DeepClaude – Claude Code agent loop with DeepSeek V4 Pro

https://github.com/aattaran/deepclaude

by alattaran • 3 months ago

678 281 3 months ago

github.com

orliesaurus• 3 months ago

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

theanonymousone• 3 months ago

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

gnat• 3 months 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.

vitaflo2• 3 months ago

Yes, Deepseek even documents how:

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

jubilanti• 3 months 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

mobeigi• 3 months ago

Been using Claude as a harness to OpenRouter for a while now. It's a nice setup if you don't mind API based billing.

esafak5• 3 months ago

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

ttoinou4• 3 months 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

esafak5• 3 months ago

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

sedawkgrep• 3 months ago

I thought this was debunked awhile ago. ?

dlx2• 3 months 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?

esafak5• 3 months 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.

CharlesW2• 3 months 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.)

DeathArrow5• 3 months ago

If using something open source, I'd say Forge Code has better results than Open Code, at least according to Terminal Bench.

_3452• 3 months 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

2ndorderthought10• 3 months 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.

girvo7• 3 months 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.

chrsw• 3 months 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• 3 months 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

energy1232• 3 months ago

It's not even that much cheaper, GPT 5.5 is about 2x more expensive per task than Deepseek v4 Pro when you adjust for less token usage, according to Artificial Analysis. Doesn't seem worth it to me.

willio58• 3 months 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

2ndorderthought10• 3 months ago

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

maxdo2• 3 months ago

This is the problem: you need the best model, not just a good one, for: - Good architecture, which requires reading specs, code, etc. reads like: lots of tokens in/out - Bug fixing — same, plus logs, e.g. datadog

Once you've found the path, patches are trivial and the savings are tiny unless you're doing refactoring/cleanup.

testing gets more and more complicated. Take a look at opencode go, and you see this:

Includes GLM-5.1, GLM-5, Kimi K2.5, Kimi K2.6, MiMo-V2-Pro, MiMo-V2-Omni, MiMo->V2.5-Pro, MiMo-V2.5, Qwen3.5 Plus, Qwen3.6 Plus, MiniMax M2.5, MiniMax M2.7, >DeepSeek V4 Pro, and DeepSeek V4 Flash

and now on your own with bugs, all of these models can produce at scale. Am i missing anything in this picture. What is the real use of cheaper models?

JSR_FDED• 3 months ago

I'd argue that you need the model that's good enough, not the best.

Culonavirus• 3 months ago

We're not yet at a point of saturation when all the frontier models would be of somewhat comparable "intelligence" and we could decide which to use based on other factors (speed, effective context window etc.), so I honestly don't see why would you (as a company or an employee) not use the best available model with the highest (or at least second highest) thinking effort. The fees are not exactly cheap, but not that expensive either.

nyssos• 3 months ago

Agreed that we're not at saturation, but we don't have a canonical "best" either. For example ChatGPT 5.5 + Codex is, in my experience, vastly superior to Opus 4.7 + Claude Code at sufficiently well-specified Haskell, but equally vastly inferior at correctly inferring my intent. Deepseek may well have its own niche, though I haven't used it enough to guess what it might be.

mohsen1• 3 months ago

This has been my experience working on tsz.dev. Only Opus 4.7 and GPT 5.5 can really be productive for the remaining test cases.

2ndorderthought10• 3 months ago

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

alexdns• 3 months ago

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

2ndorderthought10• 3 months ago

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

cyanydeez2• 3 months 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.

SchemaLoad• 3 months 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.

inciampati• 3 months ago

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

vitaflo2• 3 months 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...

2ndorderthought10• 3 months 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

georgeburdell• 3 months ago

I embrace it at this point. It ends all the shilling of vibe coded tools at work that I have endured over the past year. Everyone can now make their own tools with zero obligation to coordinate beyond shared hardware resources

altmanaltman2• 3 months ago

To be fair, HN sent it to the front page, not the user. The rest I agree.

dev_hugepages• 3 months ago

And now, because we all upvoted and commented on it, the vibe coded slop of the new user is on the front page now.

ttoinou4• 3 months ago

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

ricardobeat2• 3 months ago

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

selcuka• 3 months ago

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

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

faangguyindia2• 3 months ago

qwen also offers openai compatible endpoint.

crooked-v• 3 months 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.

_3452• 3 months ago

I've been experimenting with Hermes, I'm convinced hermes is also just bad. Like as a harness it has got to be doing something to lobotomize these models- Even GPT-5.4 performs badly in Hermes vs just using it in Codex.

rurban• 3 months ago

I'm working with Deepseek for a few weeks with opencode, and there are no desires left. claude remote maybe, but opencode web is good enough.

croes• 3 months ago

From vibe coders for vibe coders

2ndorderthought10• 3 months 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.

kordlessagain2• 3 months ago

Problem?

ex-aws-dude• 3 months ago

Its vibes all the way down

varenc2• 3 months ago

The readme absolutely buries the features that are actually non-trivial: It runs a proxy to switch models mid-session, and does combined cost tracking between Anthropic and other models you might be using. The LLM that wrote the readme never updated the general project description to highlight these features.

Also the author checked in their advertising plan: https://github.com/aattaran/deepclaude/commit/a90a399682defc...

TacticalCoder• 3 months ago

It's really getting a lot of upvotes so it's nearly as if people were feeling locked-in and wanted a way out but...

Why would you keep using CC CLI if you want to use the much cheaper DeepSeek v4 models (Flash and Pro): isn't it the opportunity to kiss CC CLI goodbye and use something not controlled by Anthropic?

Anyone here successfully moved from CC CLI to a fully open-source project? I'm asking this as a Claude Code CLI (Sonnet/Opus) user. My "stack" is all open-source: from Linux to Emacs to what-have-you. I'd rather also have open-weight models and a fully open-source (not controlled by a single company) AI CLI.

Any suggestion for something that works well? (by "well" I mean "as well as Claude Code CLI", which is not a panacea so my bar ain't the end of the world either).

KronisLV2• 3 months ago

CC can use the Flash model for sub-agents and other tasks but keep using the Pro model for the main thread and thinking there. It also has a decent permission system and commands that people are quite used to.

Personally I’d say that the closest alternative you’d get is OpenCode.

They are TUI focused and also do have a web/desktop version, though that’s not quite as good as Claude’s Desktop app (and Claude Code functionality within it) yet. The TUI itself is solid though and they support a lot of different providers and models (/connect and /models).

For GUI driven stuff, I’ve personally had good experiences with KiloCode (in Visual Studio Code, personally I also liked RooCode of which KiloCode is a fork, but that stopped development) or just using the Zed editor with their built in agent.

eloisant3• 3 months ago

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.

aftbit3• 3 months 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 $@

nadermx• 3 months ago

The AI wars have begun

stingraycharles• 3 months ago

This has been possible since the beginning.

heisenbit• 3 months ago

And they are enticing human agents to further their agendas using techniques learned from the white mice.

aaurelions2• 3 months 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.

oblio• 3 months ago

You're just mean. I count 6 lines of code!

btbuildem• 3 months ago

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

neutrinobro• 3 months ago

I know. I'm struggling to understand how this is a github repo/HN article. I've been using claude-code with a llama.cpp server and a dummy API key, and all that is required is to define 2 environmental variables to point claude at the local endpoint. Am I missing something?

rapind2• 3 months ago

ANTHROPIC_MODEL=deepseek-v4-pro[1m] ANTHROPIC_SUBAGENT_MODEL=deepseek-v4-flash

This is what I’ve been using for non-confidential projects for about a week now (soon after v4 came out). I honestly can’t tell the difference, but I’m not doing anything crazy with it either.

Worth noting that I don’t think DeepSeek‘s API lets you opt out of training. Once this is up on other providers though… (OpenRouter is just proxying to DeepSeek atm)

tariky• 3 months ago

I wanted to try this. To bring back opus and sonnet do I just reset those env's?

maxgashkov• 3 months ago

As of now, OpenRouter offers multiple providers for DeepSeek with ZDR (not sure if they respect it but still).

lhl• 3 months ago

For those that don't want their data trained on, OpenRouter allows you to have account-wide or per-request routing with either provider.data_collection: "deny" or zdr: true (zero data retention).

Also, you can use HuggingFace Inference for DeepSeek V4 or Kimi K2.6, both of which work quite well and route through providers that you can enable/disable (like Together AI, DeepInfra, etc) - you'll have to check their policies but I think most of those commercial inference providers claim to not train on your data either.

ricardobeat2• 3 months ago

ANTHROPIC_SUBAGENT_MODEL is not a valid setting, should be CLAUDE_CODE_SUBAGENT_MODEL.

faangguyindia2• 3 months ago

those who use deepseek v4, what level of output you get? Codex 5.3 or GPT 5.4?

is flash version on level of gpt 5.4 mini

adonese2• 3 months ago

I tried it on a non trivial, but also well documented and self contained task. It did amazingly well. I used deepseek v4 pro via deepseek platform. The model is very fast and also it is super cheap. I burned only 0.06 USD (I reckon how the same task would have cost me had I used e.g., amp).

PS. mentioning amp because i used to use it and I pay directly for token. I topped up 5 usd so I will be going to use it and see how far can it take me. But my impression so far is even when model subsidization is done, those open source models are quite viable alternatives.

63stack2• 3 months ago

It's close to Opus 4.5 for me

spirit233• 3 months ago

So I created https://getaivo.dev, one can use model in the coding agent directly. Just `aivo claude -m deepseek-v4-pro`

Tanxsinxlnx3• 3 months ago

does it support aws bedrock provider support,does i can use any model in this

varenc2• 3 months ago

The more interesting part of deepclaude is the local proxy it runs to switch models mid-session and do combined cost tracking. Though these features seem quite buried in the LLM-generated readme. Looking at the history, it appears they were added later, and the readme wasn't restructured to highlight this.

Also, the author checked in their apparently effective social media advertising plan: https://github.com/aattaran/deepclaude/commit/a90a399682defc... (which seems to be working)

yard20102• 3 months ago

How come such slop is allowed here, what value do these vibe coded zero shot "projects" add? Why not just post the prompt?

niobe• 3 months ago

thanks, that was super easy.

I have been wanting to try CC with different models since Opus went downhill last month..

What limitations or issues have you noticed when using DeepSeek with Claude Code if any?

port11• 3 months ago

DeepClaude doesn't support MCP tool use; does your solution work with MCP tools such as Serena?

KronisLV2• 3 months ago

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.

guluarte• 3 months ago

I'm using this

    deepseek() {
      unset ANTHROPIC_AUTH_TOKEN
      local -x ANTHROPIC_BASE_URL="https://api.deepseek.com/anthropic"
      local -x ANTHROPIC_AUTH_TOKEN="${DEEPSEEK_API_KEY}"
      local -x ANTHROPIC_MODEL="deepseek-v4-pro"
      local -x ANTHROPIC_SMALL_FAST_MODEL="deepseek-v4-flash"
      local -x API_TIMEOUT_MS=600000
      local -x CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC=1
      TMUX= command claude "$@"
    }

klaussilveira• 3 months ago

Damn, we need something like this for Ollama.

bhelkey• 3 months ago

Ollama works with Claude Code:

$ ollama launch claude --model qwen3.5 [1]

[1] https://docs.ollama.com/integrations/claude-code

thatxliner• 3 months ago

how do subagents work?

Daunk• 3 months ago

You mean `exec claude "$@"`

morpheos1373• 3 months 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• 3 months 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.

morpheos1373• 3 months 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.

LeFantome2• 3 months 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?

bwfan123• 3 months 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.

ManuelSuarez• 3 months ago

I mean, it's not like claude code is the most impressive agent of the pack.

justech• 3 months 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

aaurelions2• 3 months 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• 3 months ago

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

kopirgan• 3 months ago

On which tier?

tomw1808• 3 months ago

for me its unbearably slow - especially with deepseek v4 pro. Is that just myself? I literally signed up and canceled again, because for one prompt I needed around 5 minutes to get 600 tokens back (via ollama launch claude --mode ...)

Aeroi4• 3 months 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.

CharlesW2• 3 months 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?

adobrawy• 3 months ago

I'm a Claude Code Web fan and a rather heavy user. So I was interested in your product. However, I couldn't find an answer on the website. What parts did you find so good that you ported them?

ryanlitalien2• 3 months ago

Kudos! Cool idea, I'm on the same path you are, yet you're just one step ahead. For mouse.dev, what are you using for the cloud agent sandbox piece? I haven't moved my agents to the cloud yet (for on the go mobile enablement). Would Islo be a competitor to mouse?

https://islo.dev/

https://www.incredibuild.com/blog/why-we-built-islo-ai-codin...

wolttam2• 3 months ago

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

taocoyote• 3 months ago

Looks interesting. Does it offer anything special that pi.dev or opencode does not?

bakugo• 3 months 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• 3 months ago

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

__cayenne__• 3 months ago

The maintainer, Mario, sometimes declares the repo is on an “issue holiday” where issues are auto closed. This particular holiday is because there is a big refactor coming up. In non holiday periods issues can be reported as normal.

justinhj• 3 months ago

It's a very interesting project. Many popular open source projects are inundated with poor quality issues and prs, hence the defences they are starting to erect.

mikeocool2• 3 months ago

Their process is outlined here: https://github.com/badlogic/pi-mono/blob/main/CONTRIBUTING.m...

Maintainers review auto-closed issues daily and reopen worthwhile ones. Issues that do not meet the quality bar below will not be reopened or receive a reply.

Seems like not an unreasonable way to deal with the problem of large numbers of low quality issues being submitted.

skeledrew2• 3 months ago

They have a pretty decent explanation.

https://github.com/badlogic/pi-mono/blob/main/CONTRIBUTING.m...

DeathArrow5• 3 months ago

If you're looking for Claude Code alternatives, I would first suggest looking into pi.dev or opencode for your harness.

While those are nice, Claude Code has the largest amount of plugins and skills I want to use.

wizhi• 3 months ago

Aren't skills just literal plaintext files? Why not just copy them?

cpursley7• 3 months ago

How does the kimi subscription compare to Codex and Claude Code in terms of how much mileage you get for the pricing? I mean, I see the prices but not sure how usage that buys.

taytus• 3 months ago

Kimi feels almost limitless. I have the $40/month plan and I've never ever remotely close to hitting the limit. Using opus as the orchestrator.

mgoetzke• 3 months ago

I liked pi.dev but why is registering endpoints and models not as simple as possible ? Or am i missing something ? I always have to fiddle with the config file.

miroljub4• 3 months ago

Editing config files is not necessary. Just do /login from your session, choose your provider, and there you go.

Lihh27• 3 months ago

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

game_the0ry• 3 months ago

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

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

deadbabe• 3 months 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.

vagab0nd• 3 months 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.

kordlessagain2• 3 months 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

fHr• 3 months ago

layer on layer on layer to refactor bunch of lines xD

dopeepsreaddocs• 3 months ago

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

nclin_• 3 months ago

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

ahmadyan• 3 months 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.

viking123• 3 months ago

codex is way more subsidized currently, much more generous limits even for 20 dollars a month

DeathArrow5• 3 months ago

Terminal Bench is testing agent harness.

The best two are Codex and Forge Code.

However I am using plugins and skills that are only compatible with Claude Code or work best with Claude Code.

So, for me, Claude Code with plugins like claude-meme, Context Mode, Superpowers and Get Shit Done is better than other tools.

I think everyone should test multiple models and multiple agent harness for his specific needs, codebase and way of working.

jedisct12• 3 months ago

Ironically, there are plenty of evals showing that it’s not actually that great. Even with Anthropic models, other harnesses are more efficient, both in terms of the number of problems solved and token usage.

Significant regressions also seem to be introduced from time to time after releases.

The UX is great, and if you need a kitchen sink packed with tons of features, even though you’ll probably only end up using a fraction of them, it’s fine.

But if you want something that performs well, you’re better off using something like Opencode or Swival.dev

arendtio• 3 months ago

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).

dukeofdoom• 3 months ago

Is there some way to make claude/codex beep when it finishes a task.

999900000999• 3 months ago

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.

langitbiru• 3 months ago

I'm wondering why DeepSeek didn't create an AI coding agent like Kimi Code.

sourcecodeplz• 3 months ago

Think it is because they focus on what they know best. Coding a LLM harness is nothing spectacular.

dbeley• 3 months ago

Honestly with the likes of Opencode / pi / hermes I don't really find the "Claude Code agent loop" part particularly interesting.

The edge Anthropic has on others lies on its models performance. CLI tooling (and obviously pricing) is definitely not better than others.

danny_codes• 3 months ago

Except the model isn't particularly better anymore, as compared to the newest wave of FOSS models

portsentinel• 3 months ago

I am now thinking how far can agentic AI can go how far we can achieve

triyambakam• 3 months ago

And if I don't care about cost, what about actual performance?

sowild_fun• 3 months ago

Using a bunch of CLIs to work with DeepSeek V4, I've found that Langcli is the best fit for DeepSeek V4. For programming tasks, the cache hit rate is above 95%.

Not only can it seamlessly and dynamically switch between DeepSeek V4 Flash, V4 Pro, and other mainstream models within the same context, but it is also 100% compatible with Claude Code.

sfewfweg• 3 months ago

Langcli + deepseek v4 is very good

TheServitor• 3 months ago

It's surprisingly easy to hit $200 worth of tokens even at ~$1/M token though. No matter how many times I do the math the coding plans are the better value.

ojr• 3 months ago

I don't think it surprisingly easy at all unless you are running multiple background tasks overnight, I think Gemini will eventually be the default agentic coding agent in the future when it comes to price and efficiency because its backed by sound money.

I don't use the Claude Code harness, grep instead of using a combination of vector search is super expensive and not sure how their read file implementation is. I built my own harness for example that restrict reads and writes in a token efficient manner. Building your own harness will always be the cheapest option in the long run.

My own harness, minimalistic GUI gets the job done nothing too fancy https://slidebits.com/isogen

DeathArrow5• 3 months ago

You don't need Deep Claude. Claude Code is working with any model that exposes an endpoint for an Anthropic compatible API.

I am using Claude Code with GLM 5.1, MiniMax M2.7, Kimi K2.6 and Xiaomi MiMo V2.5 Pro.

jay1996523• 3 months ago

Claude code can already use the DeepSeek API, so what are the advantages of this tool?

lukaslalinsky• 3 months ago

I've been using DeepSeek v4 pro as an alternative to Claude models and for the first time I can see it as a real replacement. With the other Chinese models, I was missing something, but DeepSeek seems good enough for the kind of development I want to do.

Copenjin• 3 months ago

I wonder if openrouter will replicate that 120x caching, I suppose they will?

isege• 3 months ago

Claude Code is the best autonomous coding agent.

If you look at the terminal-bench@2.0 leaderboard, you'll quickly see it's actually one of the weakest agentic harnesses. Anthropic's own models score lower with Claude Code than with virtually any other harness.

So it's quite the opposite. Claude Code is arguably the worst harness to run models with.

DaanDL• 3 months ago

Okay, but not all results on there are valid, ForgeCode for instance has been cheating in the past:

https://debugml.github.io/cheating-agents/#sneaking-the-answ...

cpursley7• 3 months ago

Those benches are completely and totally meaningless when it comes down to real world work tasks, and everyone knows it.

andxor• 3 months ago

Then the benchmarks are wrong.

l5870uoo9y• 3 months ago

DeepSeek V4 Pro scores 96.4% on LiveCodeBench and costs $0.87/M output tokens.

Yes and this is a temporary discount which increases to 3.48 USD on 2026/05/31 15:59 UTC.

Source: https://api-docs.deepseek.com/quick_start/pricing

Tanxsinxlnx3• 3 months ago

does it support aws bedrock provider

tgautot• 3 months ago

Nice, it's quite usefull to have a project like this which streamlines the setup necessary to use other "brains" in claude code "body". I personally will give this a try, but Ijust find the message on pricing a bit disingenuous, the deepseek price of "$0.87/M output tokens" is a discount, and this setup anyways needs a calude.ai subscription offering claude code, which now is 100$/month min.

izietto• 3 months ago

Just want to say that I faced this very problem the last week, I discovered OpenCode agent and it works great, with DeepSeek and other models. Try it out guys.

column• 3 months ago

Pi will blow your mind :)

aucisson_masque• 3 months ago

No MCP.

No sub-agents. There's many ways to do this. Spawn Pi instances via tmux, or build your own with extensions, or install a package that does it your way.

No permission popups. Run in a container, or build your own confirmation flow with extensions inline with your environment and security requirements.

No plan mode. Write plans to files, or build it with extensions, or install a package.

No built-in to-dos. Use a TODO.md file, or build your own with extensions.

No background bash. Use tmux. Full observability, direct interaction.

eloisant3• 3 months ago

I've tried both, I prefer OpenCode. I get that Pi is more customizable but I prefer a nice, complete out-of-the-box experience and that's what OpenCode provides.

jedisct12• 3 months ago

Try https://swival.dev - Works perfectly with DeepSeek and Qwen.

syntex3• 3 months ago

Not sure you can replace Claude with DeepSeek V4 that easily and have same results.

From what I see while building my own agentic system in Elixir, the problem is in training for your specific harness/contracts. Claude/GPT-style models seem to be trained around very specific contracts used by the harness like tool call formats, planning structure, patching, reading files, recovering from errors, and knowing when to stop.

In practice, you either need a very strong general model that can infer and follow those contracts (expensive), or a weaker model that has been fine-tuned / trained specifically on your own agent contracts. Otherwise, the whole thing becomes flaky very quickly. And I suspect with Deepseek V4 you may get last options.

cpursley7• 3 months ago

I love to learn more about the system you’re building out in Elixir and your learnings if any of it is public.

syntex3• 3 months ago

Its semi public, but I probably publish it soon once its less embarrassing.

Its an Elixir agent runtime with a thin Go TUI (bubble-tea). Im building it mostly to explore agent orchestration: planner/workers/finalizer flows, local file/code-edit tools, MCP tools, permission gates, run context, compaction, and eventually larger swarms. Erlang/Elixir is interesting for this because the actor/supervision model maps pretty naturally to lots of isolated agents and long-running supervised tasks.

As i said, The main lesson so far is that everything around contracts is much more fragile than I expected unless you use a very strong model. Planners return Markdown instead of JSON, tools get called with subtly wrong args, subagents repeat broken tool calls, finalizers lie about success after workers failed. And various permissions may be interpreted by agents in unexpexted way

I also started with too many modes too early instead of making agentic path extremely solid. That made me understand better why these codebases become huge: there are endless corner cases if you want a harness to work across models, providers, tools...

Stronger models hide a lot of harness weakness and weaker models expose. Making weaker models good enough requires a surprising amount of contract hardening. But that hardening tends to make the system better for stronger models too.

Also elixir http stack was causing a lot of problems (needed to use gun eventually)

o10449366• 3 months ago

Idk, my recent experience with Claude is that 4.7 barely knows how to use basic bash tools - how to properly check when programs have finished running, even basic stuff like how to run pytest suites and read the failed tests from the output without re-running the suite to specifically look for them. It's shockingly dumb for all of the tooling they've built into Claude Code (the useless Monitoring tool that blocks bash polling/sleeping that actually works, etc.).

I finally get fed up and started using GPT 5.5 the past 4 days and its a breath a fresh air despite feeling much more minimal. With Claude I had to write so many hooks to enforce behaviors it wouldn't remember and it lacked common sense on. GPT 5.5 does a much better job with things like knowing the AWS CDK CLI can hang on long CloudFormation deployments and it should actively check the deployment status using CloudFormation API rather than hanging for 30+ minutes - and it does this all without asking.

Maybe there's better tooling built into Codex too, but at least on the surface level it seems like how smart the model is makes a significant difference because Claude has more tools than I can count and still struggles to use "grep".

Edit: Like just now - I can't tell you how many times I day I see this sequence:

"Sorry, I'll run in parallel"

"Error editing file"

"File must be read first"

Repeat 10x for the 10 subagents Claude spawned and then it gets stuck until you press escape and it says "You rejected the parallel agents. Running directly now"

rirze• 3 months ago

I’m finding great success having Claude design and review code but having codex actually implement it.

dandaka• 3 months ago

I hope they collaborate with open source harness providers (Pi, Opencode) and train models with those. So next generations will have better integration and better overall quality.

vidarh2• 3 months ago

There are certainly quirks, but identifying and conforming to those quirks is not that complex. E.g. I had Kimi "fix" my harness to work better with Kimi by pointing it at the (open source) kimi-cli + web search and telling it to figure out which differences might matter (it made compaction more aggressive, and worked around some known looping issues (by triggering compaction if it spotted looping tool calls). Largely addressing the quirks tend to harden the harness for other models too. But, yeah, it is more work to make the smaller models work with instead of against the harness.

karel-3d2• 3 months ago

Can I... somehow run this locally? DeepSeek is opensource? Do I even need their API key?

(I have no experience with running anything locally, maybe it's a stupid question)

zozbot2344• 3 months ago

Waiting for official support in llama.cpp. There is a fork that can run a lightly quantized (Q2 expert layers) DeepSeek V4 Flash in 128GB RAM without offloading weight fetches from disk.

karel-3d2• 3 months ago

Ouch. Can't run that on my M4 mac with 48GB RAM.

rsanek• 3 months ago

DeepSeek V4 Pro scores 96.4% on LiveCodeBench and costs $0.87/M output tokens

This is a heavily subsidized price and will only last until the end of the month: "The deepseek-v4-pro model is currently offered at a 75% discount, extended until 2026/05/31 15:59 UTC." [0]

The "supported backends" table is also deceiving -- while OpenRouter's server's may be in the US, the only way to get the $0.44/$0.87 pricing is to pass through to the DeepSeek API, which of course is China-based. [1]

I do think the model is quite good, I myself use it through Ollama Cloud for simple tasks. But I think some folks have bought in a little too much to the marketing hype around it.

[0] https://api-docs.deepseek.com/quick_start/pricing [1] https://openrouter.ai/deepseek/deepseek-v4-pro/providers

FooBarWidget• 3 months ago

They expect inference prices to structurally drop once they receive their big batch of Huawei Ascend chips by the second half of the year.

itrunsdoomguy• 3 months ago

Does it play Doom?

shay1607m• 3 months ago

Interesting setup

do you have any benchmarks on: - token usage over time - failures/retry rates

would be great to see how it behaves in production

zkmon• 3 months ago

Next claude news (trump style): Recent versions of Claude code no longer allow talking to other models, or helping with any code that has the goal of moving away from anthropic models.

akartit• 3 months ago

why not opencode with deepseek?

diamondosas• 3 months ago

I have a question. does anyone have a problem with switihng context between AI and your terminal

connorwhitlock• 3 months ago

96.4% on LiveCodeBench is impressive but LiveCodeBench is single-shot. The interesting test is multi-turn agentic — has anyone benchmarked DeepSeek V4 Pro vs Opus on SWE-bench Verified or similar where the cheaper model has to be more decisive about tool use over 30+ turns? Curious if there's a cliff at higher tool-call depths.

ultrasandwich• 3 months ago

Using this "out-of-the-box" with an OpenRouter subscription using DeepSeekv4, I just blew through 15 dollars in 45 minutes on a moderate sized code base, just making a plan and executing a refactoring of an upload pipeline to use a state machine. Not really seeing the cost savings for real-world work tbh.

rib3ye• 3 months ago

How is this different than using ollama to launch Claude with

ollama launch claude --model deepseek-v4-pro:cloud

jlokier• 3 months ago

That should work, but you need an Ollama Cloud account and for much usage you need to pay the Ollama Cloud $20/mo or $100/mo subscription fee.

Using the API from DeepSeek or OpenRouter also requires a fee, but it's a different, pay-as-you-go payment model.

dzink2• 3 months ago

Tried DeepSeek V4 Pro and Flash on Open Router and they worked fine - flash might have actually produced a better result, but also the same prompt across different inference providers produced the same result. Then tried DS4 Pro again via tinfoil.sh and got the same design but littered with random Chinese characters in the code. Tinfoil pegs prompt data as private / not trained on. Do know know DS4 providers that are verifiably private and not training on your prompts and outputs?

iloveplants• 3 months ago

i'm confused. how does this prove, or even insinuate, that they're training on your data? and if they were, there's no way it would appear that soon

dzink2• 3 months ago

There is no insinuation. I am looking for both private and quality inference. I am not sure why Tinfoil had the characters. I will keep trying them, but it’s an issue if not resolved.

sbinnee• 3 months ago

After some time replacing gemini 3 flash preview with deepseek v4 flash for a chat model, the biggest difference is the auto reasoning effort. Gemini flash is super fast and perfect for a chat model. But when I need some thought experiments with a handful of constraints, it struggles a bit and I switch to sonnet. But with deepseek v4 flash, it can do long complex reasoning and it gets things often right. Generating a lot of reasoning tokens means that it takes a lot of time of course. But I am happy to find a cheaper model and excited to try something other than gemini flash. Gemini flash has been so good that I was locked on it for a while.

xbmcuser• 3 months ago

With how cheap and fast DeepSeek is and now using its free chat over the last few days I just cancelled my claude subscription so far I was using the chat interface only but I might just have to learn how to use the api.

iosjunkie• 3 months ago

Get comfortable with Deepseek's privacy policy for using this for anything serious.

"To improve and develop the Services and to train and improve our technology, such as our machine learning models and algorithms. Including by monitoring interactions and usage across your devices, analyzing how people are using it, and training and improving our technology."

https://cdn.deepseek.com/policies/en-US/deepseek-privacy-pol...

jason1cho• 3 months ago

By dog fooding itself, the tool doesn't fail to live up to the expectations of its users.

DeepClaude – Claude Code agent loop with DeepSeek V4 Pro

Related Stories