musistudio/claude-code-router
One local control plane for every AI agent: route across models, fuse new capabilities, orchestrate tools, and stay fully in control.
Recommended between 2025-09-06 and 2026-02-12. Last pushed 2026-10-10.
▲ 9 recommend · ▼ 0 criticisms
What hackers say
“I use it since some weeks with opensource models and it works pretty well.”
— blancm, 2025-11-22 · strong recommendation · original comment on Hacker News ↗
show original comment
Hello, about Claude Code where only Anthoripic models are supported, in reality you can use Claude Code router ( https://github.com/musistudio/claude-code-router ) to use other models in Claude Code. I use it since some weeks with opensource models and it works pretty well. You can even use "free" models from openrouter
“Although if you want an Actually Good Experience I recommend using Claude Code Router”
— andai, 2025-11-08 · strong recommendation · original comment on Hacker News ↗
show original comment
Ask and you shall receive! https://docs.z.ai/devpack/tool/claude tldr "env": { "ANTHROPIC_AUTH_TOKEN": "your_zai_api_key", "ANTHROPIC_BASE_URL": "https://api.z.ai/api/anthropic" } Although if you want an Actually Good Experience I recommend using Claude Code Router https://github.com/musistudio/claude-code-router because it allows you to intercept the requests and forward them to other models. (e.g. GLM doesn't seem to support search or images, so I use Gemini's free tier for that.) (CCR just launches Claude with the base url set to a local proxy. The more adventurous reader can also set up his own proxy... :)
“anything with an open ai compatible endpoint can have claude code router put in front of it afaik https://github.com/musistudio/claude-code-router”
— claythearc, 2026-02-12 · original comment on Hacker News ↗
“Claude Code Router or ccr can connect to OpenRouter.”
— sathish316, 2026-02-05 · original comment on Hacker News ↗
show original comment
Claude Code Router or ccr can connect to OpenRouter. When your quota runs out, it’s a much better speed vs quality vs cost tradeoff compared to running Qwen3 locally - https://github.com/musistudio/claude-code-router
“You could look at something like https://github.com/musistudio/claude-code-router if at some point you're interested in going down that path.”
— river_otter, 2026-01-12 · original comment on Hacker News ↗
show original comment
makes sense. You could look at something like https://github.com/musistudio/claude-code-router if at some point you're interested in going down that path. I've been using gpt-oss-20b which would fit on your GPU and I've found useful for basic tasks like recipe creation and agentic tool usage (I use it with Notion MCP tools)
“They don't have to pivot, since it already exists: Claude Code Router [1].”
— alwillis, 2025-11-28 · original comment on Hacker News ↗
show original comment
> Currently Claude Code is the best, but I don't think Anthropic would pivot it into what I described. They don't have to pivot, since it already exists: Claude Code Router [1]. [1]: https://github.com/musistudio/claude-code-router
“Anthropic's API is not your only choice for a Claude Code workflow.”
— anonym29, 2025-11-23 · original comment on Hacker News ↗
show original comment
https://github.com/musistudio/claude-code-router Anthropic's API is not your only choice for a Claude Code workflow.
“Have you tried Claude Code Router with GLM 4.6?”
— DeathArrow, 2025-11-08 · original comment on Hacker News ↗
show original comment
Have you tried Claude Code Router with GLM 4.6? https://github.com/musistudio/claude-code-router
“you can use any model with Claude code thanks to https://github.com/musistudio/claude-code-router”
— Szpadel, 2025-09-06 · original comment on Hacker News ↗
show original comment
you can use any model with Claude code thanks to https://github.com/musistudio/claude-code-router but in my testing other models do not work well, looks like prompts are either very optimized for Claude, or other models are just not great yet with such agentic environment I was especially disappointed with grok code. it is very fast as advertised but in generating spaces and new lines in function calling until it hits max tokens. I wonder if that isn't why it gets so much tokens on openrouter. gpt-5 just wasn't using the tools very well I didn't tested glm yet, but with current anthropic subscription value, alternative would need to be very cheap if you consider daily use edit: I notice…
Badge for your README
[](https://hackerrepos.org/repo/musistudio/claude-code-router)