IronCurtain is a research‑grade runtime that secures autonomous LLM agents by compiling a plain‑English "constitution" into deterministic allow/deny rules, validating them, and enforcing the rules on every tool call via a policy engine. It supports a V8 sandbox or Docker‑isolated agents, provides an interactive terminal multiplexer and optional web UI for escalation handling, and includes persona/workflow features for multi‑agent pipelines.

A local analytics dashboard that unifies conversation history, token costs, and usage patterns from 17 different AI coding editors into one place.

A PyTorch implementation of Denoising Diffusion Probabilistic Models (DDPM) for generating high-quality images and 1D sequences.

Fara1.5 is a family of native computer-use agent models that can visually perceive and interact with web browsers using mouse and keyboard inputs to automate complex tasks.

A JAX-native library providing high-performance implementations of Monte Carlo tree search algorithms like AlphaZero and MuZero for reinforcement learning.

A comprehensive deep learning toolkit for clinical predictive modeling that provides a modular pipeline for healthcare AI applications.

A comprehensive machine learning and math framework for Go, providing a PyTorch-like experience with support for XLA, ONNX, and pure Go backends.

Falcon‑Perception is an open‑source, PyTorch/MLX inference library for the Falcon multimodal transformer that can answer natural‑language queries with object detection, instance segmentation, or OCR. It provides highly‑optimized paged and batch engines, a FastAPI server, a Streamlit UI, Docker/vLLM deployment for OCR, and Colab notebooks. The 270 M‑parameter Falcon‑OCR 1.5 model delivers end‑to‑end OCR quality comparable to much larger VLMs while staying three‑times smaller.

An MCP server that enables AI assistants to read, search, organize, and send emails using IMAP and SMTP.

An OpenCode plugin that automates the creation and Git worktrees, automatically spawning dedicated terminals for AI agents to work in isolation.

A library for type annotations and runtime type-checking of array shapes and data types across JAX, PyTorch, NumPy, MLX, and TensorFlow.

A WeCom channel plugin for the OpenClaw AI‑agent platform. It adds Bot (WebSocket or JSON webhook) and Agent (encrypted XML webhook) connectivity, supports rich media, proactive and streaming replies, fine‑grained access control, multi‑account setups, and exposes dozens of WeCom business APIs (messaging, email, docs, spreadsheets, calendar, meetings, file storage, contacts) via a built‑in `wecom‑cli` tool.

A suite of tools for managing and monitoring NVIDIA data-center GPUs in cluster environments, providing health monitoring, diagnostics, and governance policies.

A speculative decoding implementation for Apple Silicon that uses block-diffusion draft models to accelerate LLM inference without losing output quality.

A Python framework and terminal AI assistant that provides a complete agent harness with a unique live run forking capability to test parallel execution paths.

A durable-execution engine for AI agents and workflows that records side effects to a journal, allowing programs to resume exactly where they left off after a crash.

A self-hosted server software for Anki Vector robots that enables free voice command functionality for Vector 1.0 and 2.0 models.

OpenExo is a control system for wearable robots that uses dual microcontrollers to manage exoskeleton hardware.

A comprehensive collection of 152 browser-based tools, including on-device AI utilities for transcription and image processing, that process data locally for privacy.

A C++ and Python library for autonomous agricultural vehicles that computes efficient, kinematically feasible coverage paths for non-convex fields with obstacles.

A collection of 23 plugins for hermes-agent that add autonomy, observability, safety guards, and adaptive memory to autonomous AI agents.

A token-compression framework for AI coding agents that reduces Japanese response redundancy to lower API costs and save context space.

A VS Code extension that provides local LLM-assisted text completion, chat, and agentic coding by integrating with llama.cpp.

A RAG-based system that converts Bilibili video collections into a conversational knowledge base by transcribing audio to text and indexing it for semantic search.

A high-fidelity vulnerability scanner that combines deterministic native scanning with autonomous AI agents to audit codebases and web applications.

An MCP server that connects Claude and ChatGPT to the Intervals.icu API, enabling AI assistants to retrieve and manage athletic training, wellness, and event data.

An embeddable repository system that combines files, a SQL database, and version control into one ACID-compliant system for real-time collaboration and data history.

ONNX Simplifier (onnxsim) is a tool that automatically reduces ONNX model size and complexity by constant‑folding, shape inference, and graph optimizations, with optional correctness checks and export to MLIR, Core ML, TFLite, and more.

A reinforcement learning extension for Isaac Lab that enables humanoid robots, such as the Unitree G1, to learn complex motions via DeepMimic and Adversarial Motion Priors.

A collection of open-source marketing agents and skills that enable AI assistants to perform SEO audits, AI visibility checks, and competitive research using live public data via MCP.

A TypeScript SDK for generating and editing UI screens from text prompts, providing HTML and screenshots for rapid prototyping and AI agent integration.

A Japanese-specialized Document AI engine that provides high-accuracy OCR, layout analysis, and table structure recognition for images of documents.

A set of components and bundles for PHP applications to integrate AI capabilities, providing unified interfaces for AI platforms, agents, and AI-specific data storage.

NVIDIA Aerial™ CUDA‑Accelerated RAN is an open‑source SDK that implements 5G PHY and MAC processing on NVIDIA GPUs. It includes CUDA kernels for channel coding, modulation, MIMO, and scheduling, plus a Python API for AI/ML research, all packaged in ready‑to‑run Docker containers.

A local-first marketing operations dashboard that consolidates CRM, outreach, and AI agent activity into a single self-hosted interface for human-in-the-loop management.

The official OpenAI .NET API library that provides convenient, type-safe access to the OpenAI REST API for .NET applications.

A local AI quota aggregator and proxy that lets you use AI subscriptions from various providers (like Claude Pro or Cursor) across any AI tool or IDE.

A Claude Code skill that transforms an LLM into a CTI and OSINT analyst, providing over 120 commands for structured intelligence collection and professional report generation.

A drop-in prompt compression library that reduces LLM input-token costs by 10-40% using loss-tolerance routing to protect critical code and tool calls while compressing prose.

AI DevKit is a local npm‑based control plane that unifies configuration, monitoring, cross‑agent messaging, searchable SQLite memory, and composable engineering “skills” (requirements, design, testing, review, etc.) for many AI coding assistants such as Claude Code, Gemini CLI, Codex CLI, Cursor, and GitHub Copilot. It lets teams manage multiple agents from a single console, keep project conventions in a searchable store, and enforce a senior‑engineer workflow without modifying the underlying LLMs.

An AI-powered divination application that uses ChatGPT to provide tarot readings, Bazi analysis, and other traditional fortune-telling services.

An MCP server that enables structured, spec-driven development for AI agents by enforcing a sequential workflow of requirements, design, and tasks with a real-time monitoring dashboard.

A Swift-native agent runtime for building type-safe AI agents with support for on-device Apple Foundation Models and composable workflows.

A privacy-first desktop application that captures copied content and uses AI to automatically organize it into a structured, interconnected knowledge base and knowledge graph.

An AI agent that uses LLMs and image recognition to automate daily tasks, navigation, and activities in the game Infinity Nikki via screen capture and input simulation.

An anti-detect browser CLI that provides AI agents with C++-level fingerprint spoofing and persistent identities to bypass bot detection during web automation.

A long-form spoken dialogue generation model that transforms scripts into expressive multi-party conversations with support for up to 60 minutes of continuous audio.

A local code search engine that uses vector embeddings and ripgrep to enable semantic and keyword-based search across a codebase.