23 comments

  • oceanplexian 2 days ago 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 2 days ago ago

      And they reference that announcement and related information in the second line.

      • gcr 2 days ago 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.

  • d4rkp4ttern a day ago ago

    As others said this was possible for months already with llama-cop’s support for Anthropic messages API. You just need to set the ANTHROPIC_BASE_URL. The specific llama-server settings/flags were a pain to figure out and required some hunting, so I collected them in this guide to using CC with local models:

    https://github.com/pchalasani/claude-code-tools/blob/main/do...

    One tricky thing that took me a whole day to figure out is that using Claude Code in this setup was causing total network failures due to telemetry pings, so I had to set this env var to 1: CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC

  • eli 2 days ago 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 2 days ago 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 days ago 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

        • eli a day ago ago

          Some unsolicited advice: Streaming support is tricky. I'd strip the streaming out when you proxy until everything else is solid.

          • kristopolous a day ago ago

            Cool. Sounds good. Thanks. I'll do it.

            This will be a bit challenging I'm sure but I agree, litellm and friends do too many things and take too long to get simple asks from

            I've been pitching this suite I'm building as "GNU coreutils for the LLM era"

            It's not sticking and nobody is hyped by it.

            I don't know if I should keep going or if this is my same old pattern cropping up again of things I really really like but just kinda me

      • eli a day ago ago

        I've been hacking on this one for a few months now and it works for me https://github.com/elidickinson/claude-code-mux Been optimizing for routing to different models within one session so maybe overkill.

        But I'm surprised litellm (and its wrappers) don't work for you and I wonder if there's something wrong with your provider or model. Which model were you using?

  • dsrtslnd23 2 days ago ago

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

    • thtmnisamnstr 2 days ago 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.

      • 3836293648 a day ago ago

        But this also means tiny context windows. You can't fit gpt-oss:20b + more than a tiny file + instructions into 24GB

        • blizdiddy 9 hours ago ago

          Gpt-oss is natively 4-bit, so you kinda can

    • ryandrake 2 days ago 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.

      • storystarling a day ago ago

        I tried to build a similar local stack recently to save on API costs. In practice I found the hardware savings are a bit of a mirage for coding workflows. The local models hallucinate just enough that you end up spending more in lost time debugging than you would have paid for Sonnet or Opus to get it right the first time.

  • horacemorace 2 days ago 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 days ago ago

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

    • d4rkp4ttern a day ago ago

      Curious what llama-server flags you used. On my M1 Max 64GB MacBook I tried it in Claude Code (which has a 25K system message) and I get 3 tps.

      But with Qwen3-30B-A3B I get 20 tps in CC.

  • dosinga 2 days ago 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 2 days ago ago

    Does this UI work with Open Code?

  • mchiang 2 days ago ago

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

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