Open Source Python Artificial Intelligence Software - Page 78
Sort By:
Python Artificial Intelligence Software
View 13566 business solutionsBrowse free open source Python Artificial Intelligence Software and projects below. Use the toggles on the left to filter open source Python Artificial Intelligence Software by OS, license, language, programming language, and project status.
-
$300 in Free Credit Towards Top Cloud ServicesStart your project in minutes. After credits run out, 20+ products include free monthly usage. Only pay when you're ready to scale.
-
Gemini 3 and 200+ AI Models on One PlatformBuild generative AI apps with Vertex AI. Switch between models without switching platforms.
-
1
JEPA
PyTorch code and models for V-JEPA self-supervised learning from video
JEPA (Joint-Embedding Predictive Architecture) captures the idea of predicting missing high-level representations rather than reconstructing pixels, aiming for robust, scalable self-supervised learning. A context encoder ingests visible regions and predicts target embeddings for masked regions produced by a separate target encoder, avoiding low-level reconstruction losses that can overfit to texture. This makes learning focus on semantics and structure, yielding features that transfer well with simple linear probes and minimal fine-tuning. The repository provides training recipes, data pipelines, and evaluation utilities for image JEPA variants and often includes ablations that illuminate which masking and architectural choices matter. Because the objective is non-autoregressive and operates in embedding space, JEPA tends to be compute-efficient and stable at scale. The approach has become a strong alternative to contrastive or pixel-reconstruction methods for representation learning. -
2
JFIPA is intended to be a scalable, easy-to-deploy router and parser of messages between agents using the FIPA Agent Communication Language represented as XML
-
3
JSON_REPAIR
A python module to repair invalid JSON from LLMs
json_repair is an open-source Python library designed to automatically fix malformed JSON data and convert it into valid, parseable structures. The tool is particularly useful in scenarios where JSON output is generated by large language models or external services that may produce syntactically invalid responses. Instead of failing when encountering errors such as missing quotes, trailing commas, or incomplete objects, the library analyzes the malformed data and reconstructs it into valid JSON. The repair process can also be combined with optional JSON Schema validation to enforce structural constraints and ensure the output conforms to expected data types and formats. Developers can integrate the library into applications as a drop-in replacement for standard JSON parsing functions, allowing systems to tolerate imperfect structured data without crashing. -
4
Janus
Unified Multimodal Understanding and Generation Models
Janus is a sophisticated open-source project from DeepSeek AI that aims to unify both visual understanding and image generation in a single model architecture. Rather than having separate systems for “look and describe” and “prompt and generate”, Janus uses an autoregressive transformer framework with a decoupled visual encoder—allowing it to ingest images for comprehension and to produce images from text prompts with shared internal representations. The design tackles long-standing conflicts in multimodal models: namely that the visual encoder has to serve both analysis (understanding) and synthesis (generation) roles. By splitting those pathways but keeping one unified core transformer, Janus maintains flexibility and achieves strong performance across tasks previously requiring distinct architectures. The repository includes pretrained checkpoints (for example 1.3B and 7B parameter versions), a Gradio demo, and guidance for local deployment. -
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.
-
5
Jacomma is a framework for developing network-aware reactive information agents, using the ICM agent communication infrastructure. It offers transparent ICM bindings for java, and includes a lightweight agent execution environment.
-
6
jrgp is a strong-typed Genetic Programming system, which features a graphical interface (gool) to setup and run GP-problems and a tool (fs-d) that greatly simplifies the definition of a GP-problem.
-
7
Jina
Build cross-modal and multimodal applications on the cloud
Jina is a framework that empowers anyone to build cross-modal and multi-modal applications on the cloud. It uplifts a PoC into a production-ready service. Jina handles the infrastructure complexity, making advanced solution engineering and cloud-native technologies accessible to every developer. Build applications that deliver fresh insights from multiple data types such as text, image, audio, video, 3D mesh, PDF with Jina AI’s DocArray. Polyglot gateway that supports gRPC, Websockets, HTTP, GraphQL protocols with TLS. Intuitive design pattern for high-performance microservices. Seamless Docker container integration: sharing, exploring, sandboxing, versioning and dependency control via Jina Hub. Fast deployment to Kubernetes, Docker Compose and Jina Cloud. Improved engineering efficiency thanks to the Jina AI ecosystem, so you can focus on innovating with the data applications you build. -
8
Jina-Serve
Build multimodal AI applications with cloud-native stack
Jina Serve is an open-source framework designed for building, deploying, and scaling AI services and machine learning pipelines in production environments. The framework allows developers to create microservices that expose machine learning models through APIs that communicate using protocols such as HTTP, gRPC, and WebSockets. It is built with a cloud-native architecture that supports deployment on local machines, containerized environments, or large orchestration platforms such as Kubernetes. Jina Serve focuses on making it easier to turn machine learning models into production-ready services without forcing developers to manage complex infrastructure manually. The framework supports many major machine learning libraries and data types, making it suitable for multimodal AI systems that process text, images, audio, and other inputs. -
9
KIS Open API
Korea Investment & Securities Open API Github
The open-trading-api repository from Korea Investment & Securities provides sample code and developer resources for interacting with the KIS Developers Open Trading API, which enables programmatic access to financial market data and automated trading functionality. The project is designed primarily for Python developers and AI automation environments that want to build investment applications, algorithmic trading systems, or financial analytics tools using the brokerage’s infrastructure. It includes example scripts that demonstrate how to authenticate with the service, retrieve financial data, and execute trading operations through REST and WebSocket interfaces. The repository organizes its examples into two main groups: code designed for direct user implementation and simplified examples intended for large language model agents or automation workflows. -
8 Monitoring Tools in One APM. Install in 5 Minutes.AppSignal works out of the box for Ruby, Elixir, Node.js, Python, and more. 30-day free trial, no credit card required.
-
10
KVCache-Factory
Unified KV Cache Compression Methods for Auto-Regressive Models
KVCache-Factory is an open-source research framework designed to explore and implement unified key-value cache compression techniques for autoregressive transformer models. In large language models, the key-value cache stores intermediate attention states that enable efficient token generation during inference, but these caches can consume large amounts of GPU memory when handling long contexts. KVCache-Factory provides a platform for implementing and evaluating multiple compression strategies that reduce memory usage while preserving model performance. The framework integrates several state-of-the-art methods such as PyramidKV, SnapKV, H2O, and StreamingLLM, allowing researchers to compare and experiment with different approaches within the same environment. It also supports advanced inference configurations such as Flash Attention v2 and multi-GPU inference setups for very large models. -
11
Kaggle Solutions
Collection of Kaggle Solutions and Ideas
Kaggle Solutions is an open-source repository that compiles winning solutions, insights, and educational resources from hundreds of Kaggle data science competitions. The repository acts as a knowledge base for competitive machine learning by collecting solution write-ups, discussion threads, code notebooks, and tutorial resources shared by top Kaggle participants. Each competition entry typically includes information about the dataset, evaluation metrics, modeling strategies, and techniques used by high-ranking competitors. The repository also highlights important machine learning concepts such as feature engineering, cross-validation strategies, ensemble modeling, and post-processing methods commonly used in winning solutions. Because the content is organized by competition categories such as computer vision, natural language processing, tabular data, and time-series forecasting, users can explore techniques relevant to specific problem types. -
12
Karate Club
An API Oriented Open-source Python Framework for Unsupervised Learning
Karate Club is an unsupervised machine learning extension library for NetworkX. Karate Club consists of state-of-the-art methods to do unsupervised learning on graph-structured data. To put it simply it is a Swiss Army knife for small-scale graph mining research. First, it provides network embedding techniques at the node and graph level. Second, it includes a variety of overlapping and non-overlapping community detection methods. Implemented methods cover a wide range of network science (NetSci, Complenet), data mining (ICDM, CIKM, KDD), artificial intelligence (AAAI, IJCAI) and machine learning (NeurIPS, ICML, ICLR) conferences, workshops, and pieces from prominent journals. -
13
Kashgari
Kashgari is a production-level NLP Transfer learning framework
Kashgari is a simple and powerful NLP Transfer learning framework, build a state-of-art model in 5 minutes for named entity recognition (NER), part-of-speech tagging (PoS), and text classification tasks. -
14
Keepsake
Version control for machine learning
Keepsake is a Python library that uploads files and metadata (like hyperparameters) to Amazon S3 or Google Cloud Storage. You can get the data back out using the command-line interface or a notebook. -
15
Keras Attention Mechanism
Attention mechanism Implementation for Keras
Many-to-one attention mechanism for Keras. We demonstrate that using attention yields a higher accuracy on the IMDB dataset. We consider two LSTM networks: one with this attention layer and the other one with a fully connected layer. Both have the same number of parameters for a fair comparison (250K). The attention is expected to be the highest after the delimiters. An overview of the training is shown below, where the top represents the attention map and the bottom the ground truth. As the training progresses, the model learns the task and the attention map converges to the ground truth. We consider many 1D sequences of the same length. The task is to find the maximum of each sequence. We give the full sequence processed by the RNN layer to the attention layer. We expect the attention layer to focus on the maximum of each sequence. -
16
Keras TCN
Keras Temporal Convolutional Network
TCNs exhibit longer memory than recurrent architectures with the same capacity. Performs better than LSTM/GRU on a vast range of tasks (Seq. MNIST, Adding Problem, Copy Memory, Word-level PTB...). Parallelism (convolutional layers), flexible receptive field size (possible to specify how far the model can see), stable gradients (backpropagation through time, vanishing gradients). The usual way is to import the TCN layer and use it inside a Keras model. The receptive field is defined as the maximum number of steps back in time from current sample at time T, that a filter from (block, layer, stack, TCN) can hit (effective history) + 1. The receptive field of the TCN can be calculated. Once keras-tcn is installed as a package, you can take a glimpse of what is possible to do with TCNs. Some tasks examples are available in the repository for this purpose. -
17
KerasTuner
A Hyperparameter Tuning Library for Keras
KerasTuner is an easy-to-use, scalable hyperparameter optimization framework that solves the pain points of hyperparameter search. Easily configure your search space with a define-by-run syntax, then leverage one of the available search algorithms to find the best hyperparameter values for your models. KerasTuner comes with Bayesian Optimization, Hyperband, and Random Search algorithms built-in, and is also designed to be easy for researchers to extend in order to experiment with new search algorithms. -
18
Key-book
Proofs, cases, concept supplements, and reference explanations
The book "Introduction to Machine Learning Theory" (hereinafter referred to as "Introduction") written by Zhou Zhihua, Wang Wei, Gao Wei, and other teachers fills the regret of the lack of introductory works on machine learning theory in China. This book attempts to provide an introductory guide for readers interested in learning machine learning theory and researching machine learning theory in an easy-to-understand language. "Guide" mainly covers seven parts, corresponding to seven important concepts or theoretical tools in machine learning theory, namely: learnability, (hypothesis space) complexity, generalization bound, stability, consistency, convergence rate, regret circle. Daoyin is a highly theoretical book, involving a large number of mathematical theorems and various proofs. Although the writing team has reduced the difficulty as much as possible, due to the nature of machine learning theory, the book still places high demands on the reader's mathematical background. -
19
Spider that recollects data from MySpace Social Network. At now, it is only designed to extract information from native american people because it is used for a social science study in the UNAM (Universidad Nacional Autónoma de México).
-
20
Kiln
Open source platform for managing, testing, and deploying AI apps
Kiln is an open source platform designed to help developers build, evaluate, and deploy AI-powered applications with greater structure and reliability. It provides a unified environment for managing prompts, datasets, and evaluation workflows, allowing teams to iterate on AI behavior in a controlled and measurable way. Kiln emphasizes reproducibility, enabling users to track changes to prompts and models while comparing outputs across different configurations. Kiln also supports systematic testing of AI systems by defining evaluation criteria and running experiments to assess performance over time. Its workflow-oriented approach helps teams move from experimentation to production by organizing assets and results in a consistent format. It is particularly useful for teams working with large language models who need visibility into how changes impact outputs and overall system quality. -
21
Knock Knock
Get notified when your training ends
Knock Knock is a lightweight Python utility created by the Hugging Face team that allows developers to receive notifications when long-running machine learning tasks finish or fail. Training deep learning models often takes hours or even days, making it inconvenient for engineers to constantly monitor progress manually. The library solves this problem by adding simple decorators or command-line commands that automatically send notifications when a process completes or crashes. These alerts can be delivered through several communication platforms such as email, Slack, Telegram, or other messaging services. The goal of the project is to allow developers to monitor experiments remotely without needing to stay connected to the training environment. By adding only a few lines of code, the library can wrap around a training function and report execution status. -
22
Koila
Prevent PyTorch's `CUDA error: out of memory` in just 1 line of code
Koila is a lightweight Python library designed to help developers avoid memory errors when training deep learning models with PyTorch. The library introduces a lazy evaluation mechanism that delays computation until it is actually required, allowing the framework to better estimate the memory requirements of a model before execution. By building a computational graph first and executing operations only when necessary, koila reduces the risk of running out of GPU memory during the forward pass of neural network training. This approach enables developers to experiment with larger batch sizes and more complex architectures while maintaining stable training behavior. The system acts as a thin wrapper around PyTorch tensors and operations, meaning that it integrates easily into existing PyTorch code without requiring major changes to model implementations. It is particularly useful in environments where GPU resources are limited or where models frequently encounter CUDA memory errors. -
23
Kor
LLM
This is a half-baked prototype that “helps” you extract structured data from text using LLMs. Specify the schema of what should be extracted and provide some examples. Kor will generate a prompt, send it to the specified LLM and parse out the output. You might even get results back. -
24
Krixik
Documentation for the Krixik Python client
Small/specialized AI models are an oft-necessary complement—or alternative—to "big AI" offerings. However, infrastructure for small AI tends to be underwhelming, so building with specialized AI can be difficult, time-consuming, and even expensive. Iterating with different models, and particularly with different combinations of these models, can thus be rendered unfeasible. -
25
Kubeflow pipelines
Machine Learning Pipelines for Kubeflow
Kubeflow is a machine learning (ML) toolkit that is dedicated to making deployments of ML workflows on Kubernetes simple, portable, and scalable. A pipeline is a description of an ML workflow, including all of the components in the workflow and how they combine in the form of a graph. The pipeline includes the definition of the inputs (parameters) required to run the pipeline and the inputs and outputs of each component. A pipeline component is a self-contained set of user code, packaged as a Docker image, that performs one step in the pipeline. For example, a component can be responsible for data preprocessing, data transformation, model training, and so on.
