Open source. Open possibilities.

Aider is a terminal-based AI pair programming tool that allows developers to collaborate with LLMs to build new projects or modify existing codebases.

Provides free and paid large model API forwarding service, compatible with OpenAI protocol, can call models such as GPT, DeepSeek, Claude, Gemini, Qwen, etc.; free quota is refreshed periodically, paid price lower than official.

A fullstack reference app using React and LangGraph to build a research agent with Gemini 2.5, featuring iterative web search, reflection, and cited answers. Includes dev setup, CLI example, and Docker deployment instructions.

OpenAI-compatible proxy for Gemini Web API using cookie-based auth. Supports streaming, tool calling, and multiple models without API keys.

OmniRoute is an open-source MIT-licensed AI gateway providing one unified endpoint to access 352+ AI providers and 1200+ models (150+ free tiers). It features quota-aware auto-fallback, token compression saving 15–95%, and integrates with Claude Code, Cursor, Cline, and other coding agents.

Oh My OpenAgent (OmO) is an open-source AI coding agent toolkit with three editions: Ultimate for OpenCode, Light for Codex CLI, and standalone Senpi beta. It provides multi-model orchestration, ultrawork mode, parallel team agents, LSP/AST-Grep integration, and MCP support to automate and streamline software development workflows.

Sub2API is an open-source AI API gateway platform that aggregates subscription quotas from Claude, OpenAI, Gemini, Grok and more, and distributes them as API keys. It supports multi-account management, token-level billing, smart routing, concurrency and rate limits, built-in payments, and an admin dashboard.

CLIProxyAPI is a proxy server that exposes OpenAI/Gemini/Claude/Codex/Grok-compatible API endpoints for CLI AI coding tools. It supports OAuth login for Claude Code, ChatGPT Codex, Gemini, and Grok, multi-account load balancing, streaming, tool calling, multimodal input, a management API, and an embeddable Go SDK.

Repomix packs an entire repository into a single AI-friendly file (XML, Markdown, JSON, or plain text) for feeding codebases into LLMs like Claude, ChatGPT, and Gemini. It offers token counting, security checks, code compression, and remote repository support.

WebCodex lets ChatGPT, Claude, and other AI agents work directly with code and developer tools on your own machines. It provides a real development environment for cloud AI agents, keeping your repository local while enabling code inspection, editing, Git operations, test execution, and long-running work.

A transparency archive collecting extracted system prompts and guidelines from major AI models and agents, including OpenAI, Google, Anthropic, xAI, Perplexity, Cursor, and others, for public inspection.

A practical, from-scratch guide to training LLMs using PyTorch, covering data preparation, building a Transformer, pretraining, and post-training with SFT, DPO, PPO, and GRPO.

LangGraph is a low-level orchestration framework for building stateful, long-running AI agents, offering durable execution, human-in-the-loop control, memory, and deployment tooling.

Pake turns any webpage into a lightweight desktop app for macOS, Windows, and Linux with one command. Built on Rust/Tauri, installers are nearly 20x smaller than Electron, with shortcuts and style customization.

One API is a unified LLM API management and distribution system supporting dozens of mainstream models including OpenAI, Azure, Anthropic Claude, Google Gemini, DeepSeek, and more. It provides a unified OpenAI-compatible interface, token management, channel load balancing, user grouping, and redistribution features, deployable via single binary or Docker in one click.

Sim is a collaborative workspace for building, deploying, and monitoring AI agents and workflows. It supports 1,000+ integrations, visual/conversational/code-based agent creation, and self-hosting via Docker. Includes tables, files, knowledge bases, and a desktop app.

RightMemory provides durable memory, a user-directed Pursuit map, and reusable Agent Corrections for AI coding agents. It stores context as Git-syncable Markdown trees organized in a graph with typed edges, enabling multi-device continuity and multi-agent collaboration while keeping memory ownership explicit and vendor-neutral.

Graphify is a CLI skill that maps a codebase into a queryable knowledge graph for AI coding assistants. It uses tree-sitter for local deterministic code parsing, no embeddings, and outputs graph.html, GRAPH_REPORT.md, and graph.json.

Gemini CLI is an open-source AI agent that integrates Gemini models directly into the terminal, providing developers with a command-line interface for AI-assisted coding and automation.

LangExtract is a Python library from Google that uses LLMs to extract structured information from unstructured text, grounding every extraction to its exact source location and generating interactive HTML visualizations.