gateway

11 repositories

traefik/traefik

A reverse proxy that auto-discovers your microservices — Traefik automatically detects services running in Docker, Kubernetes, Consul, Etcd or ECS and configures routing without manual rules. It supports Gateway API, Ingress and OpenTelemetry, making it useful for teams running dynamic container or cluster environments who want self-updating load balancing and TLS via Let's Encrypt.

GoAttention 28
★65,516
BerriAI/litellm

LiteLLM moves to a Rust core for a leaner AI gateway — LiteLLM now ships a Rust core under its Python SDK, aiming to be a faster, lighter self-hosted AI gateway. It unifies 100+ LLM APIs (Bedrock, Azure, OpenAI, Anthropic, VertexAI, vLLM, Nvidia NIM) in OpenAI format, adding cost tracking, guardrails, load balancing and logging for teams running LLMOps at scale.

PythonAttention 42
★63,072
langfuse/langfuse

Open-source tracing and evals for LLM apps and agents — Langfuse is a self-hostable platform to trace, evaluate, and debug LLM applications, with integrations for LangChain, LlamaIndex, and AutoGen plus a prompt playground and management tools. Backed by Y Combinator, it suits teams needing open, self-hosted observability instead of closed SaaS-only tools.

TypeScriptAttention 38
★37,271
zeromicro/go-zero

A battle-tested Go framework now leaning into AI-native, spec-driven workflows — go-zero is a Go web/rpc framework with built-in resilience (circuit breaking, rate limiting, load shedding) proven at tens-of-millions-user scale. Its goctl tool generates code from simple API spec files across Go, iOS, Android, Kotlin, Dart, TypeScript and JavaScript, now expanding toward AI-native, spec-driven development.

GoAttention 12
★33,423
fosrl/pangolin

Self-hostable SASE: WireGuard VPN, zero-trust proxy and PAM in one — Pangolin unifies zero-trust VPN, reverse proxy, privileged access management and an identity-aware AI gateway under one identity and policy model, built on WireGuard. It explicitly targets the territory of Cloudflare One, Zscaler and Prisma but stays open-source, self-hostable and lightweight to run.

TypeScript🇺🇸 North AmericaAttention 59
★23,568
rmyndharis/OpenWA

A self-hosted WhatsApp gateway built on NestJS with swappable backends — OpenWA is a free, open-source WhatsApp API gateway for developers who want full control over messaging infrastructure without vendor lock-in. Its pluggable architecture lets you swap database engines (SQLite/PostgreSQL), media storage (local/S3), and caching (none/Redis) via config instead of code changes. Built on NestJS with Docker support.

TypeScript🌐 ElsewhereAttention 52
★16,731
maximhq/bifrost

A zero-config gateway unifying 23+ LLM providers behind one API — Bifrost is a Go-based AI gateway giving one OpenAI-compatible API across 23+ providers, with automatic failover, load balancing, semantic caching, virtual keys and budgets. It deploys in seconds via npx or Docker, includes a web UI for config and monitoring, and adds under 200µs overhead at 5k RPS—aimed at teams building reliable, multi-provider AI apps and agents.

Go🇺🇸 North AmericaAttention 46
★9,487
IBM/mcp-context-forge

A unified gateway that federates MCP, A2A, and REST/gRPC APIs — ContextForge is an open source registry and proxy from IBM that merges tools, agents, and APIs behind one endpoint, with centralized governance, discovery, and observability. It includes 40+ plugins, OpenTelemetry tracing, and runs as a compliant MCP server deployable via PyPI, Docker, or Kubernetes for multi-cluster scale.

Python🇺🇸 North America
★4,796
awslabs/agentcore-samples

Sample code for deploying AI agents at scale with Bedrock AgentCore — A collection of samples showing how to deploy and operate AI agents securely at scale using Amazon Bedrock AgentCore. It's framework- and model-agnostic, covering Strands Agents, CrewAI, LangGraph, LlamaIndex, plus runtime, gateway, identity and memory management—useful for teams moving agent prototypes into production.

Python🇺🇸 North AmericaAttention 30
★3,523
mozilla-ai/otari

A self-hosted gateway that unifies 40+ LLM providers behind one API — Otari is a Mozilla AI project that lets you run your own OpenAI/Anthropic-compatible gateway in front of 40+ model providers. It adds virtual API keys, pre-spend budget checks, usage tracking, and local routing policies for failover, useful for teams wanting to own their AI infrastructure instead of relying on a hosted proxy.

PythonAttention 55
★901
mrifqidaffaaditya/WA-AKG

Self-hosted WhatsApp gateway with multi-session dashboard and 109+ API endpoints — WA-AKG turns WhatsApp into a self-hosted REST API using Next.js 16, Baileys and Prisma. It supports multi-session accounts, scheduled messages, auto-replies and webhooks, with 109+ documented endpoints, making it suited for developers building bots, automation or customer-service gateways.

TypeScriptAttention 50
★872