transfer of model data and KV cache. The platform was originally developed as part of the serving infrastructure for the Kimi large language model system. Its architecture centers on a high-performance transfer engine that provides unified data transfer across different storage and networking technologies. This engine enables efficient movement of tensors and model data across heterogeneous environments such as GPU memory, system memory, and distributed storage systems. Mooncake also introduces distributed key-value cache storage that allows inference systems to reuse previously computed attention states, significantly improving throughput in large-scale deployments. The system supports advanced networking technologies such as RDMA and NVMe over Fabric, enabling high-speed communication across clusters. -
15
Telegram File Stream Bot
A telegram bot that will give instant stream links for telegram files
A Telegram bot to generate direct link for your Telegram files. -
16
Transformers
State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX
Hugging Face Transformers provides APIs and tools to easily download and train state-of-the-art pre-trained models. Using pre-trained models can reduce your compute costs, carbon footprint, and save you the time and resources required to train a model from scratch. These models support common tasks in different modalities. Text, for tasks like text classification, information extraction, question answering, summarization, translation, text generation, in over 100 languages. Images, for tasks like image classification, object detection, and segmentation. Audio, for tasks like speech recognition and audio classification. Transformers provides APIs to quickly download and use those pretrained models on a given text, fine-tune them on your own datasets and then share them with the community on our model hub. At the same time, each python module defining an architecture is fully standalone and can be modified to enable quick research experiments. -
17
Vespa
The open big data serving engine
Make AI-driven decisions using your data, in real-time. At any scale, with unbeatable performance. Vespa is a full-featured text search engine and supports both regular text search and fast approximate vector search (ANN). This makes it easy to create high-performing search applications at any scale, whether you want to use traditional techniques or a modern vector-based approach. You can even combine both approaches efficiently in the same query, something no other engine can do. Recommendation, personalization and targeting involves evaluating recommender models over content items to select the best ones. Vespa lets you build applications which does this online, typically combining fast vector search and filtering with evaluation of machine-learned models over the items. This makes it possible to make recommendations specifically for each user or situation, using completely up to date information. -
18
Whisper-WebUI
A Web UI for easy subtitle using whisper model
Whisper WebUI is an open-source browser-based interface that simplifies the use of Whisper speech recognition models by providing an intuitive graphical environment for transcription, translation, and subtitle generation. Built with Gradio, it allows users to upload audio or video files, process them locally, and generate accurate text outputs without relying on command-line tools. The platform integrates optimized implementations such as faster-whisper, significantly improving transcription speed and reducing memory usage compared to standard models. It supports multiple input sources including local files, YouTube content, and microphone input, making it versatile for different workflows. Whisper WebUI also includes advanced preprocessing and postprocessing features such as voice activity detection, background music separation, and speaker diarization, enabling more accurate and structured outputs. -
19
Datapipe
Real-time, incremental ETL library for ML with record-level depend
Datapipe is a real-time, incremental ETL library for Python with record-level dependency tracking. Datapipe is designed to streamline the creation of data processing pipelines. It excels in scenarios where data is continuously changing, requiring pipelines to adapt and process only the modified data efficiently. This library tracks dependencies for each record in the pipeline, ensuring minimal and efficient data processing. -
20
Dlib is a C++ toolkit containing machine learning algorithms and tools for creating complex software in C++ to solve real world problems.
-
21
Umi-OCR
Free OCR Software: No internet required, easy to use.
Support screenshots/pasting/batch importing of images, paragraph layout/excluding watermarks, scanning/generating QR codes. No need for internet connection throughout the entire process, with built-in multi language recognition library. 支持截屏/粘贴/批量导入图片，支持段落排版/排除水印，扫描/生成二维码。全程无需联网，内置多国语言识别库。 -
22
AingDesk
AI assistant that supports knowledge bases, model APIs
AingDesk is an open-source desktop and server-based AI assistant platform designed to provide a user-friendly environment for interacting with language models and building AI-powered tools. The software enables users to run local AI models or connect to external model APIs through a unified interface. One of its primary goals is to simplify the process of building knowledge-based assistants by allowing users to create local knowledge bases that the AI can search and analyze. The system supports additional features such as web search, intelligent agent workflows, and multi-model conversations within a single session. AingDesk can be deployed locally on personal machines or installed as a server using containerized environments. Its design emphasizes accessibility, making it suitable for both beginners and experienced developers who want to experiment with AI tools. -
23
Claude Code Haha
Claude Code leaked source - locally runnable version
Claude Code Haha is an experimental and often humorous adaptation of Claude-style coding agents, designed to explore and demonstrate how agentic coding systems behave under different configurations and prompts. While it retains the core functionality of analyzing and modifying codebases, the project introduces variations that highlight both the strengths and quirks of autonomous coding assistants. It serves as a sandbox for testing how agents interpret instructions, manage context, and execute development tasks in a less formal or more exploratory setting. The repository likely includes playful modifications, custom prompts, or unconventional workflows that reveal edge cases in agent behavior. Despite its informal tone, it still provides insight into how coding agents can be structured and extended. It is particularly useful for understanding limitations, failure modes, and creative applications of AI-driven development tools. -
24
DINOv3
Reference PyTorch implementation and models for DINOv3
DINOv3 is the third-generation iteration of Meta’s self-supervised visual representation learning framework, building upon the ideas from DINO and DINOv2. It continues the paradigm of learning strong image representations without labels using teacher–student distillation, but introduces a simplified and more scalable training recipe that performs well across datasets and architectures. DINOv3 removes the need for complex augmentations or momentum encoders, streamlining the pipeline while maintaining or improving feature quality. The model supports multiple backbone architectures, including Vision Transformers (ViT), and can handle larger image resolutions with improved stability during training. The learned embeddings generalize robustly across tasks like classification, retrieval, and segmentation without fine-tuning, showing state-of-the-art transfer performance among self-supervised models. -
25
GLM-OCR
Accurate × Fast × Comprehensive
GLM-OCR is an open-source multimodal optical character recognition (OCR) model built on a GLM-V encoder–decoder foundation that brings robust, accurate document understanding to complex real-world layouts and modalities. Designed to handle text recognition, table parsing, formula extraction, and general information retrieval from documents containing mixed content, GLM-OCR excels across major benchmarks while remaining highly efficient with a relatively compact parameter size (~0.9B), enabling deployment in high-concurrency services and edge environments. The model’s multimodal capabilities allow it to reason across image and text content holistically, capturing structured and unstructured information from pages that include dense tables, seals, code snippets, and varied document graphics. GLM-OCR integrates a comprehensive SDK and inference toolchain that makes it easy for developers to install, invoke, and embed into production pipelines with simple commands or APIs.
