Olmocr
A toolkit designed for converting and linearizing PDFs to create datasets optimized for large language model (LLM) training and evaluation.
Open-source AI tools in this directory span local coding agents, multi-model chat clients, and automation platforms. Browse options like Claude Code for terminal-based agentic coding, Activepieces for integration-heavy workflows, and ChatALL for talking to several models side by side. Every listing is free to use in your own projects.
190 tools available
A toolkit designed for converting and linearizing PDFs to create datasets optimized for large language model (LLM) training and evaluation.
State-of-the-art Machine Learning library for Pytorch, TensorFlow, and JAX, providing thousands of pre-trained models for natural language processing, computer vision, and other areas.
Langfuse is an open source LLM engineering platform providing observability, metrics, evaluations, prompt management, and more for LLMs. It integrates with OpenTelemetry, Langchain, OpenAI SDK, LiteLLM, and more.
Inference code for Llama models, a versatile solution for running Llama model inferences efficiently.
Anthropic's educational courses focused on AI and technology development.
An AI-powered web browsing framework that emphasizes simplicity and extensibility, allowing for easy customization and integration with various web applications.
Postgres enhanced with GPU acceleration for efficient machine learning and AI applications.
A versatile AI chat interface compatible with various models, providing seamless integration and enhanced user interaction.
A natural language interface for computers that enhances human-computer interaction through voice and text commands.
An all-in-one open-source embeddings database for semantic search, LLM orchestration, and language model workflows.
Memory for AI Agents in 5 lines of code. Cognee provides a lightweight and efficient memory management solution tailored for AI agent development.
A minimalist deep learning framework designed to be simple and easy to understand, inspired by pytorch and micrograd.
Our Newsletter
Get short emails with useful ai projects, releases, and repos worth watching.
A cutting-edge open-source operating system for robotics, enhancing the driver assistance systems on over 275 supported cars.
Build multimodal AI applications with a cloud-native stack.
STORM is an LLM-powered knowledge curation system designed to research topics and generate comprehensive full-length reports with citations. Developed by Stanford's OVAL team, STORM leverages large language models to streamline information gathering and synthesis.
Buzz transcribes and translates audio offline on your personal computer, powered by OpenAI's Whisper.
Cocoindex is a powerful data transformation framework designed for AI applications. It is ultra performant, offering incremental processing capabilities.
Ragapp provides the easiest way to implement Agentic Retrieval-Augmented Generation (RAG) capabilities in enterprise environments, enhancing AI-driven search and knowledge management with minimal setup.
A comprehensive programming framework for building agentic AI applications, supporting various integrations and community interactions.
Amurex is the world's first AI meeting copilot, acting as an invisible companion for both work and life, enhancing productivity.
Specification and comprehensive documentation for the Model Context Protocol, a standard for managing AI model contextual data efficiently.
Plate is a rich-text editor powered by AI, providing a feature-rich text editing experience.
Qdrant - High-performance, massive-scale Vector Database and Vector Search Engine for the next generation of AI. Also available in the cloud.
A high-performance, cloud-native vector database designed for scalable and efficient vector Approximate Nearest Neighbor (ANN) search.
A sophisticated text-prompted generative audio model that allows for dynamic sound generation based on text prompts.
๐ก Open source home automation that prioritizes local control and privacy, making your smart home truly yours.
AI orchestration framework to build customizable, production-ready LLM applications. Connect components such as models, vector databases, and file converters to pipelines or agents that can interact with your data. Best suited for building Retrieval-Augmented Generation (RAG), question answering, semantic search, or conversational agent chatbots.
Laminar - an open-source all-in-one platform for engineering AI products. Create a data flywheel for your AI applications, with features such as Traces, Evals, Datasets, and Labels. Part of the Y Combinator Summer 2024 batch.
Cube is a universal semantic layer platform for AI, BI, spreadsheets, and embedded analytics. It serves as an access layer for data analytics, providing real-time data access and integration across multiple sources.
A curated and ranked collection of top machine learning libraries and tools for Python. Regularly updated to highlight the best open-source machine learning projects in the Python ecosystem.
Get notified about new tools and updates to existing ones.