Alibaba

RTP-LLM: Alibaba's high-performance LLM inference engine for diverse applications.

Local-first telemetry collector for AI coding agents — unified OpenTelemetry events for Claude Code, Codex, Cursor and more. Token usage, cost, traces and security audit, exported anywhere.

Secure, fast, efficient, battle-tested at Alibaba's scale. Hybrid architecture code review tool: deterministic pipelines + LLM Agent, precise line-level comments, built-in multi-language ruleset (NPE, thread-safety, XSS, SQL injection), OpenAI & Anthropic compatible.

Alibaba Cloud's high-performance KVCache system for LLM inference, with components for global cache management, inference simulation(HiSim), and more.

XQUIC Library released by Alibaba is a cross-platform implementation of QUIC and HTTP/3 protocol.

A collection of modern C++ libraries, include coro_http, coro_rpc, compile-time reflection, struct_pack, struct_json, struct_xml, struct_pb, easylog, async_simple etc.

MNN: A blazing-fast, lightweight inference engine battle-tested by Alibaba, powering high-performance on-device LLMs and Edge AI.

The one data index for your agentic applications

An evaluation and evolution tool for Agent Skills.