Apps tagged with 'ai-gateway'

Python SDK, Proxy Server (LLM Gateway) to call 100+ LLM APIs in OpenAI format - [Bedrock, Azure, OpenAI, VertexAI, Cohere, Anthropic, Sagemaker, HuggingFace, Replicate, Groq].

Streamline your workflow with Lynkr, a CLI tool that acts as an HTTP proxy for efficient code interactions using Claude Code CLI.

Privacy-first LLM proxy and AI gateway — load balancing, multi-provider routing, API key management, usage tracking, rate limiting. Self-hosted. Zero knowledge of your prompts.

Otoroshi is a modern, cloud-native API gateway and service mesh designed to manage, secure, and observe services, webapps and APIs at scale.

AI gateway written in Go. The fastest and the most resource-efficient. It serves OpenAI-compatible API and Anthropic-compatible API for OpenAI, Anthropic, Gemini, Groq, xAI & Ollama.

An AI API platform offering 200+ AI models with a single and secure API endpoint, enabling developers and businesses to integrate all major AI models into applications and existing systems/.

The proxy server for AI-native apps. Arch handles the pesky low-level work in building agents like clariyfing vague user input, routing prompts to the right agents and unifying access to any LLM - all without locking you into a framework.

The full-stack cloud platform for AI agents. Build with intelligent routing, persistent state, and seamless handoffs. Deploy with built-in APIs, React frontends, databases, sandboxes, and monitoring — on our cloud, your VPC, or on-prem.

A high-performance, Go-native AI gateway for secure, air-gapped environments. Sub-15ms overhead with built-in NIST-aligned PII scrubbing and semantic caching. No Python, no bloat.

flo2 is a cloud LLM gateway that routes one OpenAI- and Anthropic-compatible API key to many model providers, adding no token markup while handling smart routing, fallback, racing, A/B testing and per-call cost tracking.

Unified platform for routing LLM traffic, observability, evals, prompt management, tracing, and spend controls, reducing dashboard switching time.

A self-hosted, open-source (Apache 2.0) proxy for LLM's with prometheus metrics.

Open-source, OpenAI-compatible LLM gateway you run yourself. One endpoint for 40+ providers, with virtual keys, budgets, and usage tracking.