Show HN: First Claude Code client for Ollama local models

32 points by SerafimKorablev 8 hours ago

Just to clarify the background a bit. This project wasn’t planned as a big standalone release at first. On January 16, Ollama added support for an Anthropic-compatible API, and I was curious how far this could be pushed in practice. I decided to try plugging local Ollama models directly into a Claude Code-style workflow and see if it would actually work end to end.

Here is the release note from Ollama that made this possible: https://ollama.com/blog/claude

Technically, what I do is pretty straightforward:

- Detect which local models are available in Ollama.

- When internet access is unavailable, the client automatically switches to Ollama-backed local models instead of remote ones.

- From the user’s perspective, it is the same Claude Code flow, just backed by local inference.

In practice, the best-performing model so far has been qwen3-coder:30b. I also tested glm-4.7-flash, which was released very recently, but it struggles with reliably following tool-calling instructions, so it is not usable for this workflow yet.

oceanplexian - 4 hours ago

The Anthropic API was already supported by llama.cpp (The project Ollama ripped off and typically lags in features by 3-6 months), which already works perfectly fine with Claude Code by setting a simple environment variable.

xd1936 - 3 hours ago

And they reference that announcement and related information in the second line.
- gcr - 2 hours ago
  
  Which announcement are you looking at? I see no references to llama-cpp in either Ollama's blog post or this project's github page.

horacemorace - 2 hours ago

I was trying to get Claude code to work with llama.cpp but could never figure out anything functional. It always insisted on a phone home login for first time setup. In cline I’m getting better results with glm-4.7-flash than with qwen3-coder:30b

g4cg54g54 - 2 hours ago

~/.claude.json with {"hasCompletedOnboarding":true} is the key, then ANTHROPIC_BASE_URL and ANTHROPIC_AUTH_TOKEN work as expected

dsrtslnd23 - 2 hours ago

What hardware are you running the 30b model on? I guess it needs at least 24GB VRAM for decent inference speeds.

thtmnisamnstr - 6 minutes ago

The general rule to follow is that you need as much VRAM as the model size. 30b models are usually around 19GB. So, most likely a GPU with 24GB of VRAM.
ryandrake - an hour ago

I'd like to know this, too. I'm just getting started getting my feet wet with ollama and local models using just CPU, and it's obviously terribly slow (even 24 cores, 128GB DRAM. It's hard to gauge how much GPU money I'd need to plonk down to get acceptable performance for coding workflows.

eli - 4 hours ago

There are already various proxies to translate between OpenAI-style models (local or otherwise) and an Anthropic endpoint that Claude Code can talk to. Is the advantage here just one less piece of infrastructure to worry about?

g4cg54g54 - 3 hours ago

siderailing here - but got one that _actually_ works?
in particular i´d like to call claude-models - in openai-schema hosted by a reseller - with some proxy that offers anthropic format to my claude --- but it seems like nothing gets to fully line things up (double-translated tool names for example)
reseller is abacus.ai - tried BerriAI/litellm, musistudio/claude-code-router, ziozzang/claude2openai-proxy, 1rgs/claude-code-proxy, fuergaosi233/claude-code-proxy,
- kristopolous - 2 hours ago
  What probably needs to exist is something like `llsed`.
  The invocation would be like this
  llsed --host 0.0.0.0 --port 8080 --map_file claude_to_openai.json --server https://openrouter.ai/api
  Where the json has something like
  { tag: ... from: ..., to: ..., params: ..., pre: ..., post: ...}
  So if one call is two, you can call multiple in the pre or post or rearrange things accordingly.
  This sounds like the proper separation of concerns here... probably
  The pre/post should probably be json-rpc that get lazy loaded.
  Writing that now. Let's do this: https://github.com/day50-dev/llsed

dosinga - 4 hours ago

this is cool. not sure it is the first claude code style coding agent that runs against Ollama models though. goose, opencode and others have been able to do that a while no?

d0100 - 3 hours ago

Does this UI work with Open Code?

smissingham - 2 hours ago

[dead]

mchiang - 4 hours ago

hey, thanks for sharing. I had to go to the Twitter feed to find the GitHub link:

https://github.com/21st-dev/1code

dang - 3 hours ago

Thanks for catching that. I've changed the URL at the top to that from https://twitter.com/serafimcloud/status/2014266928853110862 now.