An open-source recreation and extension of Anthropic's Claude Code, providing a CLI agent with multi-model support and advanced orchestration tools.

An open-source generative BI engine that provides a governed semantic layer for AI agents to turn business questions into correct SQL and deployable dashboards.

A deterministic codebase scanner that identifies React-specific issues in state, performance, and security, specifically designed to help AI coding agents write better code.

A tool that analyzes AI agent session transcripts to propose evidence-backed updates to agent memory files and project skills, automating the feedback loop for agent instructions.

An open-source AI memory platform that provides agents with persistent long-term memory using a self-hosted knowledge graph to store text, code, and session context.

A portable personal assistant platform built on Cloudflare Workers and MCP that allows AI agents to maintain their own memory, keys, and code across different hosts.

A privacy-focused, self-hosted AI answering engine that combines private web search via SearxNG with local or cloud LLMs to provide cited answers.

GEPA is a framework for optimizing textual parameters like prompts and agent architectures using LLM-based reflection and Pareto-efficient evolutionary search.

Buzz is an offline desktop app that transcribes and translates audio/video (or YouTube links) using OpenAI’s Whisper. It supports live microphone captioning, speaker identification, speech‑separation, multiple hardware‑accelerated back‑ends (CUDA, Apple‑silicon, Vulkan), export to subtitle formats, a searchable viewer, folder‑watch automation, CLI, and a plugin system. Install via DMG (macOS), installer (Windows), Flatpak/Snap/AppImage (Linux), or pip (Python). MIT‑licensed.

A resumable long-running task workflow and skill platform for AI-assisted coding that provides structured methodologies and multi-agent coordination for complex software requirements.

A high-performance vector database and similarity search engine written in Rust, designed for storing and retrieving embeddings with advanced filtering and hybrid search capabilities.

An unofficial Python API and CLI for Google's NotebookLM (Gemini Notebook), enabling programmatic source ingestion, cited Q&A, and bulk generation of media artifacts.

A tool that enables DLSS 5 neural rendering in games without native DLSS support by synthesizing a DLSS contract using ReShade depth and motion vectors.

VGGT-Omega is a computer vision model that predicts camera poses and depth from images to enable 3D scene reconstruction.

A cross-session memory kernel for AI coding agents that reduces API costs and latency by optimizing prompt-cache hit rates and reusing project knowledge.

An open-source AI engineering platform that enables teams to debug, evaluate, monitor, and optimize LLMs, AI agents, and ML models for production.

A structured investment research framework for Claude Code and Codex that systematizes value investing methodologies using multi-agent adversarial analysis and precise financial tools.

VDN‑Minimax‑H3 (VDN‑H3) is a hybrid‑attention video diffusion model built on MiniMax H3. It adds a lightweight linear‑attention branch and LoRA adapters, enabling near‑real‑time 768p video generation (e.g., 14‑s clip in ~11 s on a single B200 GPU). The repository provides full training scripts (four staged recipe) and optimized inference code using FP8 and FlashAttention‑4, with detailed setup instructions and performance tables.

An AI-powered job search agent that automates job collection, AI scoring, and personalized outreach across multiple recruitment platforms while requiring manual confirmation for all applications.

A real-time object detection and target locking system for Delta Force using YOLOv14 to identify game characters while filtering out environmental false positives.

An OpenAI-compatible API proxy that reverse-engineers ChatGPT's web capabilities to provide image generation and editing services with built-in account pool management.

An open-source infrastructure that provides secure, isolated cloud sandboxes for running AI-generated code and interacting with virtual desktops.

A documented workflow and set of tools (plugins, prompts, lint rules, sub‑agent orchestration, memory handling) that let developers use Claude Code / Codex as a disciplined coding teammate. Includes a “Superpowers” discipline, parallel sub‑agents, quality‑gate ESLint config, and a full onboarding Playbook.

allow-scripts allow-same-origin

An MCP server that turns AI assistants into security analysts by integrating 28 security tools and 24 APIs to automate CVE triage and risk scoring.

A universal CLI client for the Model Context Protocol (MCP) that enables AI agents and developers to interact with MCP servers via standard shell commands.

A bridge that connects AI agents running on a local machine to instant messaging platforms like Telegram, Slack, and Discord for remote control.

CodeBurn is a free, open‑source Node.js utility that locally reads session logs from dozens of AI coding tools (Claude, Cursor, Codex, Gemini, etc.) and shows you exactly how many tokens and dollars each model, project, and task has consumed. It provides a terminal UI, a web dashboard, and a menubar/tray app, can detect waste patterns (re‑reads, low read‑to‑edit ratios, unused agents, etc.), suggest and apply fixes, enforce budget caps, compare model efficiency, and even correlate spend with git commits. All processing stays on your machine; no API keys or data are sent elsewhere.

An AI relationship consultant that analyzes chat logs and relationship dynamics using a multidisciplinary knowledge base to provide emotional support and actionable dating advice.

A desktop workbench for AI coding that provides a visual interface for managing multi-agent teams, dynamic workflows, and model integrations.

A load balancer and API proxy for ChatGPT accounts that pools multiple accounts to manage rate limits and track usage via a dashboard.

An end-to-end audio understanding model that jointly performs speech transcription and speaker diarization for long-form multi-speaker audio in a single pass.

RF‑DETR is a real‑time transformer‑based vision model suite (detection, segmentation, keypoint) built on a DINOv2 backbone. It ships as the `rfdetr` Python package with several size variants (Nano‑2XL), provides Apache‑2.0 (core) and PML 1.0 (XL/2XL) licenses, and includes benchmark tables showing state‑of‑the‑art accuracy‑latency trade‑offs on COCO and RF100‑VL. Installation is via `pip install rfdetr`; usage is a single‑line `model.predict(...)` followed by optional visualisation with the `supervision` library. The project also offers a NAS pipeline on the Roboflow platform for custom architecture search.

An AI-powered coding agent featuring a dual-speed self-evolution system that improves its performance through real-time prompt injection and long-term fine-tuning.

An open-source AI-powered no-code platform for building business systems that allows AI agents and humans to collaborate on a production-proven infrastructure.

A multi-agent orchestration framework for Claude Code that enables natural-language task distribution across specialized agents and multiple AI providers.

svg‑diagram is a zero‑dependency Node skill that defines a strict visual style for SVG diagrams generated by AI coding agents and provides a command‑line linter (`svg‑lint`) to verify that a finished SVG follows the style.

A Kubernetes-native virtualization middleware that enables sharing and isolating GPU and other AI accelerator resources across multiple workloads to increase hardware utilization.

A universal mobile development tool that provides a unified dashboard and CLI to control iOS Simulators, Android Emulators, and physical devices.

ACE‑Step 1.5 is an open‑source music‑generation foundation model that combines a language‑model planner with a Diffusion‑Transformer audio decoder. It can create full songs (10 s‑10 min) in under 10 seconds on a RTX 3090, runs with <4 GB VRAM for base models, and supports LoRA fine‑tuning from a handful of tracks. The repo provides Gradio and REST interfaces, launch scripts for all major OSes, multiple model sizes (including a 4 B XL version), and extensive control over lyrics, style, tempo, and instrumentation.

A provider-agnostic TypeScript toolkit for building AI-powered applications and agents with a unified API for multiple LLM providers and integrated UI hooks.

A tool for injecting custom, revocable instructions into Codex AI programming tools to customize behavior in new conversations without modifying the software.

A visual context management tool that uses a graph-based interface to let users explicitly control and prune what an LLM sees, reducing hallucinations and wasted tokens.

An MCP server that connects Zotero research libraries to AI assistants, enabling semantic search, metadata retrieval, and PDF annotation analysis.

OpenDM is a Vision-Language-Action (VLA) model framework for open-world robot control, providing tools for training, fine-tuning, and deploying models across various robot embodiments.

A review-first terminal diff viewer designed for agent-authored changesets, featuring interactive UI, inline AI annotations, and multi-file navigation.

A vision-language foundation model for autonomous driving that integrates 3D perception, visual question answering, and motion planning into a unified framework.

An MCP server that enables AI assistants to read LinkedIn profiles, search for jobs, and manage messages using the user's own logged-in browser session.