PolyStrata — AI skill for Claude Code
Run large AI models on your own PC: Qwen3.8-Flash-Next on Strata's engine, and GLM 5.3 Flash, DeepSeek V4 Flash, LFM2.5, Qwen3.6, Ornith 1.5, Gemma 4, Tiel Coder and MiniCPM-V on a second engine writt.
How to install PolyStrata
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open psyb0t/PolyStrata and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What PolyStrata does
Run large AI models on your own PC: Qwen3.8-Flash-Next on Strata's engine, and GLM 5.3 Flash, DeepSeek V4 Flash, LFM2.5, Qwen3.6, Ornith 1.5, Gemma 4, Tiel Coder and MiniCPM-V on a second engine written for PolyStrata. One-click install for Windows and Linux, OpenAI/Anthropic API on localhost.
Alternatives in AI
- Repomix — 📦 Repomix is a powerful tool that packs your entire repository into a single, AI-friendly file 22.7k ★
- Qwen Code — A command-line AI workflow tool adapted from Gemini CLI, optimized for Qwen3-Coder models with enhanced parser 20.8k ★
- Deepreasoning — A high-performance LLM inference API and Chat UI that integrates DeepSeek R1's CoT reasoning traces with Anthr 5.4k ★
README
PolyStrata
**English** · [简体中文](README.zh-CN.md) · [日本語](README.ja.md) · [Deutsch](README.de.md) · [Français](README.fr.md) · [Español](README.es.md) · [Português](README.pt-BR.md)
Run large AI models on your own PC
Qwen3.8-Flash-Next, GLM 5.3 Flash, DeepSeek V4 Flash, LFM2.5, Qwen3.6, Ornith 1.5, Gemma 4, Tiel Coder and MiniCPM-V · free and open source
Claude Code on Qwen3.6-35B-A3B UD-Q3_K_M, on the laptop with the 8 GB card, in real time: it adds a --json option to a small program, writes a test for it and runs the tests. The server had read Claude Code's system prompt when it started ("warm_start": true).
A voxel pagoda garden, 1 shot prompt running on an RTX 5070 with Strata (Qwen3.8-Flash-Next IQ3_S, 128K context) ·
full video (49 s)
PolyStrata runs large AI models on a normal PC, models that usually need a server. They chat, write code and work with your apps and coding agents. Nothing leaves your PC.
It runs nine models, on two engines:
- Qwen3.8-Flash-Next on an NVIDIA or AMD graphics card with 12 GB or more, on Windows or Linux. It also reads pictures. Its engine is the Strata project'
Related Skills
Local LLM Benchmarks
Measured llama.cpp benchmarks on AMD Radeon RDNA4 with ROCm: RX 9070 XT + Radeon AI PRO R9700 (48 GB). Qwen3.8
Slotstream
Run a 105 GB AI model on a Mac that can't hold it. Slotstream streams Qwen3.8-Flash-Next (125B mixture of expe
Levogat AI API
Levogat - 国内 AI API 中转站：500+模型(GPT-6/Claude Opus 5/Gemini 3.8/DeepSeek V4/Grok 4.6/Qwen3.8/GLM-5.3/Kimi K3)免翻墙
LLM Bridge MCP
A model-agnostic Message Control Protocol (MCP) server that enables seamless integration with various Large La
Headless Relay
An Agent Skill that lets your coding agent ask the other AI models on your machine for help: GPT, GLM, Grok, G
Universal Bypass For Claude ChatGPT Qwen Deepseek LLM Claude Code Codex
Carefully human hand written llm jailbreaks for the latest models that are available on the market. GPT-6 Astr
Related Agents
Glm Agent
Runs Z.AI GLM on the user's GLM Coding Plan. Three modes - consult (direct API call, 1M context, for inputs to
Verina Engineer
Senior software engineer and tech lead for Verina. Use for architecture, backend (FastAPI/Python), frontend wi
Architect Glm
GLM 5.3 Flash/max design and architecture advisor. Use when the GLM lane is selected; OpenAI uses sw-architect
