#qwen3

Desktop/OS-Level autonomous agent that observes human-computer interactions to discover and automate repetitive workflows using AI-powered pattern mining.

Run Qwen3.8-27B fully offline on an Apple Silicon Mac (MLX, 4/5/8-bit) and use it as the local backend for Claude Code. Uncensored/abliterated build supported. No API key, no network. Built by yempik.

后悔承诺门 · 试验台（探针项目，非产品）：Transformer 缺一条「写通道」。第一步已实现——零后训练 / 零厂商协作 / 不碰 KV 的 harness，测四项外部强制机制（参数级风险分级、尾部强制自审、独立审核 Agent、射程锁上下文编辑）及 A–H 组合的离线效果；第二步已规划——协同进化：KV 局部编辑、推理轨迹纠错、后训练。每一步都给出可操作结论，包括证伪。

Qwen3 prompt baselines for tool selection and evaluation in the Huawei LLM Agent Competition.

Evidence-grounded Agentic RAG platform for industrial root-cause investigation using Qwen3, BGE-M3, hybrid retrieval, LangGraph, verification, and human approval.

Reproducible QLoRA SFT and DPO experiments for open-weight LLM reasoning, with locked selection, matched controls, and audit-grade provenance.

Private local AI studio for chat, vision, deep research, OpenAI-compatible APIs, and Ghidra/MCP reverse engineering