Top 23 openai-api Open-Source Projects

1. openai-cookbook

   1 245 73,964 9.4 Jupyter Notebook

   Examples and guides for using the OpenAI API

   

   Project mention: How Far Can a Small Coding Model Go With a Better Harness? | dev.to | 2026-05-20

   Hookele started from OpenAI's GPT-5.1 coding agent notebook, which wires run_command, apply_patch, web_search, and Context7 docs lookup (a third-party library-documentation service) into the Responses API. The cookbook walks through the happy path. What follows is what happens when the happy path breaks: streams that drop mid-reasoning, diffs that fail to apply because context drifted by two characters, models that stall for 40 iterations without doing anything productive.

2. SaaSHub

   www.saashub.com featured

   SaaSHub - Software Alternatives and Reviews. SaaSHub helps you find the best software and product alternatives

   

3. gpt4free

   2 45 66,281 9.8 Python

   The official gpt4free repository | various collection of powerful language models | opus 4.6 gpt 5.3 kimi 2.5 deepseek v3.2 gemini 3

   

   Project mention: GPT4Free: "educational project" for free LLM inference from various services | news.ycombinator.com | 2025-06-30

4. Hello-Python

   3 3 35,862 7.0 Python

   Curso para aprender el lenguaje de programación Python desde cero y para principiantes. 100 clases, 44 horas en vídeo, código, proyectos y grupo de chat. Fundamentos, frontend, backend, testing, IA...

   

5. one-api

   4 2 34,621 6.9 JavaScript

   LLM API 管理 & 分发系统，支持 OpenAI、Azure、Anthropic Claude、Google Gemini、DeepSeek、字节豆包、ChatGLM、文心一言、讯飞星火、通义千问、360 智脑、腾讯混元等主流模型，统一 API 适配，可用于 key 管理与二次分发。单可执行文件，提供 Docker 镜像，一键部署，开箱即用。LLM API management & key redistribution system, unifying multiple providers under a single API. Single binary, Docker-ready, with an English UI.

   

   Project mention: DeepSeek V4-Pro Just Got 4x Cheaper. But Here's What Nobody's Talking About | dev.to | 2026-05-23

   You can set this up with One-API (open source, Docker-friendly):

6. omlx

   5 18 16,061 2.2 Python

   LLM inference server with continuous batching & SSD caching for Apple Silicon — managed from the macOS menu bar

   

   Project mention: OMLX v0.3.9 Stable Merges Native MTP (Multi-Token Prediction) | news.ycombinator.com | 2026-05-21

7. open-saas

   6 46 14,620 9.1 TypeScript

   A 100% free modern JS SaaS boilerplate (React, NodeJS, Prisma). Full-featured: Auth (email, google, github, slack, MS), Email sending, Background jobs, Landing page, Payments (Stripe, Polar.sh), Shadcn UI, S3 file upload. AI-ready with tailored AGENTS.md, skills, and Claude Code plugin. One cmd deploy. Powered by Wasp full-stack framework.

   

   Project mention: Open Vibe -- Ship your SaaS with AI. Without getting stuck. | dev.to | 2026-05-12

   Phase 3 — A real SaaS. Build on Open SaaS, a free $300-value SaaS template the Wasp team maintains. Auth, payments, an admin dashboard, file uploads, AI integrations, deploy, and more.

8. gorilla

   7 54 12,892 8.5 Python

   Gorilla: Training and Evaluating LLMs for Function Calls (Tool Calls)

   

   Project mention: Sub-Agent Architectures: Patterns, Trade-offs, and a Kotlin Implementation | dev.to | 2026-03-23

   Tool confusion — a model with 20 tools tends to make worse decisions than one with 5 (tool-use accuracy degrades with scale; see the Gorilla LLM benchmark for empirical evidence)

9. langchain4j

   8 28 12,221 9.9 Java

   LangChain4j is an idiomatic, open-source Java library for building LLM-powered applications on the JVM. It offers a unified API over popular LLM providers and vector stores, and makes implementing tool calling (including MCP support), agents and RAG easy. It integrates seamlessly with enterprise Java frameworks like Quarkus and Spring Boot.

   

   Project mention: Agent Memory with LangChain4j and Oracle AI Database | dev.to | 2026-04-22

   In this article, we'll build a small, memory-backed assistant with LangChain4j and Oracle AI Database. The assistant can search prior incidents, runbooks, decisions, and shift handoffs to answer questions. It can write new memories back to the database so they become searchable in any session. Additionally, all user, agent, and tool messages are logged to database table for observability and auditing.

10. inference

    9 2 9,338 9.7 Python

    Swap GPT for any LLM by changing a single line of code. Xinference lets you run open-source, speech, and multimodal models on cloud, on-prem, or your laptop — all through one unified, production-ready inference API.

    

11. chatgpt-demo

    10 6 8,019 7.9 TypeScript

    Minimal web UI for ChatGPT.

    

12. Manifest

    11 55 6,828 9.9 TypeScript

    A complete backend in a single YAML file ✨

    

    Project mention: 10 Ways To Reduce Your LLM API Costs | dev.to | 2026-05-20

    At Manifest, we think that AI is an incredible technology, and that it deserves to be affordable. Our platform is open source and gives total control to our users. Check out our website and give us a star on GitHub to support us! Or simply share this post, as it helps others pay less for AI.

13. atomic-agents

    12 5 5,962 9.3 Python

    Building AI agents, atomically

    

14. ChatGPT

    13 4 5,892 8.1 TypeScript

    OpenAI API Free Reverse Proxy (by PawanOsman)

    

15. json_repair

    14 1 4,947 9.1 Python

    Repair malformed JSON from LLMs, APIs, logs, and user input in Python.

    

16. Learn_Prompting

    15 80 4,678 4.3 MDX

    Prompt Engineering, Generative AI, and LLM Guide by Learn Prompting | Join our discord for the largest Prompt Engineering learning community

    

    Project mention: Learn, Apply, & Get Certified in Prompt Engineering | news.ycombinator.com | 2025-09-12

17. llama-swap

    16 5 4,388 9.3 Go

    Reliable model swapping for any local OpenAI/Anthropic compatible server - llama.cpp, vllm, etc

    

    Project mention: Llama-swap: Reliable model swapping | news.ycombinator.com | 2026-03-12

18. lemonade

    17 10 4,212 9.8 C++

    Lemonade helps users discover and run local AI apps by serving optimized LLMs right from their own GPUs and NPUs. Join our discord: https://discord.gg/5xXzkMu8Zk

    

    Project mention: Adding Gemma 4 speech recognition to a .NET desktop app: the llama-server sidecar that survived | dev.to | 2026-05-26

    Lemonade is strong on Ryzen AI hardware, but it is AMD-specific. Cross-vendor was a hard requirement.

19. VLMEvalKit

    18 1 4,199 9.6 Python

    Open-source evaluation toolkit of large multi-modality models (LMMs), support 220+ LMMs, 80+ benchmarks

    

    Project mention: How Machines See: Inside Vision Models and Visual Understanding APIs | dev.to | 2025-12-26

    Run evaluations using tools like VLMEvalKit to compare model performance on your specific use case before deployment.

20. node-chatgpt-api

    19 5 4,178 8.7 JavaScript

    A client implementation for ChatGPT and Bing AI. Available as a Node.js module, REST API server, and CLI app.

    

21. optillm

    20 20 4,133 9.4 Python

    Optimizing inference proxy for LLMs

    

    Project mention: OptiLLM: Accuracy improvements on reasoning tasks with zero training | news.ycombinator.com | 2025-11-23

22. langroid

    21 29 4,029 9.4 Python

    Harness LLMs with Multi-Agent Programming

    

    Project mention: Agent Framework Is Just a Bad Clone of Elixir | news.ycombinator.com | 2026-02-19

    I ran into this question when thinking about the approach for a recent project. Yes CLI coding tools are good agents for interactive use, but if you are building a product then you do need an agent abstraction.

    You could package Claude Code into the product (via agents-sdk or Claude -p) and have it use the API key (with metered billing) but in my case I didn’t find it ergonomic enough for my needs, so I ended up using my own agent framework Langroid for this.

    https://github.com/langroid/langroid

    (No it’s not based on that similarly named other framework, it’s a clean, minimal, extensible framework with good dx)

23. copilot-api

    22 3 4,021 9.4 TypeScript

    Turn GitHub Copilot into OpenAI/Anthropic API compatible server. Usable with Claude Code!

    

    Project mention: GitHub Actions down again today | news.ycombinator.com | 2026-05-26

    Meanwhile people using a copilot proxy [1] with a third party harness have zero issues. Very clumsy enforcement if not a bug.

    [1] https://github.com/ericc-ch/copilot-api

24. vault-ai

    23 80 3,391 5.2 JavaScript

    OP Vault ChatGPT: Give ChatGPT long-term memory using the OP Stack (OpenAI + Pinecone Vector Database). Upload your own custom knowledge base files (PDF, txt, epub, etc) using a simple React frontend.

    

openai-api related posts

• GitHub Actions down again today

  4 projects | news.ycombinator.com | 26 May 2026

• DeepSeek V4-Pro Just Got 4x Cheaper. But Here's What Nobody's Talking About

  1 project | dev.to | 23 May 2026

• Cursor Just Released Composer 2.5. Here's What Actually Changed for AI Coding Agents.

  2 projects | dev.to | 21 May 2026

• How Far Can a Small Coding Model Go With a Better Harness?

  5 projects | dev.to | 20 May 2026

• How I Made an Autonomous Kubernetes SRE Agent Observable with MLflow

  2 projects | dev.to | 15 May 2026

• Copilot Squad

  5 projects | dev.to | 5 May 2026

• Why the First Turn in a Coding Agent Can Use So Many Input Tokens — and Why That Gets Better Over Time

  2 projects | dev.to | 29 Apr 2026
• A note from our sponsor - SaaSHub
  www.saashub.com | 7 Jun 2026

  SaaSHub helps you find the best software and product alternatives Learn more →

Index

Sponsored

SaaSHub - Software Alternatives and Reviews

SaaSHub helps you find the best software and product alternatives

www.saashub.com