An open-source red teaming framework for LLM systems that simulates adversarial attacks to uncover vulnerabilities and provides guardrails for production security.

An open-source framework that enables coding agents to generate production-ready Lottie animations from text prompts and SVG assets.

A .so loader for static Linux binaries that allows musl-linked executables to load glibc-linked GPU drivers and shared objects without needing a second libc.

An open-source toolkit for adding programmable guardrails to LLM-based conversational applications to ensure safety, security, and controllable dialogue flows.

An MCP server that integrates Monarch Money with AI assistants, allowing users to manage accounts, transactions, and budgets using natural language.

A model-agnostic agent-skills platform providing a thousand of specialized capabilities (plugins and skills) to extend the functionality of AI agents.

BAM provides high-fidelity servo actuator models and an identification pipeline to improve the accuracy of robotic simulations, specifically for better sim-to-real transfer in Reinforcement Learning.

BabelDOC is an open‑source Python tool that translates PDF scientific papers using LLMs (OpenAI‑compatible models) and outputs bilingual PDFs. It offers a CLI, a Python API, extensive PDF‑handling options, glossary support, offline asset packaging, and can be run locally or via a hosted beta service.

Irodori‑TTS is a flow‑matching Japanese text‑to‑speech model that supports zero‑shot voice cloning, caption‑based style control, LoRA fine‑tuning, speaker‑inversion embeddings, a distilled “MeanFlow” fast‑generation variant, and quantized checkpoints. It ships CLI tools, Gradio UIs, and training scripts for full‑model or adapter training.

A verification layer for AI coding agents that runs an internal SDK in web apps to prove code changes work by monitoring network, state, and console events.

A high-efficiency pretraining framework that allows users to pretrain 1B parameter foundation models from scratch with significantly reduced compute and data requirements.

An integrated automation system for Xianyu sellers to manage multiple accounts, automate AI-powered customer responses, and handle automatic digital product delivery.

A high-performance inference engine that allows developers to deploy AI models locally in their apps to eliminate latency, costs, and privacy concerns.

A unified post-training and real-time inference framework designed to accelerate video generation through sparse distillation and attention optimizations.

A bridge that connects AI agents to Cheat Engine via the Model Context Protocol, enabling natural language interaction with program memory for reverse engineering and modding.

A library for accelerating AI models through quantization, pruning, and distillation, enabling faster inference and reduced memory usage across various deployment frameworks.

An MCP server that enables AI assistants to interact with Obsidian vaults by reading, searching, and editing notes via the Local REST API plugin.

OpenRSI is an open initiative and framework for recursive self-improvement, providing the OpenMLE stack and Frontis-MA1 model to enable AI to autonomously improve its own machine learning engineering capabilities.

An AI-native asset reconnaissance and vulnerability monitoring platform that automates asset discovery and threat intelligence gathering using AI agents.

A Qemu-based emulator that boots iOS and macOS to a barebones root shell for kernel debugging and low-level Darwin system analysis.

A curated ecosystem of plugins, tools, and infrastructure for DeepSeek Harness (DSH) to extend agent orchestration, memory, and context management.

An open-source proofreading software that detects grammatical and stylistic errors across 20+ languages, surpassing the capabilities of basic spell checkers.

A high-accuracy, low-latency speech foundation model that provides multilingual speech recognition, emotion detection, and audio event identification.

A desktop AI agent that automates office workflows by interacting with local files, terminal commands, and browser workflows through a dedicated runtime engine.

An open-source, self-hosted algorithmic trading platform that provides a unified API for 36 brokers and tools for Python-based, no-code, and AI-assisted trading.

A multimodal data layer and visual debugger for physical AI, allowing developers to log, query, and visualize multi-rate sensor data in real-time.

An autonomous AI framework that chains reconnaissance, exploitation, and automated code remediation into a single pipeline to find and fix security vulnerabilities.

A library for guaranteeing structured outputs from LLMs by constraining generation to match specific Python types or Pydantic models.

An open-source AI email assistant that organizes inboxes, pre-drafts replies in the user's tone, and integrates with Slack and Telegram for on-the-go management.

An open-source browser API that simplifies building AI agents and web automation tools by managing browser sessions, proxies, and anti-detection.

An open-source diffusion model engine that enables high-performance inference and training of image, video, and audio generative models on consumer-grade GPUs.

An open-source, self-hosted omnichannel customer support desk that integrates live chat and email with AI-powered automation and a knowledge base.

An LLM inference framework for CPU servers that optimizes long-horizon inference by trading storage for computation to outperform GPUs in long-context scenarios.

A secure environment variable management system that provides AI agents with configuration schemas instead of secrets to prevent leaks.

An open-source research platform for developing Vision-Language-Action (VLA) models, providing a modular codebase for integrating different backbones, action heads, and training recipes for generalist robots.

OpenSquilla is a token‑efficient, micro‑kernel AI‑agent framework that routes each turn to the cheapest capable LLM. It bundles a local model router, persistent memory, sandboxed tools, web search, and on‑device embeddings, and runs the same turn loop across a desktop GUI, CLI, and chat‑channel integrations. Install via a pre‑built desktop installer, a one‑line `uv` wheel install, or from source. Supports 20+ LLM providers, many chat channels, and optional extras like Matrix or PDF generation. Licensed Apache 2.0, with privacy‑focused telemetry that can be disabled.

A fast BPE tokenizer for OpenAI models that converts text into tokens for model processing with high efficiency and lossless compression.

pi‑autoresearch is a pi‑coding‑agent extension that lets the AI run autonomous optimisation loops: it creates a session, repeatedly executes a user‑defined benchmark command, logs the metric, auto‑commits good changes, and provides a live dashboard. After the loop, it can split successful runs into reviewable git branches. The tool is domain‑agnostic, configurable, and supports optional hooks and confidence scoring.

Hatchet is an open‑source orchestration engine that lets you run reliable background tasks, AI‑agent pipelines and durable workflows. It stores all state in PostgreSQL, provides retries, scheduling, DAGs, rate‑limiting, priority queues and a real‑time UI, and offers SDKs for Python, TypeScript, Go and Ruby. You can use it as a managed cloud service or self‑host it via Docker.

A local-first AI agent desktop client that integrates LLM reasoning with local system tools for file manipulation, command execution, and remote browser-based control.

COLMAP is an open‑source Structure‑from‑Motion and Multi‑View Stereo pipeline that automatically turns collections of photos into 3‑D models. It offers a GUI, command‑line tools, Python bindings, GPU‑accelerated feature extraction, and cross‑platform binaries, making it a go‑to foundation for research and applications in computer vision, robotics, AR/VR, and any workflow that needs camera poses and dense scene geometry.

An AI-powered design skill that transforms architectural and cultural photos into art-directed editorial posters with integrated Chinese typography and spatial awareness.

A comprehensive learning resource and kernel library for modern CUDA programming with PyTorch, featuring over 200 kernels ranging from basic operations to high-performance FlashAttention and HGEMM implementations.

An MCP server that enables AI agents to integrate with 21st.dev to search for and generate UI components, themes, and templates.

A model that predicts spatially consistent 3D geometry, depth maps, and camera poses from single or multiple images using a unified depth-ray representation.

An intelligent data questioning system based on LLMs and RAG that enables conversational data analysis (ChatBI) by converting natural language into SQL queries.

A Python framework for building reliable AI applications by enforcing input/output risk validation and ensuring LLMs generate structured data.

A portable, single-file memory layer for AI agents that provides persistent long-term memory and instant retrieval without requiring a database.