An open-source data framework for building agentic applications by connecting LLMs to private data sources through ingestion, indexing, and retrieval.

A three-step, CFG-free world model that uses an external world state bank to enable endless, high-quality video generation with mid-flight re-prompting and camera control.

An open-source personal learning agent that uses layered memory and a proactive scheduler to provide personalized educational support and misconception diagnosis.

A state-of-the-art multilingual text-to-speech system that uses a Dual-AR architecture to provide realistic voice cloning and fine-grained emotional control via natural language tags.

A collection of Claude Skills for quantitative trading that enables AI agents to use financial data APIs, backtesting frameworks, and strategy development tools.

A TypeScript framework for building AI agents that share a unified action layer, data, and state with a purpose-built user interface.

OpenBidKit Yibiao is an open‑source Electron‑based desktop app that uses LLMs (OpenAI‑compatible, Ollama, LM Studio, etc.) to parse tender documents, generate full bid proposals (text, images, charts), manage a local knowledge base, and run quality checks such as plagiarism, typo, and logical error detection. It runs entirely on the user’s machine (Windows), stores data in SQLite, and is built with React, TypeScript, Vite, and a .NET 10 helper for Word/Open XML handling. Licensed under AGPL‑3.0.

Gas Town is an open‑source Go‑based workspace manager that lets you run many AI coding agents (Claude, Copilot, Codex, Gemini, etc.) on multiple Git projects while persisting every step in a Git‑backed ledger. A central AI coordinator (the *Mayor*) creates *convoys* of work items (*beads*), hands them to worker agents (*Polecats*), and a set of watchdog services (Witness, Deacon, Dogs) keep the system healthy. Completed work is merged via a Bors‑style queue (*Refinery*), and an optional federation layer (*Wasteland*) lets different installations share tasks. Installable via Homebrew, `go install`, or Docker, it provides a CLI (`gt`) for creating rigs, crews, convoys, and for monitoring progress.

A local-first, self-improving AI testing engine that automates product validation across Android, iOS, and Web by turning natural-language intent into real-device execution.

An open-source toolkit that automatically generates movie recap videos with AI-powered scripts, narration, subtitles, and rendered video from a single prompt.

An open-source quadruped robot project based on the ESP32, featuring 3D-printable parts, an emotive OLED face, and a suite of animation and simulation tools.

A Claude skill that implements the Interpretable Context Methodology (ICM) to design agent architectures using folder structures instead of orchestration code.

An autonomous improvement engine for AI coding agents that uses a loop of modification, mechanical verification, and git-based rollbacks to optimize code and systems.

An Android image editing tool that provides over 500 filters, AI-powered background removal, and batch processing for efficient photo manipulation.

An open-source design editor that natively reads .fig files and provides a programmable toolkit for AI-driven design automation and custom editor development.

An open-source automated video clipping tool that uses ASR and LLMs to extract video segments based on spoken text, speaker identity, or AI-driven content analysis.

A compact multilingual text-to-speech model with zero-shot voice cloning, available in 0.6B and 0.1B parameter versions for high-efficiency speech synthesis.

A deployment recipe for serving the Qwen3.8-Flash-Next vision-language model on a single DGX Spark using vLLM, featuring memory-mapped PLE tables and speculative decoding.

A proof-of-concept AI-powered hedge fund framework for simulating and backtesting AI-driven trading decisions using financial data and LLMs.

An open-source framework for analyzing and improving the AI coding agent work loop by turning project and session evidence into prioritized workflow improvements.

An autonomous AI company framework that orchestrates 14 expert AI agents to ideate, build, and market products 24/7 via a continuous agentic loop.

A data pipeline and transformation suite that uses knowledge graphs to extract structured data from unstructured text, enhancing an LLM's ability to reason over private data.

MemOS 2.0 is a Memory Operating System for LLM‑based AI agents. It offers a unified API to store, retrieve, edit, and delete multi‑modal memories (text, images, tool traces) organized as a graph. The system can run as a hosted cloud service (API‑key access) or be self‑hosted via Docker (Neo4j + Qdrant) or a local SQLite plugin. Ready‑made plugins integrate MemOS with OpenClaw, Hermes, and DeepSeek Harness. Benchmarks show it outperforms existing commercial memory products. Licensed under Apache 2.0.

A local, open-source desktop application that turns photos into 3D meshes using AI models running on the user's GPU.

A tool for removing image backgrounds that can be used as a CLI, Python library, or HTTP server, supporting various AI models and hardware acceleration.

A collection of Agent Skills for solving CTF challenges, providing AI agents with the technical knowledge and tooling required for cybersecurity competitions.

A decentralized geospatial intelligence platform that aggregates 60+ real-time OSINT feeds into a single map interface for global threat monitoring.

An agent skill for AI video generation that transforms rough ideas into directed prompts, managing shot planning, reference binding, and clip continuity.

A deployment recipe for serving the DeepSeek‑V4‑Flash‑Vision‑Exp model (1 M‑token context, image support) on a two‑node DGX Spark cluster using vLLM, DSpark speculative decoding, and NVIDIA‑optimized KV cache. Includes Docker images, environment‑variable configuration, optional NFS weight sharing, and many performance knobs.

herdr‑reviewr is a terminal UI plugin for the *herdr* AI‑assistant that shows live diffs of an agent’s code changes, lets you comment on specific lines, and send those comments back to the agent—all within a split pane or as a standalone app. It supports multiple diff scopes, fuzzy file search, PR read‑only view, theming, and full key‑binding customization.

A self-hosted agent platform for teams that provides isolated Kubernetes sandboxes for AI agents to execute real work via Slack or API.

llm‑d is an open‑source, CNCF‑sandbox project that adds production‑grade routing, KV‑cache tiering, and expert‑parallelism to existing LLM model servers (vLLM, SGLang). Delivered as Helm charts for Kubernetes, it lets organizations serve large language models at scale with lower latency and higher throughput across many accelerator types.

A professional web UI for OpenAI's gpt-image-2.5 API that enables text-to-image generation, mask-based editing, and conversational AI agent image creation.

An open-source AI code review agent that automates PR descriptions, reviews, and improvements across multiple Git providers.

An Obsidian plugin that embeds AI coding agents like Claude Code and Grok into your vault, allowing them to read, write, and search your notes as a working directory.

An open-source AI observability platform for tracing, evaluating, and troubleshooting LLM applications through OpenTelemetry-based instrumentation.

A self-hosted sandbox platform for AI agents that provides permanent, low-cost Linux environments with automatic lifecycle management and E2B SDK compatibility.

Open‑source framework for building and deploying algorithmic crypto‑trading bots; includes CLI, Docker, many exchange connectors, and optional LLM‑driven decision layer (Condor).

A comprehensive collection of GenAI agent tutorials and implementations, ranging from simple conversational bots to complex multi-agent systems using frameworks like LangGraph and LangChain.

A Go-based tool that detects anti-detect browsers and bots by scoring how coherent a browser environment is, identifying contradictions in its reported hardware and software surfaces.

A high-performance in-browser LLM inference engine that uses WebGPU to run language models locally without a server.

A starter kit for Claude Code and Codex that turns AI assistants into a personalized AI Operating System through structured context gathering, reliability auditing, and 3D knowledge visualization.

A lightning-fast search engine that provides full-text, semantic, and hybrid search capabilities with search-as-you-type and typo tolerance for applications.

A professional API gateway that turns a pool of Codex accounts into a unified, observable, and schedulable OpenAI/Anthropic-compatible service.

A Pi extension that enables AI agents to operate desktop applications on macOS, Windows, and Linux by interacting with the GUI when APIs are unavailable.

A self‑hosted MCP server that lets AI assistants log in to Xiaohongshu, publish posts (images or video), search feeds, like/favorite, comment, and fetch user or post details. Available as binaries, Docker image, or source build, and integrates with Claude Code, Cursor, VS Code, Open Code, Cline, etc.

A set of output-style guidelines and plugins for Claude and other LLMs to prevent broken machine-Korean and ensure clear, natural, and unambiguous Korean communication.

An AI-assisted workflow and toolset for converting raster logos into clean, animated SVG logos with a focus on precision fitting and HTML-based motion delivery.