Serve large Qwen models fast on the GPUs you actually own. Qwen3.8-27B on a single 24 GB card with vLLM: 127 tok/s single-user (381 when the answer quotes the prompt), ~1,035 tok/s at 64 concurrent, 150k-262k context. vLLM patches, requant pipeline, benchmarks.
CLI proxy that reduces LLM token consumption by 60-90% on common dev commands. Single Rust binary, zero dependencies
An agent organization structured as a company — 15+ departments, 125+ skills, each independently installable, citing the standards and regulators that settle the question. Runs in Claude Code and ChatGPT.
A practical guide to building enterprise AI agents across their full lifecycle.
DeepSeek Harness 的 Agent Teams 多智能体协作插件，支持多个 AI Agent 组成团队，协同完成复杂任务，实现任务分配、并行执行、成员通信与团队协作。 AgentTeams plugin for DeepSeek Harness
A native music streaming client, built with Rust and GPUI
WorkBuddy、CodeBuddy 桌面端增强助手：签到猫猫旅行成长计划查询、多账号独立备份、点切即用；免打扰模式让 AI 无人值守跑长任务；跨账号会话迁移、异常中断自动续接；暂存/快捷提示词；毛玻璃主题与更多实用功能。
Steam Play for macOS
Run the full 2.78-trillion-parameter Kimi K3 model, DeepSeek V4.1 Flash or GLM-5.3-Flash beyond available RAM by streaming activated weights directly from NVMe. A dependency-free, embeddable C inference engine.
An open-source Harness Engineering platform for coding agents—define harnesses as code, run controlled experiments, inspect evidence, and compare outcomes. Turn task evidence into actionable team and organization insights.