Pinned Loading
Repositories
- tair-kvcache Public
Alibaba Cloud's high-performance KVCache system for LLM inference, with components for global cache management, inference simulation(HiSim), and more.
-
- open-guardrail Public
Evidence-based guardrails for AI agents and automated workflows. Versioned policies, structured evidence, and auditable allow/deny decisions.
- MongoShake Public
MongoShake is a universal data replication platform based on MongoDB's oplog. Redundant replication and active-active replication are two most important functions. 基于mongodb oplog的集群复制工具,可以满足迁移和同步的需求,进一步实现灾备和多活功能。
- loongsuite-pilot Public
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.
- atrex-kernel-agent Public
An end-to-end agent project for GPU kernel implementation, analysis, profiling, and iterative optimization. It helps an agent turn PyTorch logic or an existing kernel into a high-performance GPU kernel through a structured, profile-driven workflow.