A Zotero plugin that automates academic paper reading by using LLMs to generate Markdown notes, mind maps, and literature reviews.

A local CLI tool that indexes and searches past coding agent sessions to provide agents and developers with exact recall of historical decisions and tool calls.

AReaL is an open‑source, fully asynchronous reinforcement‑learning framework for training large reasoning and agentic models. It offers modular micro‑services, supports many RL algorithms, runs on GPUs, NPUs or Ray clusters, and ships with dozens of ready‑to‑run examples (math, coding, search, vision‑language, RLHF, etc.).

An ultra-low-latency, self-hosted speech-to-text pipeline that enables real-time transcription and translation using advanced simultaneous speech research and multiple model backends.

An autonomous, self-maintaining personal Wikipedia that uses AI to synthesize scattered documents, web clippings, and notes into a structured knowledge base.

An open-source workspace for building and running AI agents that can automate work through interactive chat or scheduled background tasks.

An open-source platform for running AI agents as a team, providing secure sandboxing, centralized credential injection, and identity provider integration.

An AI multimodal domain knowledge engine that transforms raw documents, audio, and video into ontology-powered knowledge services for enterprise AI agents.

An AI-powered toolset for Spine 2D that automates character rigging, asset positioning, and animation generation from raw images.

A local-first AI development workbench that integrates prompt optimization, evaluations, RAG, and fine-tuning into a single workflow for teams.

A collection of measurement-first agent skills that enable AI coding agents to audit and optimize web projects for performance, accessibility, and SEO using tools like Google Lighthouse.

M365 Copilot2API is a Go‑based self‑hosted gateway that translates Microsoft 365 Copilot’s private WebSocket protocol into standard OpenAI‑ and Anthropic‑compatible REST endpoints. It provides a familiar `/v1/chat/completions` (and related) API, supports streaming, function calling, multimodal inputs, and includes a web UI for account/OAuth management, API‑key handling, proxy pools, usage stats, and automatic session cleanup. The tool lets existing OpenAI/Anthropic clients (Claude Code, Cursor, etc.) call M365 Copilot without rewriting code, but it is unofficial and intended for personal research only.

Remember-R1 is a reinforcement learning framework designed to prevent multimodal models from forgetting visual information during long-context reasoning.

An orchestration framework for mathematical reasoning agents that uses a verified fact-graph memory to ensure correctness in complex proofs.

A comprehensive library of 57 AI Agent Skills for Codex and Claude Code, automating content creation pipelines from topic planning to video editing and commercial analysis.

An AI-native health data engine that standardizes fragmented health data from lab reports and wearables into LOINC/FHIR standards for AI reasoning.

An agentic omnichannel chat marketing platform that allows users to build AI-powered chatbots with a visual flow builder and self-host their automation.

A collection of professional LLM prompts and templates designed to convert academic research papers into legally compliant Chinese patent applications.

A terminal-based AI agent that helps developers complete software tasks and terminal operations by reading code, executing shell commands, and autonomously planning actions.

Biomni is a general-purpose biomedical AI agent that automates research tasks and hypothesis generation by combining LLM reasoning, retrieval-augmented planning, and code execution.

An adapter that enables the Claude Agent SDK to be used with any client that follows the Agent Client Protocol (ACP).

An open-source workbench for AI short drama and video production that manages the pipeline from scriptwriting and asset generation to final video synthesis.

A verifiable coding agent runtime that turns engineering processes into explicit execution graphs to ensure AI-generated code is researched, implemented, and verified for production.

myAiVideos is an open‑source, Docker‑compose‑based system that automates the whole short‑video creation workflow (topic → script → visuals → audio → post‑production → distribution) for Chinese content. It uses a FastAPI orchestrator plus a Java Spring‑Boot gateway for auth, routing, circuit‑breaking and metering, and integrates multiple LLM and multimodal models (DeepSeek, GLM, Kling, TTS services). The pipeline is layered, fail‑over capable, and fully observable via Langfuse and Prometheus.

An efficient portrait animation tool that animates static images of humans and animals using driving videos or images with precise stitching and retargeting control.

A visual review tool that lets users edit HTML and Markdown files directly and send batch feedback to AI agents instead of using chat prompts.

An autonomous AI agent for Android that plans and executes multi-step tasks across various apps using UI automation and a wide range of LLM providers.

A skill for AI agents that automatically transforms a software project into a shareable launch video with music, motion, and share copy using Hyperframes.

A spatial collision-aware local planner for quadruped robots that provides a robust foundation for long-range navigation, autonomous exploration, and obstacle avoidance.

A native mobile frontend for LLMs that allows users to run models on-device using llama.cpp or connect to various commercial and open-source APIs.

OpenEnv is a Python framework that defines a Gymnasium‑style API for isolated, containerised agentic environments. It provides a server (FastAPI + Docker), an async client (with sync wrapper), a CLI for scaffolding, building, and deploying to Hugging Face Spaces, and a optional web UI for debugging. The library targets RL and LLM‑agent research, offering example environments (Echo, Coding, Chess, Atari, FinRL) and integrations with TRL, torchforge, SkyRL, and others. Early‑stage but actively governed and open‑source under BSD‑3.

A unified shell environment for AI-driven development that integrates AI coding agents, git diffs, and task trackers into a single multi-pane terminal interface.

A step-by-step AI video production workflow for Codex and WorkBuddy that guides users from topic selection to final rendering of story-based videos.

An open-source voice typing tool for Windows that transcribes speech and uses AI to clean up and insert polished text directly into any application.

An open-source, autonomous semiconductor digital design tool that provides a No-Human-In-Loop flow to convert RTL descriptions into final physical layouts (GDSII).

A hardware dashboard (ESP32 + touchscreen) that displays Claude Code usage live over Bluetooth, with Clawd animations and physical buttons for voice-mode shortcuts.

A local-first control plane that allows you to remotely run, observe, and hand off work across different AI coding agents while keeping your code and credentials on your own machines.

A vision toolkit for DeepSeek Harness that gives text-only models visual capabilities for tasks like UI restoration, long-screenshot OCR, and GUI automation.

A locally-hosted AI companion system integrating multi-modal chat, smart camera surveillance, and RAG-based memory to create a proactive personal assistant.

A Codex Skill that converts business documents and research data into high-density, editable, consulting-style PowerPoint presentations using a structured analysis and blueprinting process.

An open-source toolkit for generating precise astrological and divination charts and converting them into structured prompts for AI interpretation.

An MLIR-based compiler toolchain for homomorphic encryption that allows developers to write encrypted computations and deploy them across multiple HE libraries and schemes.

TaoMate is a research‑grade, real‑time audio‑video digital‑human generation system. The repo provides inference code, multi‑GPU launchers, and a four‑GPU interactive browser demo. It stitches together a 22 B LTX‑2.3 transformer, a Gemma‑3 text encoder, and optional Gemma‑4 dialogue model, requiring high‑memory NVIDIA GPUs and separate model checkpoints from Hugging Face.

A Swift SDK for local, low-latency audio AI on Apple devices, providing transcription, text-to-speech, and speaker diarization offloaded to the Apple Neural Engine.

A high-performance VM manager for Windows and macOS that provides GPU-accelerated isolated desktops for software testing and running computer-use AI agents.

SHARP is a fast monocular view synthesis tool that uses a neural network to generate a metric 3D Gaussian representation from a single image in under a second.

A collection of reference samples for CUDA developers that demonstrate the features of the CUDA Toolkit across C++ and Python.

Claude‑Code‑Proxy is a local command‑line service that translates Claude Code’s Anthropic API calls into requests for Codex, Kimi, Grok, OpenCode Go, or Cursor models, letting you use those providers while keeping Claude Code’s UI. It handles auth, model routing, streaming, and offers a terminal monitor for usage stats. Install via Homebrew or a script, run `claude-code-proxy serve`, and point Claude Code at `http://127.0.0.1:18765`. MIT‑licensed.