chitu: a production-grade inference engine with broad hardware support and scalable deployment options
A production-grade high-performance inference engine that supports diverse hardware backends and scalable deployment for large language models.
catalyst: a PyTorch framework for accelerated deep learning R&D that eliminates training loop boilerplate
A PyTorch framework for deep learning R&D that removes training loop boilerplate to accelerate experimentation and reproducibility.
mindshub: a unified workspace for delegating multi-step tasks to open-source agents and publishing their output as shareable artifacts
A unified workspace for delegating multi-step tasks to open-source agents to automate research, analysis, and reporting into shareable artifacts.
emdash: a desktop app for running AI coding agents in parallel using isolated Git worktrees
A desktop application for running multiple AI coding agents in parallel, using Git worktrees to isolate each task and supporting both local and remote projects.
LobsterAI: an all-scenario desktop office assistant agent that operates on local files and browser workflows
A desktop AI agent that automates office workflows by interacting with local files, terminal commands, and browser automation, featuring remote control via IM platforms.
FluidAudio: a local audio AI SDK for Apple devices that offloads inference to the Apple Neural Engine
A Swift SDK for local, low-latency audio AI on Apple devices that offloads inference to the Apple Neural Engine for transcription, text-to-speech, and speaker diarization.
moonshine: a low-latency on-device voice toolkit for real-time conversational agents
An open-source AI toolkit for building real-time, on-device voice agents and applications with low-latency speech-to-text and text-to-speech capabilities.
ComfyUI: a modular node-graph engine for precise control over generative AI workflows
A modular, node-based AI engine for visual professionals to create complex generative workflows for images, video, audio, and 3D content.
WhisperLiveKit: an ultra-low-latency self-hosted speech-to-text pipeline with real-time translation and speaker diarization
An ultra-low-latency, self-hosted speech-to-text pipeline that enables real-time transcription and translation using advanced streaming policies and multiple ASR backends.
vision: a PyTorch library for computer vision datasets, model architectures, and image transformations
A PyTorch library providing popular datasets, model architectures, and image transformations for computer vision.
mellea: a Python library for writing structured, testable generative programs with type-annotated outputs and automatic repair
A Python library for building predictable AI workflows by turning typed functions into structured LLM calls with automatic validation and retries.
agentic-awesome-skills: an installable library of 1,935+ agentic skills and playbooks for AI coding assistants
An installable library of 1,935+ agentic skills and playbooks for AI coding assistants like Claude Code and Cursor to improve task execution and context.
executorch: a unified on-device AI inference engine for deploying PyTorch models across mobile and embedded hardware
A unified solution for deploying PyTorch AI models on-device, from smartphones to microcontrollers, using a lightweight C++ runtime and ahead-of-time compilation.
darts: a unified Python library for time series forecasting and anomaly detection using statistical and deep learning models
A Python library for user-friendly time series forecasting and anomaly detection, offering a unified API for models ranging from ARIMA to deep neural networks.
loopy: a framework for creating and managing iterative feedback loops for AI agents
A library and agent skill for creating and managing "loops"—iterative, feedback-driven prompts that allow AI agents to repeat and verify tasks until they succeed.
orca: an AI orchestrator for running multiple CLI coding agents in parallel isolated worktrees
An AI orchestrator that lets developers run multiple CLI coding agents in parallel isolated worktrees with a unified desktop and mobile interface.
activepieces: an open-source AI automation platform that turns TypeScript integrations into MCP servers for LLMs
An open-source alternative to Zapier that enables AI-powered workflow automation through a no-code builder and a TypeScript-based integration framework.
FinceptTerminal: a native C++20 financial intelligence platform with institutional-grade analytics and AI-driven investment agents
A native C++20 financial intelligence platform providing institutional-grade analytics, AI agents, and connectivity to over 100 data sources for professional financial analysis.
antigravity-awesome-skills: an installable library of 1,929+ agentic skills and playbooks for AI coding assistants
An installable library of 1,929+ agentic skills and playbooks for AI coding assistants like Claude Code and Cursor to standardize recurring development tasks.
giskard-oss: a testing and evaluation framework for agentic systems featuring automated red-teaming and LLM-as-judge evals
An open-source Python library for testing and evaluating agentic systems, providing tools for automated red-teaming, vulnerability scanning, and RAG evaluation.
graphify: a knowledge graph generator for codebases that replaces grepping with path-tracing and semantic queries
A tool that maps codebases and documentation into a searchable knowledge graph, enabling developers to query relationships and trace paths between concepts instead of grepping files.
hermex: a native iOS control plane for managing self-hosted AI agents
A native SwiftUI iPhone app that serves as a mobile control plane for self-hosted hermes-webui AI agents, ensuring data and compute remain on the user's own hardware.
eliza: a local-first agentic operating system with on-device models and integrated computer control
A local-first agentic operating system that integrates AI assistants into the device runtime, providing on-device models and direct control over computer interfaces and messaging apps.
company-research-agent: what it is, what problem it solves & why it's gaining traction
A multi-agent AI tool that automates company research by gathering data from multiple sources and synthesizing it into comprehensive reports using a pipeline of specialized agents.
CubeSandbox: a high-performance secure sandbox service for AI agents with hardware-level isolation and sub-60ms boot times
A high-performance, secure sandbox service for AI agents that provides hardware-isolated MicroVMs with sub-60ms boot times and E2B SDK compatibility.
nasiko: a developer control plane for centralized management and intelligent routing of containerized AI agents
An AI agent developer control plane that provides centralized management, intelligent routing, and observability for production AI agent ecosystems.
VLM-R1: a stable and generalizable R1-style vision-language model trained with GRPO for multimodal reasoning
VLM-R1 is a framework for training R1-style Large Vision-Language Models using GRPO to improve reasoning and generalization in tasks like visual grounding, math, and object detection.
unity-mcp: an MCP-based bridge that enables LLMs to control the Unity Editor via natural language
A bridge that connects AI assistants to the Unity Editor via the Model Context Protocol, enabling developers to manage scenes, assets, and scripts using natural language.
meetily: what it is, what problem it solves & why it's gaining traction
Meetily is a privacy-first, open-source AI meeting assistant that provides local transcription and AI-powered summaries to ensure sensitive meeting data never leaves the user's device.
agency-agents-zh: a comprehensive library of 266 plug-and-play AI expert roles for professional workflows across 20 business departments
A library of 266 specialized AI expert roles with defined workflows and personas, compatible with 18 AI programming tools to provide professional-grade output across 20 business domains.
airllm: a memory-efficient inference engine that runs massive LLMs on low-end GPUs by loading one layer at a time
A library that enables running massive LLMs (up to 671B parameters) on consumer GPUs with as little as 4GB-12GB VRAM by loading models layer-by-layer.
lmdeploy: a high-performance compression and serving toolkit for LLMs and VLMs
A toolkit for compressing, deploying, and serving LLMs and VLMs, providing high-performance inference engines and quantization to maximize throughput.
WorkShadow: a local-first work log companion with AI-powered semantic search and automated report generation
A local-first desktop work log application that uses AI for semantic search, automated report generation, and Q&A over personal work history while keeping data on the user's machine.
Handy: a privacy-focused offline speech-to-text tool that pastes transcriptions directly into any active text field
A free, open-source, offline speech-to-text application that transcribes spoken words directly into any text field on a computer.
3dgrut: a hybrid Gaussian Splatting framework that combines rasterization and ray tracing for distorted cameras and complex optical effects
A framework implementing 3D Gaussian Ray Tracing and Unscented Transform to enable distorted camera support and secondary ray effects like reflections and shadows in Gaussian Splatting.
WorldGen: a fast text-to-3D scene generator for creating immersive 360° environments
WorldGen is a tool that generates immersive 3D scenes from text prompts or images in seconds, supporting both Gaussian Splatting and mesh outputs for VR, games, and simulations.
claude-scientific-writer: a deep research and writing tool for generating publication-ready scientific papers and grant proposals with verified citations
A deep research and writing tool that generates publication-ready scientific papers, grant proposals, and clinical reports backed by real-time literature search and verified citations.
skills: a browser automation CLI for AI agents with anti-bot bypass and human-in-the-loop handoff
A browser automation CLI for AI agents that bypasses anti-bot walls and provides token-efficient, indexed interactions for easier web navigation.
sem: a semantic version control tool that tracks changes to functions and classes instead of lines
A semantic version control tool built on Git that tracks changes at the entity level (functions, classes, methods) rather than lines, providing deeper structural insights for humans and AI agents.
agent-scripts: a centralized hub for managing shared AI agent rules and reusable workflow skills across local workspaces
A centralized management system for shared AI agent instructions, reusable skills, and portable helper scripts across local workspaces.
page-agent: a client-side GUI agent that enables natural language control of web interfaces via text-based DOM manipulation
A JavaScript library that enables natural language control of web interfaces through text-based DOM manipulation, allowing developers to to embed AI copilots directly into webpages.
ai-website-cloner-template: a reusable template for reverse-engineering websites into Next.js codebases using AI coding agents
A reusable template for reverse-engineering websites into Next.js codebases using AI coding agents to automate design extraction and component reconstruction.
ISAT_with_segment_anything: an interactive semi-automatic image segmentation annotation tool based on Segment Anything
An interactive semi-automatic image segmentation annotation tool that uses the Segment Anything Model (SAM) to accelerate the creation of labeled datasets.
graphify: a codebase-to-knowledge-graph mapper that integrates with AI coding assistants for architectural querying
A tool that maps codebases and project assets into a queryable knowledge graph, integrating with AI coding assistants to provide architectural context.
ai-berkshire: a value-investing research framework that simulates a multi-agent team of investment masters to produce decision-grade reports
A structured investment research framework for Claude Code and Codex that systematizes value investing methodologies to produce professional, decision-grade financial reports.
chatwiki: a workflow automation platform that transforms WeChat official accounts into AI agents
A workflow automation platform that turns WeChat official accounts into AI agents with drag-and-drop workflows and integrated knowledge bases.
PaddleOCR: what it is, what problem it solves & why it's gaining traction
A global leading OCR toolkit and document AI engine that converts PDFs and images into structured JSON or Markdown data for LLM-ready applications.
agentrq: what it is, what problem it solves & why it's gaining traction
AgentRQ is an agent-human collaboration platform that uses the Model Context Protocol (MCP) to synchronize task management and communication between humans and AI agents in real-time.
skills: what it is, what problem it solves & why it's gaining traction
A collection of Agent Skills and MCP servers that enable AI coding assistants to build, manage, and troubleshoot applications on the Cloudflare Developer Platform.
a2a-python: what it is, what problem it solves & why it's gaining traction
A Python SDK for building agentic applications that follow the Agent2Agent (A2A) Protocol, enabling standardized communication between AI agents.