LM Warden

Your coding agent, on your own GPUs.

LM Warden speaks the three protocols coding agents use: OpenAI Chat Completions, the Anthropic Messages API and the OpenAI Responses API. So Claude Code, Codex CLI, OpenCode, Aider, Cline, Cursor and the rest connect with a base URL and a key, and their requests show up per key, per session, with the phase each one is in.

You don’t write the config by hand. In the console, Connect picks your client, your model and your key and writes the files to paste. Each page below shows the same files with placeholders, what works, and what we saw when we ran it.

ClientProtocolSupportRun live
Claude CodeAnthropic MessagesFull support2026-10-04
Anthropic SDKAnthropic MessagesFull support2026-10-04
OpenCodeOpenAI Chat CompletionsLocal models only2026-10-04
AiderOpenAI Chat CompletionsLocal models only2026-10-04
Grok CLIOpenAI Chat CompletionsLocal models only2026-10-04
OpenAI SDKOpenAI Chat CompletionsLocal models only2026-10-04
ContinueOpenAI Chat CompletionsConfigured from its docsdocs only
ClineOpenAI Chat CompletionsConfigured from its docsdocs only
CursorOpenAI Chat CompletionsConfigured from its docsdocs only
Codex CLIOpenAI ResponsesLocal models only2026-10-05

Missing a client? Ask in GitHub Discussions.