An open-source e-commerce system based on Laravel 13 that integrates AI models and Model Context Protocol (MCP) for intelligent automation.

KISS Sorcar is an open‑source, local‑first AI‑agent framework that runs a daemon (`kiss‑web`) and provides VS Code, web/mobile, and Python interfaces for issuing natural‑language tasks. It supports any LLM you configure (OpenAI, Anthropic, Gemini, local endpoints, etc.), mixes multiple models in one workflow, and includes 43 built‑in third‑party agents for messaging, email, smart‑home, and productivity services. Custom Python “extension agents” let you define prompts, tools, budgets, and safety hooks per task. All prompts stay on your machine; the system handles git worktree isolation, voice wake‑word, scheduled automations, and tool calling, making it a privacy‑focused, extensible personal AI assistant.

A privacy-first, open-source Android expense tracker that uses on-device AI to automatically parse bank SMS notifications into a structured financial timeline.

FableCodex is a Codex plugin that enforces an evidence‑based, multi‑step workflow (goal ledgers, findings gates, verification) for code‑generation tasks, helping users avoid missed steps in larger or safety‑critical changes without altering the underlying model.

An explainable AI text risk analyzer that provides weighted signals and risk estimates instead of binary verdicts to assist in human-led triage.

An agentic AI framework based on Apache Flink that allows developers to build AI agents capable of real-time stream processing.

An end-to-end agent benchmark that tests AI agents' ability to perform complex, real-world tasks in live environments using tools like browsers and bash terminals.

An open-source engine for Claude Code that turns goals into verified code via graded PRDs, dependency-ordered task graphs, and evidence-based execution.

A library for fine-tuning LLMs, vision, audio, and OCR models natively on Apple Silicon using an Unsloth-compatible API for easy prototyping and scaling to cloud GPUs.

A Python WebRTC driver for Unitree Go2, G1, and R1 robots that enables high-level control, video/audio streaming, and sensor data access without firmware modification.

Kalshi Trading Bot CLI is a Bun‑based command‑line tool that uses Octagon AI probability estimates to find edges on Kalshi prediction markets, size trades with half‑Kelly, enforce a five‑gate risk engine, and support basket building, backtesting, paper‑trading, and a learning loop (calibration, reflection, hypotheses). Install via `bunx kalshi-trading-bot-cli@latest`, run the setup wizard for API keys, then use commands like `search`, `analyze`, `buy`, `basket build`, and `portfolio` to trade or simulate strategies.

A comprehensive machine learning toolkit for Rust, similar to scikit-learn, providing classical ML algorithms and preprocessing tools.

A Model Context Protocol (MCP) server that exposes local filesystem and command execution capabilities to AI agents with built-in sandboxing and user approval workflows.

A command-line OCR tool for macOS that extracts text, QR codes, and barcodes from the screen, images, or PDFs using Apple's Vision framework.

A modular, voice-activated AI desktop assistant that combines speech recognition, LLM reasoning, image generation, and system automation to control your computer hands-free.

An RL-based locomotion control system for the TienKung humanoid robot that enables natural walking and running behaviors through Adversarial Motion Priors (AMP).

A hardware-accelerated motion planning library that uses CPU SIMD instructions to perform collision checking and forward kinematics in microseconds.

An open-source LLM framework for extracting structured data and insights from documents with precise source references and automatic justifications.

A Python framework for building autonomous and traditional AI agents, featuring secure workspace execution, custom tool integration, and a unified OCR pipeline.

A library for building multimodal AI applications and agentic teams, featuring a unified provider interface, multi-agent debate frameworks, and a knowledge graph with sleep/dream lifecycles.

MatrixOne is an AI-native HTAP database that combines transactional, analytical, and vector search capabilities with Git-style version control for data management.

A lightweight knowledge graph construction and visualization tool based on Neo4j and Spring Boot, featuring visual editing, ER modeling, and external data source integration.

A PyTorch domain library for fine-tuning and using pretrained Geospatial Foundation Models for tasks like image segmentation and classification.

PoinTr is a transformer-based model for point cloud completion that reconstructs full 3D objects from partial point clouds using a geometry-aware encoder-decoder architecture.

User posted a long README of llama.rn covering many features. Assistant offers to help with specific questions and provides a concise TL;DR of key usage points.

A local-first shared memory system for AI agents and on-device models that stores searchable memory in a single file on disk without requiring a hosted vector DB.

A Python text-to-speech library designed for low-latency audio generation from strings, generators, and LLM token streams, supporting a wide variety of local and cloud TTS engines.

A browser-hosted mobile simulation platform for GUI agent research that provides programmable state and deterministic judges for scalable RL training and verifiable evaluation.

Anny is an open‑source, PyTorch‑based differentiable human‑body mesh model covering all ages. It offers multiple rigs (compact 104‑bone default, full MakeHuman), several mesh topologies (including SMPL‑X and SOMA), and fine‑grained shape, local‑change, and facial‑action parameters. Install via pip, run a quick Python example to output a .ply mesh, or launch an interactive Gradio demo. The library is Apache‑2.0 licensed, builds on MakeHuman assets, and is intended for research/production tasks such as pose estimation, animation, and cross‑age body modeling.

TorchNPU is a PyTorch adapter plugin that enables the PyTorch framework to run on Huawei Ascend AI processors, providing optimized compute and distributed training capabilities.

A suite of Python packages for Neuro AI, providing tools for curated dataset fetching, high-performance data loading, and scalable model training and benchmarking.

A conversational application for the Reachy Mini robot that integrates real-time voice, vision, and choreographed motion via LLM-powered tool calling.

A collection of advanced scenario-driven demos showing how to integrate OpenAI ChatKit with FastAPI and React to create AI agents that synchronize with real-time UI state and interactive widgets.

A powerful Go framework for building production-ready AI agents with integrated memory management, multi-LLM support, and enterprise-grade observability.

Resource2Skill converts human-created tutorials and multimodal resources into executable skills that AI agents can use to operate professional software like Blender, Excel, and PowerPoint.

A local-first AI filmmaking workspace that integrates coding agents with a visual canvas and a unified API for generating images, video, and voice.

A local LLM integration and set of fine-tuned small models that enable private, offline voice and chat control for Home Assistant smart homes.

An open-source video translation tool that transcribes, translates, and dubs videos into 33 languages with native-sounding AI voices.

A comprehensive tabular analytics and learning toolbox that integrates over 45 machine learning methods and 300 datasets to benchmark and optimize performance on tabular data.

An open-source ranking service that provides real-time personalization and reranking for search and recommendation systems using machine learning and LLMs.

A PyTorch library for neural network quantization that supports both post-training quantization and quantization-aware training to improve model efficiency.

A plugin for Claude Code and Codex CLI that provides AI agents with a curated, LLM-optimized knowledge base across 18 core AWS services for automated cloud engineering.

MOTIP is a multiple object tracking framework that treats tracking as an in-context ID prediction problem to directly decode ID labels for current detections.

An MCP server that gives Claude private, local-first journaling and semantic search capabilities to maintain persistent memory across conversations.

A Python CLI framework that stores threat‑hunting investigations as markdown using the LOCK pattern, makes them searchable, and optionally lets LLM agents generate research, run queries, and automate parts of the hunt.

A curated collection of open datasets containing data from over 602 million cells designed to accelerate the creation of virtual cell models.

A Python-based simulation environment for marine vehicles that provides models for AUVs, USVs, and ships to test guidance, navigation, and control systems.

A deliberately vulnerable CTF-style training platform for learning the OWASP Top 10 for LLM Applications through scripted labs and real local model exploitation.