DeepClaude – Claude Code agent loop with DeepSeek V4 Pro, 17x cheaper

176

aalattaran about 5 hours ago 80 commentsRead Article on github.com

DE version is available. Content is displayed in original English for accuracy.

⚡ Community Insights

Discussion Sentiment

76% Positive

Analyzed from 1603 words in the discussion.

Discussion (80 Comments)Read Original on HackerNews

aftbit•about 4 hours ago

    #!/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 $@

aaurelions•about 3 hours ago

It seems like any project that makes fun of Claude is bound to reach the top spot on Hacker News. Even if it’s just a project consisting of four lines of code.

btbuildem•about 2 hours ago

This in essence is what allows one to use any model with CC -- including local.

nadermx•about 3 hours ago

The AI wars have begun

stingraycharles•about 1 hour ago

This has been possible since the beginning.

vitaflo•about 4 hours ago

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...

2ndorderthought•about 4 hours ago

There probably isn't a point. Someone didn't understand something, didn't research it, so they 1 shotted their first thought and sent it to the front page of HN and all of their socials. It's the future bruh

croes•about 3 hours ago

From vibe coders for vibe coders

2ndorderthought•about 2 hours ago

I don't always copy paste vibe coded project readme mds into Claude code and ask them to rewrite it but when I do... actually that's all I do now because my goal in life is to make wealthy overvalued companies wealthier.

kordlessagain•43 minutes ago

Problem?

ttoinou•about 4 hours ago

I thought the tool format wasnt exactly the same ? So plugging any IA into claude code requires a conversion of format

selcuka•about 2 hours ago

DeepSeek has a dedicated Anthropic-compatible endpoint [1].

[1] https://api-docs.deepseek.com/guides/anthropic_api

ricardobeat•about 3 hours ago

Many of them expose “anthropic-compatible” APIs for this very purpose.

crooked-v•about 3 hours ago

I'm curious how well it actually works. I tried Deepseek with Hermes and Opencode and it seemed extremely bad about using some of the basic tools given, like the Hermes holographic memory tools, even with system prompt instructions strongly pointing them out.

justech•about 3 hours ago

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

wolttam•about 3 hours ago

I’m going to throw my harness in the ring: https://codeberg.org/mlow/lmcli

Aeroi•about 3 hours ago

agreed. OpenCode is a strong base, and with a couple modifications it can become a very effective harness. my sideproject mouse.dev I’ve been combining parts from OpenCode, Claude Code, and Hermes to build a cloud agent architecture that works well from mobile.

CharlesW•about 2 hours ago

> OpenCode is a strong base, and with a couple modifications it can become a very effective harness.

I personally didn't find it to be competitve with Claude Code as a harness. Can I ask how you modified it to perform better?

Aeroi•about 2 hours ago

I haven’t run formal evals but i improved the experience for my own needs and it feels noticeably better with these modifications.

-Claude-style subagents -an MCP layer for higher-level tools -Cursor-style control plane modes like Ask, Plan, Debug, and Build.

The MCP layer lets the harness use things like GitHub file/code read, PR creation, web search/fetch, structured user questions, plan-mode switching, user skills, and subagents.

So the improvement is mostly from better ui/ux orchestration and tool access. There's some things from hermes that are interesting as well.

Most of my focus has been on applying this stack to sandboxed cloud agents so you can properly code and work from mobile devices.

I can't definitively say that the stack is better or worse than Claude code, more just tuned for my use case I guess.

bakugo•about 2 hours ago

> I would first suggest looking into pi.dev

Looked into this one. Thought it was suspicious that it only had 7 open issues on github. Turns out they have a bot that auto-closes every single issue just because.

I honestly have no words.

LPisGood•about 1 hour ago

The idea is for it to he extremely minimal which strikes me as a very opinionated stance, and not opinions I agree with.

aaurelions•about 3 hours ago

Another very cost-effective option is Ollama Cloud. In a month of use, I only hit the 5-hour limit once, when I ran 8 agents simultaneously for 2 hours.

postatic•about 3 hours ago

definitely worth it - have both ollama cloud, opencode and hermes running to test them all out, working great so far.

nclin_•33 minutes ago

Is claude code the best coding harness? Anyone running evals on that?

ahmadyan•27 minutes ago

In my anecdotal experience, it is not. Same model, opus, works better in 3P harnesses such as Factory Droid or Amp.

Claude code, on the other hand, is the most subsidized one, both for consumers (through max subscription) and for enterprises (token discounts). It is also heavily optimized for cost, specially token caching and reduced thinking, at the expense of quality.

_345•about 4 hours ago

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

2ndorderthought•about 4 hours ago

A lot of people are having good experiences doing things like using opus for designing and using locally hosted qwen3.6 for implementation.

I could see a serious cost reduction story by using opus for design and deepseek for implementation.

Personally I would avoid anthropic entirely. But I get why people don't.

girvo•about 4 hours ago

Like me: that’s what I do. Either Opus 4.7 or GLM 5.1 for planning, write it out to a markdown file, then farm it out to Qwen 3.6 27B on my DGX Spark-alike using Pi. Works amusingly well all things considered.

brianjking•38 minutes ago

How are you interacting with GLM 5.1? Via the Claude Code harness? I really wish they'd release a fully multimodal model already.

2ndorderthought•about 4 hours ago

How is glm 5.1? I have t tried it yet but have been meaning too

aftbit•about 3 hours ago

What hardware are you using to power this?

chrsw•about 3 hours ago

I keep re-learning this lesson: I chug along with a lesser model then throw a problem at it that's too complex. Then I try different models until I give up and bring in Opus 4.6 to clean up.

brianwawok•about 3 hours ago

And I keep using Opus to like, make git commits. Really just need a smart router that is actually smart, vs having to micromanage model

willio58•about 3 hours ago

I don’t find this with sonnet at all. As long as I have a solid Claude.md and periodically review the output and enforce good code practices via basic CI gates I’ve rarely ever found myself having to switch to opus

2ndorderthought•about 2 hours ago

You might be surprised then at how good cheaper models solve your problems

dopeepsreaddocs•about 1 hour ago

Did... Did you just ask an AI to one-shot something that normally amounts to no more than setting two env variables?

alexdns•about 4 hours ago

obviously vibe coded ( co authored ) + the prices dont even match

2ndorderthought•about 4 hours ago

It's going to be real hard to find headlines that weren't vibe coded from here on out unfortunately.

SchemaLoad•about 3 hours ago

Unless I actually know the author I assume everything here is vibeslop and full of mistakes.

Maybe I need to switch to some news publication that actually does real research and writing still. Because public forums like this have been completely destroyed by LLMs.

cyanydeez•about 4 hours ago

welp, pack it it in boys, it was nice conceptualizing all you as real humans on the internet. I guess I'll just have to go touch grass if I want to feel parasocial.

dragontamer•about 3 hours ago

I mean, we have the tech and community to actually build in person meetups and sign CRT certificates, right?

If we touch grass in person and swap certificate requests, we can actually rebuild a trust network.

This is a pretty old problem with regards to clubs / secret societies and whatnot. And with certificates / PKI, our modern security tools have solved all the technical problems.

inciampati•about 2 hours ago

poorly vibe coded. machines can check details easily, use them.

vagab0nd•about 2 hours ago

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.

kordlessagain•38 minutes ago

CC has the ability to use Ollama as well, which includes the ability for Ollama to proxy to Ollama's cloud models. It's brilliant, and works with a single Ollama command that doesn't mess with CC at all (so you can run them at the same time).

If you are interested, I've built an agentic terminal that helps manage these types of things better: https://deepbluedynamics.com/hyperia

orliesaurus•about 4 hours ago

Is there a way to do this directly by using claudecode CLI (which I already have installed) and openrouter??

vitaflo•about 4 hours ago

Yes, Deepseek even documents how:

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

theanonymousone•about 4 hours ago

Yes, from Claude Code themselves: https://code.claude.com/docs/en/llm-gateway

jubilanti•about 3 hours ago

Here's a oneliner:

   ANTHROPIC_BASE_URL="https://openrouter.ai/api" ANTHROPIC_AUTH_TOKEN="$OPENROUTER_API_KEY" ANTHROPIC_DEFAULT_SONNET_MODEL="deepseek/deepseek-v4-flash" CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC=1 claude

gnat•about 4 hours ago

This repo's README explains how it works and you can do it yourself. claude looks for environment variables that say which API endpoint to talk to, which key to pass, which model name to use for haiku/sonnet/opus-level workloads, etc.

Lihh27•about 3 hours ago

the wrapper is basically env var glue. You’re still betting the whole loop on Anthropic's closed client.

game_the0ry•about 3 hours ago

Cost engineering [1] will be the next hot topic for AI.

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

deadbabe•about 2 hours ago

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.

fHr•about 1 hour ago

layer on layer on layer to refactor bunch of lines xD

2ndorderthought•about 4 hours ago

Oh shoot now the next CC upgrade will blow your subscription for doing this

esafak•about 4 hours ago

Why wouldn't you use something open source like OpenCode, which already support DSv4 and has more features than CC?

CharlesW•about 2 hours ago

Coding harnesses make a big difference, and OpenCode is notably less effective than Claude Code (1) in my experience, (2) with the models I've tried it on. (I've not yet tried it with DSv4.)

dlx•about 3 hours ago

As someone who does use other models with CC, I am curious about opencode, what extra features does it have that you find essential?

esafak•about 3 hours ago

I like being able to add a wide array of models, define perms for agents and subagents, turn MCPs on and off at will, and be able to fix bugs I find in it.

dlx•about 3 hours ago

fair enough...any drawbacks that you've found?

ttoinou•about 4 hours ago

More features than CC ?

Also opencode tracks you by default. Its not safe. Every first prompt you send is routed through their servers, logged and they can use your data however they want

sedawkgrep•about 3 hours ago

I thought this was debunked awhile ago. ?

esafak•about 3 hours ago

I could not find any evidence of prompt logging. The code is open; can you point me to it?

morpheos137•about 3 hours ago

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.

hgyyy•about 3 hours ago

I think OAI and Anthropic will be ok for a year or two. But after that If they still continue to earn revenues from selling tokens to firms/software engineers they will be in serious trouble.

The American firms are not demonstrating escape velocity and as long as china offers something somewhat comparable and offers it at a very low price to compensate for any difference in quality, they will not be generating enough in cash flows to finance reinvestment. I highly doubt they’ll be able to continue raising external financing for numerous periods from here on out - they gotta start showing strong financials and that they are running away from the open source models.

LeFantome•about 1 hour ago

The performance gap will likely close as Chinese hardware improves. This is happening very rapidly.

Already DeepSeek v4 is being hosted on Huawei Ascend 950. What do you think those cost relative to NVIDIA gear?

morpheos137•about 1 hour ago

I wouldnt put it past the US gov to ban foreign models. they tried to ban tiktok. what is being demosrrated here is silicon valley can not withstand a competitive market.

LeFantome•about 1 hour ago

Good luck banning Open Source models.

Not only that but other countries are very unlikely to follow suit, so it is just a straight-up productivity tax on the US.

bwfan123•24 minutes ago

> anthropic messed up big time harness works with any muh commodity LLM

that surprised me too. The intelligence is at the client, and by making that open, anthropic has commoditized the coding agent.