aisix
Open-source AI gateway for LLMs & AI agents, built in Rust. One OpenAI-compatible API for OpenAI, Anthropic, Gemini, Bedrock & more — routing, guardrails, caching, rate limits, observability.
- 227
- Rust
- Apache-2.0
- 3 d ago
Open-source AI gateway for LLMs & AI agents, built in Rust. One OpenAI-compatible API for OpenAI, Anthropic, Gemini, Bedrock & more — routing, guardrails, caching, rate limits, observability.
Engine-agnostic LLM gateway in Rust. Full OpenAI & Anthropic API compatibility across vLLM, TRT-LLM, TokenSpeed, SGLang, OpenAI, Gemini & more. Industry-first gRPC pipeline, KV cache-aware routing, chat history, tokenization caching, Responses API, embeddings, WASM plugins, MCP, and multi-tenant auth.
An Agent Development Kit (ADK) allowing for seamless creation of A2A-compatible agents written in Go.
A2A agent server enabling Google Calendar scheduling, retrieval, and automation
An Agent Development Kit (ADK) allowing for seamless creation of A2A-compatible agents written in Rust.
A command-line tool to scaffold and manage enterprise-ready AI Agents powered by the A2A (Agent-to-Agent) protocol
A Git-first CLI coding agent that turns ideas, issues, and tasks into real code changes. It can run remotely from your mobile phone or automate your computer.
Open-source desktop app for AI agents that code, browse, create content, and control local or remote computers. Use cloud or local models with your own API keys.
Telnyx Edge Compute CLI: deploy serverless edge functions with KV, SQL databases and stateful actors for voice AI apps.
Curated catalog of Agent Skills for the Inference Gateway ecosystem
This project provides a Kubernetes Operator for managing the lifecycle of the inference-gateway and its related components. It simplifies deployment, configuration, and scaling of the gateway within Kubernetes clusters, enabling seamless integration of inference workflows.
local model & cloud models collab to solve tasks, no private data is sent to the cloud
An Agent Development Kit (ADK) allowing for seamless creation of A2A-compatible agents written in TypeScript
ROCm-first OpenAI-compatible inference gateway for open-weight reasoning models. Single active profile (gpt-oss-20b, deepseek-r1-distill, qwen3-4b), host-mounted weights, fail-closed contract. FastAPI + vLLM.
Hardware probe and best-of-N sampling harness in C. Ranks GGUF quantisations against measured VRAM and RAM, drives Ollama or llama.cpp over OpenAI-format HTTP on localhost, and gates every candidate behind a static check and a test run.