A proxy server that provides unified OpenAI, Gemini, and Claude compatible API interfaces for various AI providers, allowing CLI tools to access models using existing subscriptions via OAuth.

A high-performance CLI proxy that compresses bash output for AI agents, reducing input tokens by up to 90% through smart filtering and grouping.

A GPU-accelerated terminal and SSH workspace designed to integrate and manage AI CLI sessions, such as Claude Code and Codex, in a single native environment.

A software factory framework that turns AI coding agents into a virtual engineering team with specialized roles for product planning, architectural review, QA, and security audits.

An open-source application for managing physical iOS devices to run scheduled automation workflows, featuring a built-in TikTok plugin and remote control capabilities.

A set of rules and filters for AI coding agents to prevent the generation of generic "AI slop" in UI, copy, and code comments.

A CLI for git worktree management designed to let developers run multiple AI agents in parallel by simplifying the creation and switch between separate working directories.

MiniMind is a complete, open-source codebase for training a very small (~64M parameter) large language model entirely from scratch on a tiny budget (about 3 RMB and 2 hours). It covers the full modern LLM lifecycle—pretraining, SFT, LoRA, DPO, RLAIF (PPO/GRPO/CISPO), tool use, and agentic RL—and includes experimental extensions for MoE, vision, and diffusion models.

An open-source workspace that integrates multiple AI coding agents into a single board, allowing users to assign issues to agents as if they were human teammates.

A lightweight, Rust-based database manager supporting 90+ databases with a built-in AI SQL assistant and MCP server for AI agent connectivity.

A cybersecurity skills router that provides AI agents with structured methodologies and tool routing for reverse engineering, penetration testing, and CTF challenges.

A plain C/C++ implementation for high-performance LLM and VLM inference across a wide range of hardware with minimal setup.

A personal cloud operating system for developers that provides isolated workspaces for AI agents and a catalog of 944 self-hosted apps, all accessible via a secure browser-based desktop.

A smart AI router and proxy that saves 20-40% of tokens and provides automatic fallback between subscription, cheap, and free AI models for coding tools.

An open-source, local-first AI research workbench that enables reproducible science by combining AI agents, Python/R execution, and traceable provenance for all research artifacts.

A self-hosted, OpenAI-compatible LLM router that optimizes costs and reliability using automatic model selection and a managed fallback safety net.

A high-performance code intelligence engine that builds a structural knowledge graph of codebases to provide AI agents with efficient, low-token access to architectural insights.

A self-hosted, extensible AI platform that provides a unified interface for local and cloud-based models, featuring built-in RAG, agent creation, and enterprise-grade user management.

An AI API gateway platform that enables the distribution and management of subscription quotas for various AI model providers.

A from-scratch C++/CUDA inference engine optimized for the NVIDIA RTX 5090 to deliver maximum single-GPU performance for Qwen models.

A bridge that lets AI agents like ChatGPT and Claude work directly with code and developer tools on your local machine without moving repositories to the cloud.

WorkBuddy2API is a self‑hosted Go service that turns one or many Tencent CodeBuddy accounts into an OpenAI‑compatible `/v1/chat/completions` API. It handles OAuth login, token refresh, multi‑account pooling, rate‑limit/cool‑down logic, session stickiness, cost‑aware routing and scheduled tasks (sign‑in, activity reporting, “cat travel”). Deploy with Docker‑Compose, add accounts via `login.sh`, and call the gateway just like any OpenAI endpoint.

An AI prompt optimization tool that iteratively improves prompts for text and image generation models to enhance output quality and accuracy.

Soup is a Python CLI (with optional web UI) that lets you fine‑tune LLMs—including 8B models—on low‑VRAM GPUs using a single YAML config and one command. It offers layer‑streaming, QLoRA, many training objectives, export to GGUF/ONNX/TensorRT, and an OpenAI‑compatible server, all with zero‑SSH, auto‑detected settings, and extensive documentation.

A VS Code extension and GitHub Copilot app canvas that analyzes local AI coding session logs to provide insights into prompting patterns, context health, and developer productivity.

An open-source AI Gateway and Python SDK that provides a unified OpenAI-compatible interface for calling 100+ different LLM providers.

GenOffice is an open‑source, cross‑platform desktop Office suite (Docs, Sheets, Slides, PDF, HTML, Markdown) that edits real `.docx`, `.xlsx`, `.pptx` and other formats. It embeds an AI agent that can modify documents directly—producing tracked changes, live formulas, new slides, etc.—and all edits are reversible. The suite works locally; only AI calls go over the network, and you can plug in any major LLM provider or your own endpoint. Installers are provided for macOS, Windows and Linux.

Project NOMAD is an offline-first knowledge and education server that bundles local AI chat (with RAG), offline Wikipedia, courses, maps, and data tools into a self-contained Docker-orchestrated system, keeping critical information available without internet.

A high-throughput library for LLM inference and serving that uses PagedAttention to optimize memory management and increase efficiency.

A fast, GPU-rendered, keyboard-driven IDE that integrates a modular AI coding agent and Unix-style composable tools for power users.

An open-source gateway and router for agent workflows that unifies multiple LLM providers under one API and optimizes model routing based on production traffic.

An edge-native MoE serving engine that enables running frontier-scale open-weight models on consumer hardware by optimizing CPU-GPU co-execution and memory management.

A local-first tool that aggregates session logs from AI coding assistants like Claude Code and Gemini CLI to track token usage and costs across models and projects.

A cross-provider workflow for Claude Code and Codex that ensures AI-generated code is independently reviewed and inspected by a second AI model to prevent errors.

An MCP bridge that connects AI assistants to the TradingView Desktop app via Chrome DevTools Protocol for AI-assisted chart analysis and Pine Script development.

A macOS app that displays a screen-edge notch showing real-time usage limits and session status for various AI coding assistants.

A Terraform and OpenTofu skill for AI agents that eliminates hallucinations and reduces token usage through a failure-mode-first diagnostic workflow.

An open-source orchestration platform for managing teams of AI agents through org charts, budgets, and goal-aligned task management.

A service and agent skill for stripping AI provenance marks and watermarks from text and files across multiple vendors and formats.

Codex Router is a community‑maintained bridge that lets the Codex editor/CLI send prompts to many external LLM providers (Anthropic, Kimi, DeepSeek, Grok, Gemini, Claude, etc.). It stores credentials locally, offers a guided installer, a macOS menu‑bar/desktop‑widget UI, and a Homebrew‑installable CLI. Experimental bridges let it reuse existing Claude, Cursor, and Gemini agents without exposing their OAuth tokens.

A lightweight, stealthy headless browser engine written in Rust for AI agents and web scraping, serving as a high-performance, low-memory replacement for headless Chrome.

A middleware tool that lets users replace the temporal upscalers and frame generation technologies in games that already support DLSS, FSR, or XeSS.

Ollama is a cross‑platform runtime that lets you download and run open‑source large language models locally. It offers a CLI, a REST API (localhost:11434), and official Python/JS SDKs, plus many community integrations (web UIs, LangChain, AutoGPT, etc.). Install with a one‑line script or Docker, then launch models like `ollama run gemma4` or use `ollama launch` to connect to coding assistants or personal bots.

A network diagnostics and browser detection toolbox that provides IP analysis, global connectivity tests, and AI service status monitoring.

A toolkit to extract and normalize local chat history from multiple AI coding assistants into JSONL format for backup, analytics, or fine-tuning.

An enterprise-grade, local-first agent workbench that unifies multiple AI agent engines into a single workspace for coordinating tasks and creating editable content.

MinerU is a professional document parsing tool that converts PDFs, images, and Office files into structured Markdown or LaTeX, featuring tiered parsing quality and stable locators for AI agents.

A self-hosted AI gateway that centralizes the management of multiple AI model providers, providing a consistent API, routing, and usage tracking for teams and applications.