An open-source framework of 100+ text-based games used to benchmark and train LLM agents in competitive and cooperative environments.

tslearn is a Python library that brings scikit‑learn‑style machine‑learning tools to time‑series data, offering preprocessing, classification, clustering, regression, and similarity metrics, all compatible with standard scikit‑learn pipelines.

A multiplayer workspace for teams and AI agents to collaborate on shared documents and evidence using a Git-backed markdown filesystem.

A framework for building and deploying AI agents that scales from simple chatbots to fully autonomous systems, supporting both synchronous and asynchronous workflows.

A conversational data analysis system (ChatBI) that uses LLMs and RAG to convert natural language queries into SQL and visual charts across multiple database types.

An NPC orchestration framework that simulates realistic human computer activity and network traffic for cyber training, security research, and cognitive simulation.

A high-performance morphological analysis library in Rust for Japanese text tokenization, providing bindings for Python, Node.js, and other languages.

An in-context reinforcement learning framework for skill internalization, enabling AI agents to improve their performance on complex tasks like ALFWorld and Search-QA.

A memory layer for AI trading agents that provides outcome-weighted recall of past trades and a tamper-evident SHA-256 audit trail for regulatory compliance.

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 framework for building AI agents on Convex with persistent chat threads, tool calling, and real-time streaming updates.

An AI-powered penetration testing tool that uses autonomous agents to perform blackbox and whitebox security audits directly from the terminal.

Kwipu turns document folders and Obsidian vaults into a property-graph RAG index that can be queried via a terminal, 3D web interface, or MCP client.

GPTLink is a PHP and Vue-based framework for quickly deploying a professional AI chat website with an integrated admin console and monetization features.

A browser extension that uses LLMs to detect and skip sponsored segments in Bilibili videos by analyzing subtitles and audio.

A text-based game generator and sandbox environment used for training and testing reinforcement learning agents in simulated text worlds.

An automated research assistant that uses local LLMs via Ollama to systematically search, scrape, and summarize web information based on prioritized research focus areas.

An open-source framework for developing and evaluating LLM agents in Factorio, using a code synthesis REPL pattern to test long-term planning and resource management.

A collection of copy-paste React components that transform raw AI tool-call JSON into interactive UI elements like charts, forms, and maps.

An open-source multiagent framework that automates the complete scientific research lifecycle, from hypothesis generation and experimentation to writing publication-ready manuscripts.

ainovel‑cli is a Go‑based terminal UI that uses a multi‑agent LLM pipeline (Coordinator, Architect, Writer, Editor, Arbiter) to automatically draft long‑form novels. It offers a fully Vietnamese‑localized interface, supports Vietnamese or Chinese output, works offline with local Ollama models or with cloud APIs, and provides rich slash‑command controls for planning, editing, style simulation, import/export, and real‑time steering. The project includes checkpoint recovery, rolling two‑tier planning, and 4‑level context compression to handle very long stories.

A self-hosted AI roleplay chat platform that allows users to run their own server for multi-device access and centralized data storage.

An open-source live chat and conversational app development platform that integrates AI chatbots with human agents across multiple channels.

An open-source template for deploying a personal AI agent with persistent memory and integrations for Slack, GitHub, and Linear.

A command-line interface that allows developers to interact with Amazon Q Developer directly from their terminal.

A document indexing and retrieval tool for analysts that allows querying private research collections with citations, supporting both cloud and fully local AI models.

A local-first desktop companion powered by MiniCPM that provides a chat interface and visual reactions to the activity of coding agents.

An AI-powered conversational platform for real estate property search and market analytics, featuring natural language search and AI-driven valuation forecasts.

An MCP server that gives AI assistants secure access to the Kite Connect trading API for market data retrieval, portfolio management, and trade execution.

An enterprise AI Agent workbench for audit delivery that automates evidence retrieval, control testing, and remediation within a traceable and evaluatable workflow.

A state-driven AI persona engine for Telegram that simulates human behavior through sleep schedules, relationship stages, and long-term memory to avoid typical chatbot patterns.

A governed, on-prem GraphRAG and agent framework that combines hierarchical tree-search with knowledge graph reasoning for verifiable, multi-hop AI retrieval.

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

A reference solution for building enterprise RAG pipelines using NVIDIA NIM microservices, supporting multimodal data extraction and agentic multi-hop retrieval.

An intelligent document automation system that uses YOLO, OCR, and LLMs to extract and analyze financial data from bank statements with a focus on local LLM execution and PII privacy.

A lightweight Python toolkit for Retrieval-Augmented Generation (RAG) that supports DuckDB or PostgreSQL and integrates with various LLM providers.

A federated AI search and RAG platform that queries data sources live, eliminating the need for vector databases and ETL pipelines while keeping data in place.

A generative UI toolkit for React that enables AI agents to dynamically render and update UI components based on LLM tool calls.

A tiny, fast JavaScript library for rule‑based natural‑language processing (tokenisation, POS tagging, simple transformations) that runs in browsers or Node. Ideal for lightweight text manipulation, extraction, and templating when you don’t need heavyweight AI models.

A Rust framework for building composable AI agent runtimes that integrate models, tools, and memory into a single orchestrated execution environment.

An open-source AI agent studio for building and runing agentic workflows with a visual builder and GitHub integration.

Obsidian Text Extractor is a community plugin that adds OCR‑based text extraction for images, PDFs and Office files inside an Obsidian vault. It uses Tesseract.js locally, caches results as JSON, and exposes a simple API for other plugins (e.g., Omnisearch). Limitations include unreliable PDF extraction, no mobile support, and the project is currently unmaintained.

MCP Server Tauri is a Node‑based Model Context Protocol server that connects AI assistants (Claude, Cursor, Windsurf, etc.) to a running Tauri v2 app. It streams screenshots, DOM snapshots, console logs, and Tauri IPC traffic, and exposes 21 commands for UI automation, IPC inspection, log streaming, and mobile device listing. By installing a small Rust bridge plugin into the Tauri binary, the server gives the assistant rich, real‑time context, enabling AI‑driven debugging, code generation, and cross‑platform UI control without external drivers.

An open-source, self-hosted platform for tracking and optimizing brand visibility and citations across AI answer engines like ChatGPT, Perplexity, and Gemini.

A local-first, private bookmark manager for technical resources that uses AI to summarize, organize, and provide semantic search over saved content.

An open-source automation platform that uses AI agents to triage issues, draft specs, and manage pull requests for OSS projects.

An MCP server that enables AI models to integrate with Xiaohongshu, allowing them to search for notes, read content, and post comments via direct API requests.

A solution accelerator providing reusable architecture and code to build custom enterprise copilots using Azure OpenAI and Azure AI Search for RAG-based data interaction.