Search Results for "real" - Page 9
Sort By:
Showing 1073 open source projects for "real"
View related business solutions-
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.
-
Our Free Plans just got better! | Auth0You asked, we delivered! Auth0 is excited to expand our Free and Paid plans to include more options so you can focus on building, deploying, and scaling applications without having to worry about your security. Auth0 now, thank yourself later.
-
1
OpenManus
Open-source AI agent framework
...The platform emphasizes task decomposition, allowing agents to break down objectives into smaller steps and execute them sequentially or recursively. OpenManus supports integration with external tools, APIs, and environments, making it suitable for real-world automation workflows. It is built to be flexible and extensible, enabling customization of agent behaviors, tools, and reasoning strategies. Overall, OpenManus provides a foundation for creating more capable, autonomous AI systems that can handle dynamic and goal-driven tasks. -
2
Norfair
Lightweight Python library for adding real-time multi-object tracking
Norfair is a customizable lightweight Python library for real-time multi-object tracking. Using Norfair, you can add tracking capabilities to any detector with just a few lines of code. Any detector expressing its detections as a series of (x, y) coordinates can be used with Norfair. This includes detectors performing tasks such as object or keypoint detection. It can easily be inserted into complex video processing pipelines to add tracking to existing projects. -
3
Grafana
Leading open-source visualization and observability platform
...With support for 100+ data source plugins—including Prometheus, Loki, Elasticsearch, InfluxDB, SQL/NoSQL databases, and OpenTelemetry—Grafana helps teams correlate metrics, logs, and traces across applications and infrastructure. Users can build interactive dashboards with rich visualizations, template variables, and reusable panels to monitor systems and troubleshoot issues in real time. Grafana includes capabilities such as ad hoc data exploration, alerting, annotations, and flexible query support. Its extensible plugin ecosystem integrates with cloud platforms, databases, and developer tools—allowing teams to build observability workflows without vendor lock-in. The easiest way to get started with Grafana is with Grafana Cloud, our fully managed, full-stack observability platform. -
4
Substra
Low-level Python library used to interact with a Substra network
An open-source framework supporting privacy-preserving, traceable federated learning and machine learning orchestration. Offers a Python SDK, high-level FL library (SubstraFL), and web UI to define datasets, models, tasks, and orchestrate secure, auditable collaborations. -
Error to trace to log to deploy. One click. No SSH.AppSignal links every error to the trace, the trace to the log, the log to the deploy that shipped it.
-
5
Pixoo
A library to help you make the most out of your Pixoo 64
Pixoo is a Python-based library for controlling Divoom Pixoo LED displays using Bluetooth Low Energy (BLE). It allows users to send images, animations, or text to Pixoo devices, enabling creative integrations like desktop widgets, real-time data displays, or custom artwork. -
6
Text Generation Inference
Large Language Model Text Generation Inference
Text Generation Inference is a high-performance inference server for text generation models, optimized for Hugging Face's Transformers. It is designed to serve large language models efficiently with optimizations for performance and scalability. -
7
Z80-μLM
Z80-μLM is a 2-bit quantized language model
...The repository provides a complete workflow where you train or fine-tune conversational models in Python, then export them into a format that can be executed on classic Z80 systems. A key deliverable is producing CP/M-compatible .COM binaries, enabling a genuinely vintage “chat with your computer” experience on real hardware or accurate emulators. The project sits at the intersection of machine learning and systems constraints, showing how model architecture, quantization, and inference code generation can be adapted to extreme memory and compute limits. It also functions as an educational reference for how to reduce inference to operations that fit an old-school instruction set and runtime environment. -
8
ModelScope
Bring the notion of Model-as-a-Service to life
ModelScope is built upon the notion of “Model-as-a-Service” (MaaS). It seeks to bring together most advanced machine learning models from the AI community, and streamlines the process of leveraging AI models in real-world applications. The core ModelScope library open-sourced in this repository provides the interfaces and implementations that allow developers to perform model inference, training and evaluation. In particular, with rich layers of API abstraction, the ModelScope library offers unified experience to explore state-of-the-art models spanning across domains such as CV, NLP, Speech, Multi-Modality, and Scientific-computation. ... -
9
Salt
Automate the management and configuration of infrastructures at scale
Salt Bootstrap is a shell script that detects the target platform and selects the best installation method. (Supported Platforms) Your Salt master can manage itself, so a Salt minion is installed along with the Salt master. Before implementing Salt to manage any data center infrastructure it is important to understand a few things about Salt platform support including: What platforms will the Salt Master run on? What systems and infrastructure can be managed by a Salt Minion? Salt runs on... -
Cut Data Warehouse Costs by 54%BigQuery delivers 54% lower TCO with exabyte scale and flexible pricing. Free migration tools handle the SQL translation automatically.
-
10
BlenderMCP
Blender Model Context Protocol Integration
...It allows users to control Blender using natural language prompts, effectively turning AI into a co-creator for 3D modeling, scene construction, and asset manipulation. The system establishes a two-way communication channel between Blender and the AI, where commands can be sent and results retrieved in real time. It includes features for object manipulation, material editing, and scene inspection, giving the AI deep control over the modeling environment. The project also supports integration with external asset sources such as Sketchfab and Poly Haven, expanding the range of available resources. Additionally, it allows execution of Python scripts within Blender through AI commands, enabling advanced automation and customization. -
11
Everywhere
Context-aware desktop AI assistant that understands screen content
...It distinguishes itself from traditional AI tools by eliminating the need for manual input methods such as copying text or taking screenshots, instead allowing users to invoke assistance instantly through a shortcut. It can analyze on-screen information in real time and provide contextual responses, making it useful for tasks like troubleshooting errors, summarizing articles, translating text, and refining written content. It integrates with multiple large language model providers and supports various tools, enabling flexible and extensible AI-powered workflows. Everywhere features a modern design with interactive elements such as markdown rendering, keyboard shortcuts, and voice input capabilities. ... -
12
Diffusion for World Modeling
Learning agent trained in a diffusion world model
...The project introduces the idea of using diffusion models, commonly used for image generation, to simulate the dynamics of an environment and predict future states based on previous observations and actions. Instead of interacting directly with a real environment, the reinforcement learning agent learns within a generative model that produces frames representing the environment. This approach allows training to occur in a simulated world that captures detailed visual dynamics while reducing the need for costly interactions with real environments. The system has been applied to tasks such as Atari game simulations and demonstrations involving complex environments like first-person shooter games. -
13
Advanced NLP with spaCy
Advanced NLP with spaCy: A free online course
Advanced NLP with spaCy is an open-source educational repository that provides the materials for an interactive course on advanced natural language processing using the spaCy library. The course is designed to teach developers how to build real-world NLP systems by combining rule-based techniques with machine learning models. The repository includes lessons, exercises, and examples that guide learners through tasks such as tokenization, named entity recognition, text classification, and training custom NLP models. It also demonstrates how spaCy pipelines work and how developers can extend them with custom components and training data. ... -
14
AI Engineer Headquarters
A collection of scientific methods, processes, algorithms
...The project serves as a curated collection of resources, methodologies, and tools covering topics across the entire artificial intelligence development lifecycle. Rather than focusing only on theoretical knowledge, the repository emphasizes applied learning and encourages engineers to build real systems that incorporate machine learning, large language models, data pipelines, and AI infrastructure. The curriculum includes a progression of topics such as foundational AI engineering skills, machine learning systems design, large language model usage, retrieval-augmented generation systems, model fine-tuning, and autonomous AI agents. ... -
15
Agent Behavior Monitoring
The open source post-building layer for agents
Agent Behavior Monitoring is an open-source framework designed to monitor, evaluate, and improve the behavior of AI agents operating in real or simulated environments. The system focuses on agent behavior monitoring by collecting interaction data and analyzing how agents perform across different scenarios and tasks. Developers can use the framework to observe agent actions in both online production environments and offline evaluation settings, making it useful for debugging and performance analysis. ... -
16
LongBench
LongBench v2 and LongBench (ACL 25'&24')
LongBench is a comprehensive benchmark designed to evaluate the ability of large language models to understand and reason over very long textual contexts. Traditional language model benchmarks typically evaluate tasks involving relatively short inputs, which does not reflect many real-world applications such as analyzing large documents or entire code repositories. LongBench addresses this gap by providing datasets that require models to process and reason over long sequences of text across multiple tasks. The benchmark includes multiple categories such as single-document question answering, multi-document reasoning, summarization, long dialogue understanding, and code analysis. ... -
17
LLM Colosseum
Benchmark LLMs by fighting in Street Fighter 3
...The system places language models inside the environment of the classic video game Street Fighter III, where they must interpret the game state and decide which actions to perform during combat. This setup creates a dynamic environment that tests reasoning, situational awareness, and decision-making abilities in real time. Instead of relying purely on reward signals as in reinforcement learning agents, the models analyze contextual information and generate strategic actions based on the game environment. Performance is evaluated using a competitive ranking system that assigns models an ELO rating based on their results across matches against other models. -
18
CAG
Cache-Augmented Generation: A Simple, Efficient Alternative to RAG
CAG, or Cache-Augmented Generation, is an experimental framework that explores an alternative architecture for integrating external knowledge into large language model responses. Traditional retrieval-augmented generation systems rely on real-time retrieval of documents from databases or vector stores during inference. CAG proposes a different approach by preloading relevant knowledge into the model’s context window and precomputing the model’s key-value cache before queries are processed. This strategy allows the model to generate responses using the cached context directly, eliminating the need for repeated retrieval operations during runtime. ... -
19
LLM Guard
The Security Toolkit for LLM Interactions
...The toolkit also helps prevent sensitive information leaks by identifying secrets such as API keys or credentials before they are processed by the model. LLM Guard supports both input and output filtering pipelines, allowing developers to sanitize prompts and validate generated responses in real time. The library integrates easily with existing AI frameworks and can be deployed in production environments to enhance the security posture of LLM-based applications. -
20
Torrra
A Python tool that lets you search and download torrents
Torrra is an open-source BitTorrent client and library focused on simplicity, performance, and extensibility for developers and self-hosted enthusiasts. It provides a command-line interface (CLI) and API that make it easy to add torrenting functionality to applications or automate downloads within scripts and workflows. The core of Torrra is built with modern asynchronous I/O and efficient resource handling, allowing it to manage multiple active torrents, peer connections, and swarm... -
21
AI Agents Masterclass
Follow along with my AI Agents Masterclass videos
...The project includes structured lessons, code examples, and practical exercises that cover foundational concepts like prompt engineering, chaining agents, tool usage, plan execution, evaluation, and safety considerations. It breaks down how autonomous agents interact with external systems, handle iterative reasoning, and integrate with third-party services or APIs to perform real tasks — for example, web search, browsing, scheduling, or coding assistance. Students of the masterclass can follow written modules or Jupyter notebooks that illustrate concepts step by step and progressively build more capable agents. The content is suitable for both beginners and intermediate developers because it starts with basic principles and escalates to advanced architectures like multi-agent coordination. -
22
StreamSpeech
StreamSpeech is a seamless model for offline speech recognition
...The model supports eight tasks: offline ASR, speech-to-text translation, speech-to-speech translation, and TTS, as well as their streaming or simultaneous counterparts, all handled by the same underlying system. During simultaneous translation, StreamSpeech can optionally output intermediate ASR transcripts and text translations, giving users or downstream applications real-time visibility into what the system is hearing and how it is translating. -
23
MuJoCo Playground
An open source library for GPU-accelerated robot learning
...MuJoCo Playground supports both the MJX JAX implementation and the Warp physics engine, enabling flexible use across research pipelines. The environments are designed for fast training, compatibility with reinforcement learning libraries, and real-time trajectory visualization using rscope. -
24
GenAI Processors
GenAI Processors is a lightweight Python library
...Processors can be composed sequentially (to build multi-step flows) or in parallel (to fan-out work and merge results), which makes sophisticated agent behaviors easy to express with simple operators. The library offers built-in processors for classic turn-based Gemini calls as well as Live API streaming, so you can mix “batch” and real-time interactions in the same graph. It leans on Python’s asyncio to coordinate concurrency, handle network I/O, and juggle background compute threads without blocking. -
25
NVIDIA Isaac GR00T
NVIDIA Isaac GR00T N1.5 is the world's first open foundation model
...It accepts multimodal inputs—such as language and images—and uses a diffusion transformer architecture built upon vision-language encoders, enabling adaptive robot behaviors across diverse environments. It is designed to be customizable via post-training with real or synthetic data. The vision-language model remains frozen during both pretraining and finetuning, preserving language understanding and improving generalization. Streamlined MLP connection between vision encoder and LLM with added layer normalization.
