openapi

open-webui/open-webui

A self-hosted, provider-agnostic hub for local and cloud LLMs — Open WebUI unifies Ollama and OpenAI-compatible APIs behind one offline-capable interface, letting users mix local and cloud models freely. Granular RBAC, plugin support via Filters/Actions/Tools, and MCP/OpenAPI tool server connections make it appealing to teams needing customizable, secure self-hosted AI agents.

User-friendly AI Interface (Supports Ollama, OpenAI API, ...)

fastapi/fastapi

Python type hints power this high-performance API framework — FastAPI builds on Starlette and Pydantic to turn standard Python type hints into automatic request validation, serialization, and interactive OpenAPI/Swagger docs. It targets developers who want NodeJS/Go-level performance with less boilerplate and fewer bugs than typical Python web frameworks.

FastAPI framework, high performance, easy to learn, fast to code, ready for production

usebruno/bruno

An offline, Git-friendly API client that skips the cloud entirely — Bruno stores API collections as plain-text files using its own Bru markup, so you can version them with Git instead of syncing to a vendor cloud. It's built for developers who want a privacy-respecting, offline alternative to Postman or Insomnia and full control over their collection data.

Opensource IDE For Exploring and Testing API's (lightweight alternative to Postman/Insomnia)

fastapi/full-stack-fastapi-template

A batteries-included FastAPI + React starter with Cloud deploy option — A GitHub template combining FastAPI, SQLModel, PostgreSQL, React, Vite, Tailwind CSS and shadcn/ui, with JWT auth, email recovery, Pytest/Playwright tests and GitHub Actions CI/CD. It bundles optional FastAPI Cloud deployment alongside Docker Compose, making it useful for developers who want a ready-to-clone full-stack boilerplate.

Full-stack web application template with FastAPI, React, SQLModel, PostgreSQL, Vite, Tailwind CSS, shadcn/ui, FastAPI Cloud, and Docker Compose.

grpc-ecosystem/grpc-gateway

Serve one gRPC API as both gRPC and REST, generated from proto files — A protoc plugin that reads google.api.http annotations in your gRPC service definitions and generates a reverse-proxy server translating RESTful JSON calls into gRPC. Useful for teams who want a single proto source of truth while still exposing a REST/OpenAPI-compatible API to clients.

gRPC to JSON proxy generator following the gRPC HTTP spec

apache/apisix

The Cloud-Native API Gateway and AI Gateway

samchon/typia

Super-fast/easy runtime validators and serializers via transformation

mvanhorn/cli-printing-press

A printing press that forges AI-agent-ready CLIs from any API — This Go tool studies official API docs, community CLIs, and MCP servers, then auto-generates a token-efficient CLI, a Claude Code skill, and an MCP server for any API or website. It bakes in local SQLite sync, offline search, and compound commands, demonstrated by its ESPN, flight-goat, and linear-pp-cli examples.

Every API has a secret identity. This finds it, absorbs every feature from every competing tool, then builds the GOAT CLI — designed for AI agents first, with SQLite sync, offline search, and compound insight commands.

HelpCode-ai/anythingmcp

Self-hosted gateway that wraps 517 APIs as MCP tools — AnythingMCP connects REST/OpenAPI, SOAP, GraphQL, OData and SQL systems to Claude, ChatGPT and Copilot without writing a custom MCP server. It ships 517 ready-made connectors, including SAP, Etsy and Amazon Seller, with 23 needing no API key, plus RBAC, SSO and audit logs for enterprise use.

MCP gateway for AI agents: turn any REST/OpenAPI, GraphQL, SOAP or SQL API into MCP tools. 562 ready-made connectors (SAP, ERP, e-commerce) with RBAC, SSO, audit logs and a knowledge graph.

rasonyang/ai-native-callcenter

A single Go binary turns FreeSWITCH into an AI-first call center — Self-hosted call center where a speech-to-speech model answers calls by default and a flow decides when to hand off to a human agent, who takes over mid-call via a Chrome extension without dropping the line. Runs as one Go binary with PostgreSQL and FreeSWITCH, works with OpenAI, Grok, Qwen or Doubao realtime models, and ships an API-first design with a built-in agent desktop.

Self-hosted AI call center: AI talks, code controls the call. AI agents answer every call; humans take over without dropping it. Runs on FreeSWITCH with your SIP trunk and realtime model (OpenAI, Grok, Qwen, Doubao, or any compatible gateway). API-first, with a built-in agent desktop.