An easy way to use Claude Code with local LLMs
Summary
Community maintainer integrates Lemonade local LLMs with Claude Code and other CLIs, enabling local LLM usage.
Similar Articles
Running local LLM's as agents in Claude Code
This article presents a custom MCP setup that enables offloading coding tasks from Anthropic's Claude models to local Qwen3.8-27B models within the same session, using tools like llama.cpp.
Gitlawb/openclaude
OpenClaude is an open-source coding-agent CLI that supports various cloud and local LLM providers, offering a terminal-first workflow with features like prompts, tools, and streaming output.
@TheAhmadOsman: You can run local models at home and use any agent harness like Codex or Claude Code with them
Ahmad built a simple tool that makes Claude Code work with any local LLM, demonstrated using vLLM serving GLM-4.5 Air on 4x RTX 3090s.
@QingQ77: Give text-only LLMs in Claude Code (like DeepSeek, CodeLlama, Qwen-Coder) vision capabilities via a local Ollama vision model. Supports three modes: describe clipboard screenshot, capture fullscreen and describe, read saved image files. All images…
LocalEyes gives text-only LLMs in Claude Code (e.g., DeepSeek, CodeLlama) local vision via Ollama, enabling image description without cloud uploads. Setup takes two commands.
I built a tool to turn your Claude Code sessions into fine-tuning data for local models
A new open-source tool called claude_converter converts Claude Code session logs into fine-tuning datasets compatible with TRL/SFTTrainer, Axolotl, and LLaMA-Factory, enabling developers to repurpose real coding conversations for training local models.