anthropic-proxy

Self-hosted LLM security proxy. PII redaction, prompt injection defense, KVKK/GDPR/PCI-DSS compliance. Sub-millisecond latency

Free Claude API + free OpenAI API in one unified proxy. Drop-in compatible with Anthropic SDK, OpenAI SDK, Claude Code CLI, OpenCode, LangChain. 100+ models (Claude Opus 4.7, Sonnet 4.6, Haiku 4.5, GPT-5.5, GPT-5.4-mini, GPT-5.3-codex). Open beta — totally free.

A single-binary proxy that lets Claude Code drive OpenAI-compatible backends.

A highly compatible proxy bridge with translation for API requests to multiple backend providers (OpenAI-Oauth, RunPod, Ollama,,etc.). Configure endpoints through a web admin UI and map virtual model names to actual backend models. Create API keys to share and monitor usage and costs by tools / teams. Opencode/Claude to queue servers too.

Hardened LLM and MCP gateway container — deployment recipes for the customer-edge service-edge image with policy enforcement, mTLS, and multi-provider routing.

Unified AI API Gateway — one API key to manage all your LLM providers: OpenAI, Anthropic, Google, DeepSeek, Qwen, and more. Smart routing, cost tracking, health monitoring, team management.

Anthropic-compatible proxy for Claude Code with provider routing (OpenRouter, GitHub Models, NIM, LM Studio, llama.cpp).

Lightweight proxy for using Cline API via Anthropic-compatible or OpenAI-compatible provider

Cut Claude Code token costs by routing subagent tasks to cheaper models (Kimi) while keeping main Claude interactions on Anthropic

Reverse-engineered Command Code OpenAI & Anthropic proxy gateway v3 | Auto-accept | 8-level reasoning | Multi-account OAuth | Long-session streaming | Windows exe

A lightweight OpenAI & Anthropic compatible API gateway with intelligent provider routing, automatic failover, and streaming. Optimized for n8n AI Agents and Claude Code.

Production-grade AI Gateway with reversible Content Shield (DLP) — mask, redact, block PII/PHI/secrets in LLM traffic.

Cost-first AI inference router — tries cheapest capable provider first, fails over across 21+ LLM providers (36 via OpenRouter). OpenAI/Anthropic SDK compatible, Bitwarden secrets management, 5 cost tiers from free to premium.

Production LLM gateway: OpenAI-compatible API in front of OpenAI, Anthropic, and Bedrock. Ordered-fallback routing with per-provider circuit breakers, Redis prefix cache, Prometheus + Grafana, Kubernetes.