Search Results for "intelligence" - Page 93
Sort By:
Showing 7182 open source projects for "intelligence"
View related 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.
-
Build Agents and Models on One PlatformGemini Enterprise Agent Platform is Google Cloud's comprehensive platform for developers to build, scale, govern, and optimize agents and models. Choose from Google's most advanced models and third-party models like Anthropic's Claude Model Family.
-
1
yek
Serialize repositories into LLM-ready context w/ smart prioritization
Yek is a Rust-based CLI tool designed to serialize text-based files from a repository or directory into a single structured output for large language model use. It scans projects using .gitignore rules to exclude irrelevant files and automatically filters out binary or oversized content. Yek prioritizes files based on Git history, placing more important content later in the output to align with how language models process context. Yek supports multiple directories, individual files, and glob... -
2
Short Video Factory
AI tool for automatic batch short video creation and editing
Short Video Factory is an open source desktop application designed to simplify the creation of short-form videos using AI-driven automation. It enables users to generate product marketing clips and general content videos by combining simple prompt-based input with pre-prepared media assets. Short Video Factory integrates multiple stages of video production, including script generation, voice synthesis, video editing, and subtitle effects, into a single streamlined workflow. By leveraging AI... -
3
LiveKit Agents
Framework for building realtime multimodal voice AI agents apps
LiveKit Agents is an open source framework designed for building realtime AI agents that can participate as programmable entities within communication sessions. It enables developers to create conversational and multimodal agents capable of processing voice, audio, and other inputs in realtime environments. These agents can join LiveKit rooms as participants and interact with users or systems through speech, text, and other modalities. LiveKit Agents provides libraries and tooling that allow... -
4
WeKnora
LLM framework for document understanding and semantic retrieval
WeKnora is an open source framework developed for deep document understanding and semantic information retrieval using large language models. It focuses on analyzing complex and heterogeneous documents by combining multiple processing stages such as multimodal document parsing, vector indexing, and intelligent retrieval. It follows the Retrieval-Augmented Generation (RAG) paradigm, where relevant document segments are retrieved and used by language models to generate accurate, context-aware... -
Build Securely on AWS with Proven FrameworksMoving to the cloud brings new challenges. How can you manage a larger attack surface while ensuring great network performance? Turn to Fortinet’s Tested Reference Architectures, blueprints for designing and securing cloud environments built by cybersecurity experts. Learn more and explore use cases in this white paper.
-
5
Dagger
Containerized automation engine for programmable CI/CD workflows
Dagger is an open source automation engine designed to build, test, and deliver software in a consistent and programmable way. It enables developers to define software delivery workflows using code instead of complex shell scripts or configuration files. Dagger executes tasks inside containers, ensuring that automation runs in identical environments across local machines, CI servers, or cloud infrastructure. Dagger provides a core execution engine and system API that orchestrates containers,... -
6
Folo
Folo is the AI Reader
Folo is an AI-powered RSS reader and information aggregation platform designed to help users follow online content in a single, distraction-free timeline. The project focuses on reducing information overload by automatically organizing feeds and surfacing the most relevant updates based on user preferences. It incorporates AI features that summarize timelines, label entries, and adapt recommendations over time so the reading experience becomes more personalized. Folo is built as a modern... -
7
Sprite Fusion Pixel Snapper
A tool to snap pixels to a perfect grid
Sprite Fusion Pixel Snapper is a utility designed to eliminate sub-pixel rendering issues that often arise in pixel art, UI icons, and 2D sprite graphics when displayed on screens with high DPI or during motion animations. The tool works by adjusting sprite rendering coordinates and texture sampling so that every pixel aligns cleanly to the screen’s pixel grid, avoiding blurring, distortion, or unintended smoothing artifacts. This is especially important in pixel art games, retro-styled... -
8
Instructor
Structured outputs for llms
Instructor is a tool that enables developers to extract structured data from natural language using Large Language Models (LLMs). Integrating with Python's Pydantic library allows users to define desired output structures through type hints, facilitating schema validation and seamless integration with IDEs. Instructor supports various LLM providers, including OpenAI, Anthropic, Litellm, and Cohere, offering flexibility in implementation. Its customizable nature permits the definition of... -
9
DeepSpeed
Deep learning optimization library: makes distributed training easy
DeepSpeed is an easy-to-use deep learning optimization software suite that enables unprecedented scale and speed for Deep Learning Training and Inference. With DeepSpeed you can: 1. Train/Inference dense or sparse models with billions or trillions of parameters 2. Achieve excellent system throughput and efficiently scale to thousands of GPUs 3. Train/Inference on resource constrained GPU systems 4. Achieve unprecedented low latency and high throughput for inference 5. Achieve extreme... -
99.99% Uptime for MySQL and PostgreSQL DatabasesCloud SQL Enterprise Plus delivers near-zero downtime with 35 days of point-in-time recovery. Supports MySQL, PostgreSQL, and SQL Server.
-
10
Multi-Page Automation
Browser extension designed to automate OAuth authentication
Multi-Page Automation is a browser extension designed to automate OAuth authentication flows for AI coding tools and integrations. It simplifies the process of obtaining and managing authentication tokens required to access external APIs. The extension handles login steps, token retrieval, and session management automatically. It is particularly useful for developers working with AI tools that require repeated authentication. The project reduces friction in development workflows by... -
11
Chainlit
Build Python LLM apps in minutes
Chainlit is an open-source Python package that makes it incredibly fast to build and share LLM apps. Integrate the Chainlit API in your existing code to spawn a ChatGPT-like interface in minutes! Integrate seamlessly with an existing code base or start from scratch in minutes. Understand the intermediary steps that produced an output at a glance. Deep dive into prompts in the Prompt Playground to understand where things went wrong and iterate. Invite your teammates, create annotated datasets... -
12
User Scanner
Scan usernames and emails across many platforms from the CLI
...It helps users quickly determine whether a specific username or email is already associated with accounts on social networks, developer platforms, creator communities, gaming services, and other sites. user-scanner is useful for security researchers, investigators, and analysts performing open source intelligence, as well as individuals or businesses looking for a unique username across multiple services. By scanning many platforms in a single command, it simplifies the process of checking account existence and identifying a digital footprint. user-scanner uses a modular architecture where each platform is implemented as a small validator module that determines whether a username exists or is available. -
13
Groq Python
The official Python Library for the Groq API
Groq Python is the official Python SDK for the Groq REST API, giving Python developers straightforward access to Groq’s LLM, chat, audio, and other AI services. Through this library, you can call Groq’s models from Python code — for example to request chat completions, code generation, transcription, or any supported endpoint — using idiomatic Python syntax. The SDK handles authentication (via environment variable or parameter), defines proper type-safe request/response data types, and... -
14
Super Magic
All-in-one AI productivity platform with agents, workflows, and IM
Magic is an open source all-in-one AI productivity platform designed to help organizations build, deploy, and scale AI-driven applications efficiently. It is not a single tool but a complete product ecosystem composed of multiple integrated systems that work together to enhance productivity across different business scenarios. Magic centers around a general-purpose AI agent system called Super Magic, which can autonomously understand tasks, plan actions, execute workflows, and perform error... -
15
img2obj
Codex plugin that turns attached object images into code-only
img2obj is a Codex plugin that reconstructs an object from a reference image as procedural Three.js code rather than extracting or downloading a mesh. It first checks whether the image is suitable, then creates an ObjectSculptSpec describing geometry, materials, hierarchy, pivots, sockets, and visual priorities. Reconstruction proceeds through blockout, form, look development, and interaction phases so details are added in a controlled order. The plugin supports hard-surface objects, organic... -
16
WASTE
Run the full 2.78-trillion-parameter Kimi K3 model
WASTE is an embeddable C inference engine for running extremely large mixture-of-experts models when the weights exceed available RAM. It keeps the shared model trunk in memory and streams only the experts selected for each token from fast NVMe storage. A bounded cache reuses recently needed experts, while lookahead routing begins disk reads before the next layer requires them. Its main target is the full 2.78-trillion-parameter Kimi K3 model, including multimodal image input. The engine has... -
17
Kimi K3 in C
A 2.78-trillion-parameter Kimi K3 running inference on a single CPU
Kimi K3 in C is a portable C99 inference engine built to run the 2.78-trillion-parameter Kimi K3 model on CPUs without BLAS, machine-learning frameworks, or GPUs. It demonstrates inference from a roughly 1.56 TB checkpoint with measured memory use as low as 8.24 GB. The runtime streams model trunk layers and routed experts from disk instead of keeping all weights resident in memory. Memory presets balance pinned layers and an expert LRU cache for laptops, desktops, workstations, and servers.... -
18
BigMac
An open-source toolkit for BigMac-style pipeline-parallel training
BigMac is an open-source toolkit for pipeline-parallel training of multimodal large language models. It preserves optimized language-model pipeline schedules while placing encoder and generator work around them. This design reduces activation memory without bringing back cross-module pipeline bubbles. Its scheduler creates global operator plans, while its executor runs those plans through a shared schedule abstraction. A Megatron-Core reference backend and Qwen3 and Qwen3-VL tutorials help... -
19
JoyAI-VL-Interaction
An Open Real-time Video-Language Interaction System
JoyAI-VL-Interaction is an open real-time video-language interaction system built around an 8B-scale vision-first model. It is designed to watch a webcam or livestream continuously and decide whether to speak, stay silent, or delegate a harder task. Unlike turn-based assistants, it focuses on event-driven interaction where timing matters as much as answer quality. The repository releases the model, training recipe, time-aligned interaction data, and deployable system together. Its system... -
20
ASSERT
Requirement-driven evaluation harness for AI agents and LLM
ASSERT is a requirement-driven evaluation harness for AI agents and LLM applications. It turns natural-language specifications, policies, product requirements, and launch criteria into structured tests that can be reviewed, executed, scored, and improved. The pipeline derives behavior categories, generates single-turn and multi-turn test cases, runs them against a target system, and uses an LLM judge to score conversations against the stated policies. It can evaluate hosted models, custom... -
21
Wandesk
Give intelligence shape. Let AI sculpt your desktop
Wandesk is an open-source AI desktop environment that lets users build local apps by describing what they need in natural language. It combines chat, generated apps, shared workspace context, personal memory, files, tasks, and agent integrations into one desktop-like interface. Its App Workshop can generate a React UI, backend API, and SQLite storage together, allowing users to create usable local tools without manually writing the whole application. Wandesk is local-first, works without... -
22
Guizang Social Card Skill
Claude Code / Codex skill — generate Xiaohongshu carousels
Guizang Social Card Skill is an AI-agent skill for generating polished social image packages in a Guizang-inspired visual style. It is designed for formats such as Xiaohongshu or Rednote carousels, WeChat Official Account covers, article covers, product update graphics, thumbnails, and screenshot-heavy posts. The skill turns articles, scripts, screenshots, product notes, subtitles, or photos into structured social card outputs. It supports editorial magazine layouts and Swiss-style visual... -
23
TokenSpeed
TokenSpeed is a speed-of-light LLM inference engine
TokenSpeed is an LLM inference engine designed for high-performance production agent workloads. It aims to combine TensorRT-LLM-level speed with vLLM-level usability, making it relevant for teams that need fast generation without sacrificing developer ergonomics. The project is focused on the specific needs of agentic systems, where latency, throughput, and efficient scheduling matter across many short or tool-heavy requests. It builds on ideas and components from the broader open-source... -
24
Kaggle Python Docker
Kaggle Python docker image
Kaggle Python Docker is Kaggle’s official Docker image repository for the Python environment used by Kaggle Notebooks. It contains the Dockerfiles and build configuration for both CPU-only and GPU-enabled notebook images. The project helps users understand, reproduce, and test against the same Python environment that powers Kaggle’s cloud notebooks. It includes a large curated package set for data science, machine learning, visualization, notebooks, and scientific computing. The images are... -
25
MiniMind-O
A 0.1B Omni model trained from scratch
MiniMind-O is an educational open-source project for building a small end-to-end Omni model from scratch. It extends the MiniMind family by exploring a model that can handle text, audio, and image inputs while producing text and streaming speech outputs. The project is designed to make multimodal AI training more accessible by keeping the model size small enough for ordinary personal hardware. It includes both mini and full training data paths, allowing learners to run a complete workflow...