An AI agent framework that runs natively on Android, managing sessions and tool execution on-device while using external LLM APIs for inference.

A tool for creating digital personas of former partners by analyzing chat histories and personality traits to simulate their specific tone and emotional patterns.

A composable development process for agentic coding harnesses that organizes AI coding workflows into modular, reusable skills and structured pipelines.

A self-hosted AI agent orchestration platform that allows operations teams to visually design, manage, and audit agent workflows while engineers handle the system integrations.

A family of multimodal AI models for high-quality, expressive, and real-time translation across nearly 100 languages, supporting speech and text modalities.

A fast non-linear dimension reduction library for visualizing high-dimensional data and preprocessing for machine learning tasks.

A minimalistic and portable C-based computer vision library providing state-of-the-art algorithms for face, object, and text detection.

A Python package for uplift modeling and causal inference that estimates the causal impact of interventions on individual users to optimize targeting and personalization.

A Redis module that adds full-text search, secondary indexing, and vector similarity search to Redis, enabling high-performance querying of database records.

A multi-agent workspace that transforms existing AI CLI tools into a unified orchestration hub for parallel execution and automated workflows.

A Python library for Chinese NLP preprocessing and parsing, providing tools for data cleaning, entity extraction, and automatic LLM evaluation.

oneDNN (oneAPI Deep Neural Network Library) is an open‑source, cross‑platform performance library that supplies highly optimized CPU and GPU kernels for deep‑learning operators. It implements the oneAPI specification, supports Intel, AMD, Arm, and experimental Power/IBM z/RISC‑V hardware, and is used by major frameworks such as PyTorch, TensorFlow, ONNX Runtime, and llama.cpp.

A set of ComfyUI nodes that bring Photoshop-like layer and mask compositing functionality to the platform, reducing the need for external editing software.

An open-source self-evolving agent framework that dynamically updates its skills, memory, and brain model through interaction while employing a multi-layer security scaffold.

A Gaussian processes framework in Python that provides tools for implementing and optimizing probabilistic models for regression and classification.

kimchi is a terminal‑based AI coding assistant built on the pi‑mono SDK. It orchestrates one or more LLMs across roles (planner, builder, reviewer, explorer, researcher), supports multi‑model routing, persistent project management via Ferment, tag‑based usage tracking, optional LSP integration, and remote‑session teleporting.

A collection of GPU-accelerated graph analytics packages that enable the creation and manipulation of graphs and the execution of scalable graph algorithms.

A Rust ecosystem for developing AI applications using local or remote models, featuring a unified interface for multi-modal models and a compiler-backed inference runtime.

A Python framework for AI-driven character animation that unifies neural network training, inference, and visualization using NumPy and PyTorch.

An open-source multi-agent AI assistant that allows users to build autonomous AI teams and companies to execute complex tasks across desktop, web, and mobile platforms.

A comprehensive audio and video processing toolkit that extends OpenAI's Whisper for transcription, speaker diarization, summarization, and RAG-based video chatting.

An autonomous agent framework for Elixir that provides a formalized architecture for state management, multi-agent orchestration, and fault-tolerant workflows.

A Vue.js implementation of Ant Design X, providing a UI component library and data flow tools specifically designed for building AI conversational interfaces.

An AI agent skill that allows AI assistants to search and recommend 10,000+ curated prompts for the Nano Banana Pro (Gemini) image generation model.

InternAgent‑1.5 is an open‑source autonomous‑agent framework for long‑horizon scientific discovery. It can generate hypotheses, design and run (simulated) experiments, optimise algorithms (via the MLEvolve core), and answer research questions using a Deep Research pipeline. The system includes a persistent memory module, task suites for algorithm discovery and paper‑reproduction, and unified launch scripts for discovery or QA modes.

A memory layer for AI trading agents that provides outcome-weighted recall of past trades and a tamper-evident SHA-256 audit trail for regulatory compliance.

Official Python client for DeepL’s translation and text‑improvement API, supporting text, document, glossary, and custom‑instruction features.

An open-source standalone MCP host that enables developers to build and deploy AI agents by connecting LLMs with MCP servers.

CrewAI Studio is a Streamlit‑based GUI that lets you design, run and export multi‑agent AI crews built on the CrewAI framework, supporting several LLM providers and custom tools, with easy installation via Conda, virtualenv, Docker or one‑click deployment.

A scalable framework for time series forecasting that allows any scikit-learn compatible machine learning model to be used for forecasting millions of series.

A Go SDK that provides an interface for developers to integrate Google's generative AI models, like Gemini, into their Go applications.

A solution accelerator for building a conversational assistant that indexes unstructured organizational data to provide grounded answers with inline citations.

A production-ready foundation for AI chat apps that provides authentication, streaming, and unified access to over 120 AI models.

A library for evaluating AI model outputs using LLM-as-a-judge, RAG-specific metrics, and heuristic methods through a unified interface.

A modularized codebase for building and training small-scale large multimodal models, supporting a wide variety of LLMs, vision towers, and connectors.

A GPU-accelerated VLSI placement toolkit that treats chip component placement as a deep learning optimization problem to achieve massive speedups over traditional CPU tools.

A C++17 library for simplifying CUDA kernel benchmarking, offering parameter sweeps and detailed throughput and bandwidth measurements.

An AI-friendly MCP server that enables AI agents to search, read, and edit Notion workspaces via the Notion API.

A fast, secure MCP server that uses WebAssembly sandboxing to allow AI applications to safely execute plugins written in any WASM-compatible language.

A chat-based financial research platform that combines institutional-grade data from the Valyu API with secure Python code execution for advanced analysis.

An AI-native, cloud-native distributed file system that provides a high-performance POSIX layer and multi-tier caching over cloud object storage for AI training and Agent platforms.

A native Swift macOS menu bar app for tracking Claude Code token consumption, costs, and server-side usage limits in real-time.

A free, offline AI coding environment for Mac and Linux that integrates Ollama and OpenCode to provide local LLM-powered agentic coding without API costs.

NavDP is an end-to-end mapless navigation model using diffusion policies that enables robots to perform real-time path planning and obstacle avoidance with cross-embodiment generalization from simulation to reality.

A fast and accurate Korean morphological analyzer that uses statistical language models and Skip-Bigrams to resolve linguistic ambiguity and process large volumes of text.

An MCP server that automatically scans GitHub, npm, PyPI, Hacker News, and Stack Overflow to determine if a startup idea already exists and provides a reality score.

An AI-powered documentation generator that uses a multi-agent architecture to analyze codebases and automatically create READMEs and AI assistant configuration files.

A software library that combines tree-boosting with Gaussian processes and mixed-effects models to handle non-linearities and data dependencies like spatial or grouped effects.