OpenAI Open Source Projects
OpenAI-related tools help developers build applications that use language, speech, and other AI capabilities through model APIs or compatible interfaces. They address practical needs such as connecting applications to models, managing prompts and workflows, validating structured responses, and processing audio. Some tools also make it easier to switch between providers or run components locally, depending on their design and requirements.
Open source options in this area include client libraries, agent frameworks, API proxies, observability and safety tools, and model inference utilities. When choosing one, check its license, maintenance activity, supported models and API versions, security practices, and integration requirements. These tools are useful to developers and teams building AI-enabled software, as well as people exploring model workflows or seeking more control over how their applications connect to AI services.
24 repositories · updated September 20, 2026
Maskit: Local Privacy Gateway for LLMs and AI Tools
Maskit is a local privacy desensitization gateway engineered for large language models and AI tools. It automatically masks sensitive data in requests sent to AI services and then seamlessly restores it in streaming responses, ensuring private information remains local. This innovative solution supports various AI assistants like Cursor and Claude Code, along with any tool offering a configurable Base URL.
ctx-gate: LLM Context Gateway for Efficient Token Usage
ctx-gate is an LLM-agnostic context optimization proxy that reduces token consumption in AI interactions. It intelligently prunes conversation history and tool outputs, ensuring critical facts are retained without altering your workflow. Compatible with Anthropic and OpenAI APIs, ctx-gate helps developers manage LLM costs and maintain prompt fidelity.
tunnel-client: Securely Connect Private MCP Servers to OpenAI Services
The `tunnel-client` is an OpenAI-developed client that enables secure connections between private or localhost Model Context Protocol (MCP) servers and OpenAI services like ChatGPT, Codex, and AgentKit. It allows developers to integrate their internal MCP servers without exposing them to the public internet, ensuring enhanced security and operational control. This tool is ideal for scenarios requiring secure access from private networks to OpenAI's powerful AI models.
ADK-Rust: Build AI Agents in Rust with a Powerful Development Kit
ADK-Rust is a robust Agent Development Kit (ADK) for building AI agents in Rust. It offers a flexible framework with modular components for models, tools, memory, and real-time voice capabilities. Designed to be model-agnostic and deployment-agnostic, ADK-Rust empowers developers to create powerful and efficient AI agents.
aimock: Comprehensive Mocking for AI Application Testing
aimock is a powerful tool designed for comprehensive testing of AI applications by mocking various AI APIs and services. It offers a unified solution to simulate interactions with LLM APIs, vector databases, and other AI infrastructure, ensuring deterministic and efficient testing workflows. With features like record and replay, chaos testing, and seamless framework integrations, aimock significantly simplifies the development and validation of robust AI systems.
LobeHub: Your Chief Agent Operator for AI Team Orchestration
LobeHub acts as a Chief Agent Operator, streamlining the management of your AI team. It enables hiring, scheduling, and reporting on agents for 24/7 operations, allowing users to maintain control without constant online presence. This platform transforms individual AI tools into a cohesive, productive team.
Observers: A Lightweight Library for AI Observability in Python
Observers is a Python library designed for AI observability, enabling developers to track and store interactions with generative AI APIs. It provides a flexible framework with various observers for popular LLM providers and multiple storage backends. This tool helps in monitoring, debugging, and analyzing AI model behavior effectively.
FreeLLMAPI: Stack 16 Free LLM Tiers for 1.7 Billion Tokens/Month
FreeLLMAPI is an OpenAI-compatible proxy that aggregates the free tiers of 16 LLM providers, offering access to approximately 1.7 billion tokens per month. It simplifies access to diverse models through a single endpoint, featuring smart routing, automatic failover, and encrypted key storage. This powerful tool is designed for personal experimentation, allowing developers to leverage multiple free LLM resources efficiently.
Guardrails: Enhancing LLM Reliability and Structured Data Generation
Guardrails is a Python framework designed to build reliable AI applications by adding guardrails to large language models. It helps detect, quantify, and mitigate risks in LLM inputs/outputs, and facilitates the generation of structured data. This framework ensures more predictable and safer interactions with AI models.
codex-plugin-cc: Integrate OpenAI Codex for Code Reviews in Claude Code
The `codex-plugin-cc` repository offers a powerful integration for Claude Code users, enabling them to leverage OpenAI's Codex directly within their existing workflow. This plugin facilitates AI-powered code reviews, task delegation, and background job management, streamlining development processes. It provides a suite of commands for various review types and task handling, significantly enhancing developer productivity.
Article-Assistant--RAG-Telegram-Bot: AI-Powered Knowledge Base via Telegram
The Article Assistant is a sophisticated RAG (Retrieval-Augmented Generation) Telegram bot designed to create interactive knowledge bases from various documents. Users can upload PDFs or provide URLs, and the bot will provide AI-powered answers with source citations. This tool efficiently transforms static content into a dynamic, queryable resource.
TTSFM: OpenAI-Compatible Text-to-Speech API Service (Project Notice)
TTSFM was a project designed to mirror OpenAI's TTS service, offering a compatible API for free text-to-speech conversion with multiple voice options. Built on the openai.fm backend, it provided a Python SDK, RESTful API, and a web playground for easy testing and integration. Please note, the project is no longer functional as the openai.fm demo website has been shut down.