An autonomous multi-model AI agent swarm for offensive and defensive security automation, designed to solve CTFs and perform penetration testing by coordinating diverse LLMs via a shared blackboard.

Codex‑Manager is a Rust/Tauri desktop and service app that lets you pool, manage, and route OpenAI‑style API keys (Codex, Gemini, Claude, etc.). It provides UI‑driven account import/export, quota tracking, automated reset reminders, a local OpenAI‑compatible gateway, model routing, and a plugin/skill ecosystem.

A visual fiducial system for robotics that detects unique markers in images to provide precise identification and 3D pose estimation.

A platform for reproducible world model research and evaluation that provides a unified interface for data collection, training, and model-predictive control evaluation.

A production-ready platform for building photorealistic AI avatars with real-time lip-sync, zero-shot voice cloning, and multi-LLM support.

A browser-based and CLI tool for batch-translating subtitles using AI, ensuring timecodes are preserved by separating dialogue from timing data.

A memory system that turns local Markdown files into a queryable knowledge graph for both humans and AI agents, providing structured retrieval via CLI and MCP.

A library for training speculative decoding draft models that integrate directly with vLLM to reduce LLM inference latency without losing output quality.

Xorbits Inference (Xinference) is a versatile library for easily deploying and serving large language, speech, and multimodal models across heterogeneous hardware.

A Python framework for building production-ready conversational AI applications with a built-in UI, reducing development time from weeks to minutes.

A lightweight Python proxy that allows multiple AI agents, including Hermes Agent, OpenClaw, and OpenCode, to run simultaneously on a single WeChat account.

An automatic time series forecasting tool that uses an additive model to handle strong seasonality, holiday effects, and trend shifts.

A graph-based knowledge base that uses LLMs to compile raw documents into an interlinked wiki and knowledge graph for shared human-AI memory.

A computational simulation of the C. elegans roundworm that models its nervous system and 3D body to study emergent biological behaviors.

A design engineering system for AI coding agents that provides design rules and verification tools to ensure AI-generated UIs are professional and production-ready.

A production-ready FastAPI and LangGraph template for AI agent backends that integrates stateful conversations, long-term memory, and observability tools.

A high-performance streaming Markdown renderer for Vue 3 and other frameworks, designed to eliminate flicker and layout shifts in AI chat interfaces.

A local-first visual generation studio and runtime that provides a unified interface for image and video generation across multiple AI providers with advanced iteration tools.

An intelligent agent-powered document search platform that enables users to upload, process, and query documents through a chat interface using RAG.

An open-source terminal coding agent for the Grok API that features desktop automation, remote control via Telegram, and sandboxed execution.

A shared runtime for composing and observing backend services, allowing developers and AI agents to dynamically add and call functions via a unified system surface.

An agent skill that transforms architecture discussions into a single-source-of-truth data file, generating both an interactive isometric map and a synchronized text documentation file.

The official CLI for the MiniMax AI Platform, enabling text, image, video, speech, and vision generation from the terminal or within AI agents.

A package that translates machine learning models into High Level Synthesis (HLS) code for ultra-low-latency inference on FPGAs.

A lossless context management plugin for Hermes Agent that uses a SQLite-backed DAG engine to preserve raw conversation history and provide tools for precise memory recall.

A high-performance 3D Gaussian Splatting and Mesh renderer that uses Chunked Streaming LOD to handle massive 3D datasets.

A secure Telegram client for the OpenCode CLI that allows users to remotely run AI coding tasks, manage sessions, and monitor progress from their phones.

A universal AI gateway that provides a unified local endpoint for multiple AI providers, enabling tools like Claude Code and Codex to share a single server.

A self-hosted AI investment assistant that integrates a multi-agent framework to provide real-time stock monitoring, deep research analysis, and automated alerts for global markets.

Second Brain is a Cloudflare‑Workers‑based personal and team memory service that stores notes, decisions, and other context for AI assistants. It provides semantic recall via vector search, personal + shared layers, prompt‑capsule support, and integrates with many tools (Claude, ChatGPT, CLI, browser extension, Obsidian, Notion, iOS shortcuts). Deployable via a one‑click Cloudflare button, a desktop app, or manual CLI, it runs in the user’s own Cloudflare account, keeping data private. Licensed MIT.

Liza is a multi-agent orchestration system for software delivery that uses behavioral contracts and adversarial review to produce production-ready code with minimal human intervention.

A persistent memory extension for the Pi agent that adds session search, long-term fact retention, and procedural skill saving to prevent the agent from forgetting context across sessions.

A programming paradigm and meta-framework called Cordis that enables spatiotemporal composability, allowing software components to be dynamically added, removed, and reverted without side effects.

A high-accuracy speech-to-text system that allows users to choose between verbatim transcription (including fillers) and clean, intended text, featuring precise word-level timings.

A family of high-precision end-to-end speech recognition models optimized for noisy environments, far-field audio, and extensive Chinese dialect support.

Ix is a system intelligence tool that parses codebases into a persistent graph of symbols and relationships, allowing humans and AI agents to query structure instead of searching text.

A modular framework for building predictable agentic AI pipelines using Pydantic and Instructor to ensure consistent, structured outputs.

A Calibre plugin that translates ebooks into specified languages using various translation engines like ChatGPT, Gemini, and DeepL.

A macOS sandboxing tool that uses sandbox-exec to restrict LLM coding agents to a least-privilege file system access model.

A UI extension for the Pi editor that adds a customizable powerline status bar, a persistent bash mode, and AI-themed loading messages.

A large-scale open-source library for 2D/3D image and point cloud processing, used widely in robotics and 3D perception.

EasyAIoT is an open‑source cloud‑edge‑device platform that unifies AI video analytics, IoT device management, and enterprise integration. It runs on tiny edge boxes (≈1 GB RAM), supports both professional IP cameras and consumer P2P cameras (Tapo, Tuya, Ring, etc.) via a built‑in RTC module, provides native YOLO/SAM inference, federated edge scheduling, and a one‑click installer (PANEL) for on‑site acceptance. Installable on Linux, Windows, macOS, and ARM, it offers web, mobile, and SCADA‑style dashboards for real‑time monitoring and alerting.

A vision routing plugin for DeepSeek Harness that enables agents to interact with image pixels via tool calls and provides a built-in keyless free vision fallback.

A ComfyUI pipeline for creating consistent character sprites, allowing users to manage appearance, poses, clothing, and emotions across multiple images.

A macOS application that centralizes the search and management of local conversation histories from various AI coding agents while tracking quota usage.

A framework for sim-to-real transfer in legged robots that uses data-driven system identification and evolutionary optimization to align simulation dynamics with real-world hardware.

A set of ComfyUI nodes for fast and simple face swapping in images and videos, featuring face restoration and blended face model creation.

An open-source AI agent that autonomously investigates cloud infrastructure incidents, performs root cause analysis, and suggests code fixes to reduce on-call engineer workload.