DeepSeek reasonix, DeepSeek native coding agent with high caching and low cost (esengine.github.io)
229 points by Alifatisk 6 hours ago
agrippanux 42 minutes ago
This website seems to have been generated by Codex - I asked Codex to create an HTML overview of a feature for my team and it made an overly produced monstrosity - complete with the same large stat boxes that were for the most part devoid of meaningful information - using the same font, colors, layout, hero section, etc. It was also terrible on mobile just like this is.
In the end I had Claude produce a one-page html file that was 95% of the way there and it took minor editing to clearly explain the intent of the feature.
embedding-shape 5 hours ago
I'm not sure you need a "DeepSeek native coding agent" to take advantage of DeepSeeks cache, yesterday as the Codex quota usage issue still wasn't solved for me, I wrote a tiny little bridge so I could use DeepSeek V4 Pro via Codex, and seems most of everything I did was basically cached as far as I can tell: https://i.imgur.com/7eKn6wN.png (2026-05-23 Input (Cache hit): 39,123,200 tokens, Input (Cache miss) 1,692,286), and the bridge is doing not special, just massage the DeepSeek API shape into what Codex expects, nothing particular about caching at all.
Besides being even better at the caching, I'm not sure what benefits you'd get compared to just firing up OpenCode with the DeepSeek API yourself, it'll similarly do caching for sure and also "talks directly to api.deepseek.com" if that matters, and you'll get a much more mature harness.
tontinton an hour ago
Yep exactly my thoughts, went and looked at the code for the deepseek provider in my coding agent. and basically all of what the author wrote there is implemented... http://github.com/tontinton/maki for the curios
3uler 4 hours ago
Opencode has really bad cache stability issues that they seem uninterested in fixing at the moment.
dathery 2 hours ago
The OpenCode devs talk about this on Twitter a lot, e.g. https://xcancel.com/thdxr/status/2048268697790300343
> tool call pruning breaks cache and people will tell you this is horrible and expensive
> except i looked at some anthropic data and real user behavior ends up with better cache hits and 30% less spend
> even this is needs to be analyzed further, it's just not simple
> for openai data it's inverted! cache hit ratio is actually better [sic: I think he meant worse based on the screenshot] with tool call pruning turned on
> but the net $ saved is only 5%
> kimi is a funny one - it has better cache hits with pruning on...but is also more expensive!
There was also another thread recently where he discussed that pruning improves user experience (models are smarter with less context) but I can't find it.
This can also be disabled in the config: https://opencode.ai/docs/config/#compaction
huqedato 3 hours ago
I can't confirm this. Having utilized Opencode for a large project over the past 10 months, with multiple models and agents, we've never run into such 'cache stability issues'."
metalspot 24 minutes ago
I am getting 98.6% cache hit ratio on deepseek-v4-flash with opencode
embedding-shape 4 hours ago
That'd be really easy to spot and also fix, most likely. Any open issue you could point us to, must surely been reported already?
nolok 3 hours ago
krzyk 3 hours ago
kiproping 2 hours ago
This would be a better page to link to https://github.com/esengine/DeepSeek-Reasonix/blob/main/docs...
They explain some of the the reasons why they have a better solution and why they are very opinionated
>Automatic prefix caching activates only when the exact byte prefix of the previous request matches. Most agent loops reorder, rewrite, or inject fresh timestamps each turn — cache hit rate in practice: <20%.
So they optimize on this plus other techniques to improve cache hits, making it cheaper.
bwfan123 5 hours ago
> I wrote a tiny little bridge so I could use DeepSeek V4 Pro via Codex
Can you share the bridge. DeepSeek v4 is awesome paired with claude-code or opencode. I found that claude code costs me less than opencode and I am presuming this is due to a better engineered harness.
embedding-shape 4 hours ago
Sure, keep in mind it's a steaming pile of hacked together hacks, probably won't work in every case, doesn't support every feature that should be supported (like parallel tool calling, both Codex + DeepSeek API support it), and it might make your computer catch on fire: https://gist.github.com/embedding-shapes/eab3e63e5a95d3d78a2...
I only used it for a few hours to play around with stuff before the quota issue was fixed and I could resume using GPT models, and the bridge was coded by DeepSeek-V4-Flash-IQ2XXS + DwarfStar4 locally, I take no responsibility for what might happen with your computer or you, during usage or just reading the code.
Edit: heh, like don't look at line 117 for example where seemingly it likes to handle misspellings in the .env file which totally wasn't my fault for typo'ing the API key in that file... I'm sure there are tons of sharp edges and dumb stuff in there.
bayesianbot 2 hours ago
LiteLLM can serve OpenAI API endpoint IIRC and proxy that to other providers like DeepSeek, should work with Codex
Den_VR 4 hours ago
I’m feeling more a novice every day, but how isn’t this just handing over your code to team deepseek for whatever they might want
embedding-shape 4 hours ago
oldmanhorton 3 hours ago
jijji 2 hours ago
himata4113 5 hours ago
this appears to be native to the terminal, as in, there's no special application that runs or wraps an agent inside a tui. So basically instead of commands you type plain english?
embedding-shape 5 hours ago
> this appears to be native to the terminal, as in, there's no special application that runs or wraps an agent inside a tui
Same with codex? codex-rs at least, is a TUI as well, it does run a "app-server" in the background, that the TUI actually interacts with, but that's just an implementation detail. Also makes it easy to hook in your own programs to fire of codex "headless" sessions even without the TUI.
carterschonwald 6 minutes ago
i cant find anything substantiated in the code that actually differentiates it from any other harness.
my fork of oh my pi that i have a lot of experiments in, is lterally designed to only work well with models that have decent reasoning levels, like deep seek models. check it out!
https://github.com/cartazio/oh-punkin-pi/blob/main/scripts/b... — thats the install script for after clone
fair warning: tis my dog food test bed as i build even fancier stuff
skeledrew 5 hours ago
Not a fan of that page. The animated typing and resulting continuous resize of the example keeps moving the content beneath it down and up. Such bad UX.
embedding-shape 4 hours ago
Agents or no agents, people still need to test their websites on different resolutions or at least window width, but seems this is becoming a lost art.
mirekrusin 4 hours ago
Yeah, doesn’t look designed for people who want to read it beyond animated typing animation.
m4rkuskk 2 hours ago
Claude design AI slob.
wg0 44 minutes ago
Performance is horrible when you type but caching is magical.
Extremely pro consumer tool. I have been hammering it hard with 97% cache utilization and barely $0.03 dollar spent for me constantly exploring a codebase.
declan_roberts 4 hours ago
I love the focus on cache hit efficiency. Hats off to the deekseek team for creating a great product that maximizes cost efficiency for the user.
bwfan123 4 hours ago
> Hats off to the deekseek team for creating a great product
I have been using it for a while, and I wholeheartedly agree. imo, it is as good as codex or claude which I also use. It is a winner in the cost-sensitive tier, and if some startup could put it together with data-retention in mind, it could be a great product sold to the enterprise, as data-retention and privacy are the main issues for the coding-assistant usecase.
chillfox 4 hours ago
Deepseek v4 pro is definitely my preferred cheap model, it's very good, and I use it all the time for my personal projects (opencode go plan), but I also use Claude Opus all the time at work and Deepseek is not as good as that, but it does compete with Sonnet for capability, and beats it on price.
nicce 3 hours ago
Just in case, note that this project is someone's side project
> Independent open-source project · not affiliated with DeepSeek
Bombthecat 3 hours ago
Adding already cheap API cost and you probably could let it run for days and the same task..
stavros 4 hours ago
How can you have cache hit efficiency? Isn't it just a matter of not changing the previous context? I don't understand what knobs there are to tweak on this.
everforward 4 hours ago
> Isn't it just a matter of not changing the previous context?
Yes, but a lot of harnesses change previous context. E.g. the system prompt injects the current time/date, working directory, files in the working directory, etc. Compaction also changes the whole previous context. I _think_ changing the list of tools also invalidates cache, so invoking a subagent with different tools would invalidate the cache.
My vague impression is that it's in a similar vein to functional programming languages. It generally disallows doing things that lead to bugs (cache misses in this case), and presumably allows you to do those things in a way that makes it much clearer that this is likely to cause cache misses. I would guess that in this paradigm, you don't mutate your existing session, you derive a new session by mutating the prior context into a new context.
chillfox 4 hours ago
storus an hour ago
Can it instruct DeepSeek during an LLM call to start removing old tool calls from the context instead of waiting for the LLM call to finish if the context size approaches DeepSeek's dumb zone? Claude Code can't do that, /compact can only happen after the LLM call; it's often preferable to start cleaning up context during an LLM call, especially when tool calls are huge like reading markdown files; implementation-wise all that is needed is to start removing earliest <tool call start> ... <tool call end> and replacing them just with some log entry stating this tool call was already performed, then re-running KV cache prefill (so the "online" compaction would get 0.5s latency hit every time it's performed). That way one can read 1000 files in one LLM call.
nextaccountic an hour ago
> Tool-call repair
> Tool arguments the model produces occasionally have JSON typos, unclosed quotes, or shape mismatches. Reasonix runs a schema-aware repair pass before dispatch so malformed args still execute.
So Deepseek API doesn't have a structured output option where you give a grammar and the model promises the output will follow this grammar?
Or it does, but it's buggy?
unshavedyak 3 hours ago
It's pretty funny, i'm a $200/m Claude subscriber and i've had little need to use anything else. However the more Claude has been restricting my workflow (notably around the recent IDE/-p usage change) the more i've been wanting to go elsehwere.
I'm concerned since i really want SOTA reasoning, but DeepSeek still has me interested.
Alifatisk 2 hours ago
> I'm concerned since i really want SOTA reasoning
I think you should give other models a try and see how much they differ from SOTA models. I did this and realized, even Qwen-2.5-Max was enough. I am sure even Claude Sonnet 3.5 is enough for things I play around with. I am not really striving for fields medal in Mathematics.
unshavedyak 20 minutes ago
That's fair, neither am i - i do tend to work in large, complex, full of legacy decision based codebases. Eg i have access to Sonnet (of course), but i choose to solely work in Opus because i find its output reads better, analyzes better, etc.
The "cost" is dumb models is just so high for me. Eg every bad decision they make increases my frustration quite a bit. Despite putting a lot of effort into my workflow to help reduce the number of decisions they make, they always will. So my hedge is always against that.. trying to reduce how insane they can be heh.
0xbadcafebee 2 hours ago
You should definitely stick to the $200 plan, and not try the $10 coding plans with open weight models and higher limits. Anthropic needs your money to stay solvent, and you'll sleep better knowing you're using SOTA.
gck1 44 minutes ago
I gave a fairly complex reverse engineering task to DS-4 xhigh and GPT-5.5 xhigh today.
After about 6 hours, both ultimately failed to fully RE, however, there were some drastic differences:
DS stopped every 30 minutes or so, saying it did full RE and it should all work now, while in fact, it didn't complete even 1% of it. It also looked for shortcuts again and again, despite me prompting heavily that the specific shortcut may not be used. It was a complete and utter failure.
GPT-5.5, on the other hand, blew me away. It just did the right things, didn't jump to next steps until it was sure it completed the initial layers and had a full understanding of what's required. The only time I prompted it during the 6 hours was when I saw it going in the right direction and I could nudge it slightly towards an even better way. I never felt I was fighting it. Okay, maybe a little bit - after compaction, it sometimes would go on a "no I'm not helping you with reverse engineering" tangent, but it would resolve in a clean session.
I cancelled my Claude subscription a month ago, so I haven't tested that, but DeepSeek has reminded me a lot of how I worked with Opus 4.6/4.7. Which perhaps could be a positive sign to some, but GPT-5.5 showed me that the way claude/ds work is just way too annoying.
ttul 18 minutes ago
What you’re experiencing is the difference in model intelligence. Most models can seem pretty good at simple stuff over short time horizons. Complex work requires that more intelligence be stuffed into those trillion-dimensional spaces.
KronisLV an hour ago
> i've been wanting to go elsehwere.
There's always the option of using Anthropic's models for some tasks like planning and then just hand over the implementation task to something like DeepSeek. Across different tools, a Markdown plan works pretty okay. That's what I'm planning to do if I go from the 5x Max subscription down to the Pro.
I am also writing a launcher that makes using 3rd party providers with Claude Code easy (https://ccode.kronis.dev) and I already have a local proxy up and running, just not dynamic model switching yet. Though it shouldn't be too hard to add, will probably be there within a week or two, depending on my schedule.
I don't think it's wise to leave Anthropic altogether because their models are great (and a subscription gives you features like Remote Control which I like), but switching tiers and maybe saving a bit of money seems viable! On the other hand, you do need a quality baseline, because I remember using Cerebras with GLM 4.6 way back and there was a bit too much slop.
logicchains 2 hours ago
If you want SOTA reasoning you should be using GPT 5.5 Pro.
unshavedyak an hour ago
This is fair, but i've found the different models to have different moods and require different interactions to get them to stick to just the specific edits i ask for, etc.
I used to surf the three big players frequently and got really tired of the effort needed to steer some models. In the end i ended up sticking with Claude because it required less steering effort. While not strictly reasoning, a models ability to follow clear directions consistently is something i'd consider part of its SOTA capabilities.
Eventually i just tired of exploring. I just want stability.
Which ironically is why i'm thinking about moving from Claude. The very basic IDE/-p usage getting removed from my plan is a UX stability issue. I'm trying to progressively improve my workflows and efficiency, not have to establish a new foundation anytime something shifts. Quite frustrating.
auggierose 2 hours ago
Codex has only GPT 5.5
schaefer 4 hours ago
Okay, I'm curious.
From the FAQ, I see:
>Can I point it at a self-hosted / private DeepSeek endpoint?
>Yes. Since 0.30 we accept non-standard key prefixes for self-hosted DeepSeek endpoints. Just point `baseUrl` at your internal address — the loop, cache strategy, and tool protocol are unchanged.
But my question is: If I use Reasonix to talk to a deepseek endpoint through openrouter, am I still getting the cache-hit benifits of this agent harness?
csunoser 4 hours ago
Yes*. At least from my limited usage of deepseek-flash for a few billion tokens on openrouter, the cache-hit rate is >95%. And I simply used the claude code harness pointed at the openrouter anthropic compatible endpoint with no fluff.
schaefer 3 hours ago
thank you!
danborn26 2 hours ago
High caching rates for coding agents can drastically reduce latency and API costs. I am curious to see how the caching strategy handles context invalidation across multiple files.
imagetic 3 hours ago
mi_lk an hour ago
Not sure about the story but it would be funny if pi folks actually own this domain.
chuckadams an hour ago
They do. That's Pi's old name.
chabes 3 hours ago
Aka pi.dev
mmaunder 4 hours ago
Unusable thanks to the top animation pushing the rest of the site down repeatedly as you’re trying to read.
singiamtel 3 hours ago
I would've liked benchmarks against other harnesses showing the caching performance
Alifatisk 2 hours ago
Is there benchmarks and measurements that offers comparisons between different harnesses?
mmarcant 43 minutes ago
"byte-stable prefix cache" -- give us your codebase in a way that's even EASIER for us to train on.
singingtoday an hour ago
That site does not render correctly on my android. Lots of text on the right breaking the reactive layout.
hebetude 3 hours ago
Wow the UI looks exactly what I vibe coded yesterday. What a coincidence
huqedato 3 hours ago
It's obvious why...
hirako2000 5 hours ago
Good timing given the cost spike across other frontier models.
notjes 4 hours ago
Good thing DS just made their discount permanent. https://x.com/deepseek_ai/status/2057854261699195173
m101 2 hours ago
For those of you that use deepseek v4 occasionally, what harness do you use it with? I’m only familiar with claude code and codex.
Any comments on what you can or cannot rely on it for relative to cc and codex would be appreciated too!
eikenberry 5 minutes ago
Maybe check out Goose. It is the standard agent harness being developed by The Linux Foundation under the AAIF. Under active development and the implementation seems to have a good leg up on the other popular agents.
droidjj an hour ago
Check out pi.dev. OpenCode is a nice batteries-included Claude Code replacement, but I’m in love with the extensibility of Pi.
chuckadams an hour ago
Any Pi extensions you'd specifically recommend? I'm just starting out with Pi, but I've had mixed results with extensions. I'm using Pi with gemma4 26b locally, so anything that's friendly to small local models would be appreciated. I think the only extension I'm using right now is pi-total-recall.
gck1 3 minutes ago
theanonymousone 4 hours ago
Isn't caching a server-side thing? How does the agent affect it, significantly at least?
embedding-shape 4 hours ago
Say you put the current time down to the second in the system prompt, which is the message that goes in front of the entire conversation, then basically nothing will be cached, every agent turn needs to ingest the entire session over and over. Contrast to not doing that, and the backend can leverage caching all the way up to the latest message, as nothing until then changed.
esperent 4 hours ago
Surely other agent CLIs are not dumb enough to invalidate cache on every turn over something so obvious?
chillfox 4 hours ago
brookst 3 hours ago
embedding-shape 4 hours ago
theanonymousone 3 hours ago
Yes, of course you can destroy it. But how far can you "improve", beyond decent "common sense" behaviour.
yalogin 3 hours ago
Can someone give me a eli5 version of what this is? It really sounds useful to Claude subscribers.
Is this improving the cache hit and hence overall efficiency of coding workflows?
Does it also let me host a local llm (deepseek)? What are model min requirements for this?
timcobb 3 hours ago
You can also ask Claude and get an immediate answer, the power is yours
Salgat 35 minutes ago
Certainly you realize that these comments exist for more than a single person right? You expect potentially hundreds of viewers to each burn through AI tokens instead of just getting a direct and relevant answer here? This has the same vibe as the old forum posts where the only response was a "google it".
fouric 3 hours ago
I don't think it's particularly effective to create a new coding agent when there's existing open-source agents (especially extremely extensible ones like Pi) that already optimize for cache hits, have far larger communities, and work for providers other than Deepseek.
I specifically use multiple different models and providers, so this wouldn't be useful for me.
And it contributes to the problem of each person vibe-coding their own, incompatible, half-baked tool in a space, instead of contributing to a small set of tools and expanding them.
It'd be better to just extend an existing tool.
ricardobeat 3 hours ago
> The loop is append-only, engineered around DeepSeek's byte-stable prefix cache — long sessions hold 90%+ cache hit and input-token cost collapses to ~1/5. Terminal-first, leave it running.
AI marketing slop. This is how all models and coding harnesses work, isn't it?
The author claims (in another AI-written post):
> LangChain — along with every generic agent framework I checked — rebuilds the prompt every turn. Timestamps get injected. History gets reordered. Tool schemas re-serialize with different whitespace.
I haven't touched LangChain in a long, long time, but don't think any of the current harnesses, Claude Code, Pi, Crush, OpenCode etc do that except if you change configuration? Keeping the context stable for caching is a very basic principle and not a wild innovation.
This posing as DeepSeek-specific is also a mystery.
hmokiguess 3 hours ago
Click on the download page, it's hilarious. It has a lot of information about the "smart probe" on the download and it's a realtime probe you can rerun.
That's the pinnacle of AI slop over engineered garbage in my opinion. All of that information is noise.
pkulak 3 hours ago
Doesn't Pi Agent do exactly this? Assuming "append only" means they do some kind of compaction as well.
quotemstr 3 hours ago
> no reordering, no marker-based compaction
Is this really the behavior you want? Yes, doing tool-result clearing and such will blow your cache, but if you do it only occasionally, it's still likely a win. Yes, cache hits are good, but not so good that it's okay to be profligate with context to preserve those precious, precious KVs.
Hfuffzehn 2 hours ago
This is really tickling the conspiracy theorist part of my brain.
"Independent open-source project · not affiliated with DeepSeek" "Reasonix only targets DeepSeek because..." "Why DeepSeek only? Can I swap to Claude / GPT? It's a design choice, not a limitation"
The lady doth protest too much, methinks?
Nicely timed shortly after the making the rebate permanent anouncement.
Could just be Chinese devs trying to help western devs with some software and a western facing marketing campaign to raise awareness. Could be DeepSeek astroturfing. Could be "someone" in China trying to get more access to western data.
Who knows?
andai 2 hours ago
But Claude made the website?
Alifatisk 2 hours ago
What conclusion are you drawing from that?
am17an 3 hours ago
This Claude front end skill is now soon to be slop.
auggierose 2 hours ago
Oh, I was wondering why all new websites look shitty in the same way.
ricardobeat 3 hours ago
Already is. Every new website looks exactly the same.
ankitwarbhe 2 hours ago
you created it yourself ?
Alifatisk 2 hours ago
No.
sergiotapia 4 hours ago
What AI model did you use for the website design? This is the second one I see with the exact same font and color scheme. Just curious because Claude models lean towards purples for example. Thank you!
pcwelder 4 hours ago
Opus 4.7 selects such palette and motifs by default. Might even be first iteration of claude design.
franga2000 4 hours ago
This design still screams Claude to me, but a newer version than what you're thinking of. At some point they added a markdown file that tells it to use obviously AI designs like lots of blue/purple and gradients. Since then, this is its new style.
sheepscreek 4 hours ago
DeepSeek v4 perhaps?
FergusArgyll 3 hours ago
Frontend design skill by Anthropic specifically says not to use purple. I'd be surprised if it still uses purple. Have you seen that recently?
canadiantim 5 hours ago
So what's best low cost coding agent these days? Kimi 2.6? Qwen's latest closed model? Composer 2.5? DeepSeek?
throw10920 an hour ago
Cursor with Composer 2.5 seems to be competitive with frontier models (Opus and GPT-5.5) for a significant price discount. Benchmarks are gamed, as always, but $0.55/task vs $11.02 a task definitely indicates that there's some cost advantage.
bwfan123 5 hours ago
In my experience, it is claude-code paired with deepseek-v4. For penny-pinchers like me, I can have long coding sessions with it with no anxiety about the cost. Also, prompting it to what you want and verifying the outputs is more important than the quality of the model. So, I am better off with a cheaper model and taking the responsibility for prompting it and verifying the results.
esperent 4 hours ago
It's obviously much cheaper paying by the token but how does it compare to a codex subscription on cost?
epolanski 4 hours ago
Can you quantify the actual costs in a week and the use you make?
wongarsu 4 hours ago
passive 4 hours ago
I've gone through ~600m tokens in Xiaomi Mimo though Claude, and it's been the most effective use of an agent I've had yet. It's very capable, but generally not ambitious, picking simple but effective solutions to most problems I give it. Going to write something longer about the experience when I get to a billion tokens.
Alifatisk 4 hours ago
I do have my eyes on the coding plan, which is quite generous.
gandreani 4 hours ago
Are you using Mimo 2.5 pro?
passive 3 hours ago
skeledrew 4 hours ago
Seems to be DeepSeek.
abalashov 3 hours ago
Although I have little interest in agentic coding, when I do use it, I have found Kimi K2.6 to give Opus-quality output, and have switched entirely to it for pretty much everything.
throw10920 3 hours ago
I've used Opus extensively and tried K2.6 on a few projects, and the gap is huge. K2.6 is nowhere near the performance of Opus. That's fine because it's also far cheaper, but public benchmarks line up with my own personal experience that they aren't comparable in terms of intelligence.
(that is, different places on the Pareto efficiency graph)
ac29 5 hours ago
Kimi 2.6 is great. Qwen3.7-max benchmarks similarly but I havent used it yet
stavros 4 hours ago
For me, it's by far Deepseek. It's many times cheaper than competitors, and about as good as Sonnet 4.6.
fouric 3 hours ago
I'd generally agree about Deepseek being as good as Sonnet - but I have extreme trouble with prompt compliance with V4 Pro in a way that I've never had with Sonnet. I'll tell it "find the bug, but don't fix it" or "please use this tool I just developed" and it'll ignore me a high fraction of the time.
It's bad enough that I'm working on guardrails at the harness level because prompting appears to be useless.
Do you have the same issue?
stavros 3 hours ago
lostmsu 5 hours ago
Just use codex with 5.5 on low reasoning levels
WhereIsTheTruth an hour ago
Y'all should not be writing js/ts/slop/npm based clis anymore
It's the agentic era, pick a better option
Just stop
Alifatisk 29 minutes ago
Whats that option?