Open Source API Tools
An application programming interface (API) defines how software systems exchange data and request services. APIs let applications connect without sharing their internal implementation, supporting tasks such as retrieving information, updating records, and coordinating services. They are used in web and mobile applications, automation, data pipelines, and integrations between organizations. Common approaches include REST, GraphQL, and event-driven messaging, each with different patterns for structuring requests and responses.
Open source API tools include server frameworks, client libraries, gateways, documentation generators, testing utilities, and services for monitoring usage. When choosing one, consider its protocol support, security features, licensing, documentation, maintenance activity, runtime requirements, and fit with your existing stack. These tools are useful to developers building integrations or services, as well as teams seeking more control over how software communicates and how API usage is managed.
179 repositories · updated October 4, 2026
SwarmLLM: Run Local and Distributed AI Models
SwarmLLM runs open AI models on your computer and can pool resources with other computers to run larger models. It also provides OpenAI- and Anthropic-compatible APIs for local apps and agents.
e2a: Email API for Applications and AI Agents
e2a provides an email API and relay for applications and AI agents. It supports transactional sending, inbound mailboxes, and agent replies, with optional human review and hosted or Docker-based deployment.
shimmy: Serve Local GGUF Models with an OpenAI-Compatible API
Shimmy is a Rust inference server that runs GGUF language models locally and exposes an OpenAI-compatible API. It suits developers who want a lightweight alternative for connecting existing tools to local models without Python or llama.cpp.
router: Route AI Requests to the Best Model
weave-os/router is a Go proxy that routes AI requests across configured model providers, while accepting Anthropic, OpenAI, and Gemini API formats. It suits developers who want model choice and routing behind one endpoint, including agent and coding-tool users.
llm-d-router: Route Inference Requests Intelligently
llm-d Router directs inference requests using model-serving signals such as KV-cache locality, load, and priority. It is for teams running LLM serving on Kubernetes that need proxy-integrated routing and request flow control.
inference-gateway: Unify LLM Providers Behind One API
Inference Gateway proxies requests to cloud and local LLM providers through compatible APIs. It is suited to teams building provider-flexible AI services that need self-hosting, MCP tools, authentication, or observability.
harnessrouter: Unify Agent Harnesses Behind One API
HarnessRouter is a self-hosted Python service that exposes multiple agent harnesses through a unified, OpenAI Responses-compatible API. It suits teams building agent features that want shared session, streaming, file, and cancellation handling across harnesses.
n8n-sandbox-service: Run Commands in Isolated Environments
n8n-sandbox-service provides an API for creating isolated, on-demand environments to run commands and manage files. It is intended for teams that need to execute work in containers or Firecracker microVMs and manage those environments centrally.
a3m-router: Route LLM Requests Across Providers
A3M Router is a self-hostable gateway that routes OpenAI-compatible requests among language model providers. It offers heuristic and ML-based routing, provider failover, semantic caching, and optional parallel ensembles to help manage cost and availability.
otari: Route LLM Requests Through a Self-Hosted Gateway
Otari is a self-hosted, OpenAI-compatible gateway for routing requests to multiple LLM providers through one endpoint. It adds virtual keys, budget controls, routing policies, and usage tracking for teams managing provider access and spend.
OGAD: Run Private AI Models on Your Desktop
OGAD is a desktop AI studio and local runtime for running text, vision, image, and speech models on your own hardware. It also provides an OpenAI-compatible local API, with optional Pro features for on-device memory and activity capture.
tunnel-client: Connect Private MCP Servers to OpenAI
A Go client that connects private or localhost MCP servers to ChatGPT, Codex, the Responses API, and AgentKit through an OpenAI-hosted tunnel. It is designed for teams that need remote access without exposing MCP servers to the public internet.