76 comments

[ 5.2 ms ] story [ 82.3 ms ] thread
Is there a way to do this directly by using claudecode CLI (which I already have installed) and openrouter??
(comment deleted)
(comment deleted)
Why wouldn't you use something open source like OpenCode, which already support DSv4 and has more features than CC?
If you're okay with sonnet level performance, this sounds like a straight upgrade. But I find that sonnet messes up too much, that it ends up not being worth cost optimizing down to using it or another sonnet-level model. Glad to have this as an option though
Oh shoot now the next CC upgrade will blow your subscription for doing this
obviously vibe coded ( co authored ) + the prices dont even match
I'm not exactly sure what the point of this is. Deepseek already has instructions to use its API with many CLI's including Claude Code directly:

https://api-docs.deepseek.com/quick_start/agent_integrations...

Also Claude Code is one of the worse CLI, the only good thing is that it's the default for Claude.

I don't see why anyone would want to use it for any other model than Claude instead of OpenCode or Pi.

    #!/bin/sh
    export ANTHROPIC_BASE_URL=https://api.deepseek.com/anthropic
    export ANTHROPIC_AUTH_TOKEN=sk-secret
    export ANTHROPIC_MODEL=deepseek-v4-flash
    export CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC=1
    exec claude $@
Wonder if there's a way to launch the desktop Claude app like that, especially on Windows, not just the Claude Code TUI/CLI. Might not be possible and you'd just have to use --remote as a workaround.
I'm using this

    deepseek() {
      unset ANTHROPIC_AUTH_TOKEN
      local -x ANTHROPIC_BASE_URL="https://api.deepseek.com/anthropic"
      local -x ANTHROPIC_AUTH_TOKEN="${DEEPSEEK_API_KEY}"
      local -x ANTHROPIC_MODEL="deepseek-v4-pro"
      local -x ANTHROPIC_SMALL_FAST_MODEL="deepseek-v4-flash"
      local -x API_TIMEOUT_MS=600000
      local -x CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC=1
      TMUX= command claude "$@"
    }
You mean `exec claude "$@"`
anthropic messed up big time harness works with any muh commodity LLM, meanwhile VCs were duped on the myth of FOOM AGI, probably not a cooincidence Anthropic is enmeshed with the scifi fan fic forum known as lesswrong. The world wants useful tools. The bay area bubble in contrast thrives on Mythos.
If you're looking for Claude Code alternatives, I would first suggest looking into pi.dev or opencode for your harness. And then for models, you can choose from OpenCode Go (IMO most cost effect at this moment), OpenRouter, or direct from DeepSeek. Better if you go the Kimi route IMO and just buy a subscription from kimi.com
(comment deleted)
the wrapper is basically env var glue. You’re still betting the whole loop on Anthropic's closed client.
Cost engineering [1] will be the next hot topic for AI.

[1] A fancier way of saying "reducing cost."

(comment deleted)
I had a call with our CTO and we are pivoting away from Claude Code to DeepClaude because the cost savings are too substantial to ignore.
This has become a problem for me. I like trying new things. But I also know that in about a week, there's going to be a better/cheaper setup. And a week after that. And ideally I'd like to get some coding done when I'm not tinkering with the tools.

So I think I'll stay with CC for now.

layer on layer on layer to refactor bunch of lines xD
Did... Did you just ask an AI to one-shot something that normally amounts to no more than setting two env variables?
Is claude code the best coding harness? Anyone running evals on that?
I always wonder why everybody is so hyped about the cli harnesses. I am quite happy with Cursor (even though I used to do coding with tmux+vim in the old days). One of the features I like very much is that I can switch between different models without having to have an account with every model provider.

The main thing I am missing is having it on all my devices (like using it via the smartphone). They have a solution for that too (the cloud version), but that is too expensive IMHO. The last time I checked out Claude Code, it was too expensive for my taste as well (burning through tokens like there was no tomorrow).

Is there some way to make claude/codex beep when it finishes a task.
I just spent half my day getting CUDA and LLAMA to work with my 5070TI.

I was able to use it in agent mode with Roo, I stopped after having it write out a plan, but I'll continue when I have more time.

Deepseek feels less likely to do a straight up rug pull since you can self host with enough money, but I'm still more excited about local solutions.

Usually I just need grunt work done. I'm not solving difficult problems.