«It uses an architecture where everything is a plugin»
Ok, that's enough for me. I have developped over the year a plugin fatigue.
Every product relying on "community plugins" for their features implies it works fine the 6 first months, then it's a nightmare of incompatible, deprecated, incompatible plugins, with no consistency and no governance.
I understand how attractive it can be to companies to think, hey, let's make a very small product and rely on other people to make features, and I hope it works, but I'm personally staying away from that.
I have read the underlying paper, and found it may be useful, but not that useful.
For those who want to know what it achieves: it adds hot-reload and dynamic enable/dispose capabilities to a plugin system, like the one in Pi agents, though they push the boundaries further, to the UI components and so on.
For those who want to know what it does: if you have some PLT knowledge, ask your agent to explain the algebra to you better; for those who aren't familiar, the framework requires each plugin to provide how it initializes and how it destructs (like C++'s RAII, Rust's Drop trait and so on), and the runtime will then properly handle the lifecycle events and the common pitfalls. In addition, it provides a clean way to declare the dependencies between plugins, and the runtime will also properly process the lifecycle changes on a broader plane.
I think it's worth reading if you are not familiar with OSGi, iPOJO, React's useEffect and so on (which the paper itself mentions); for others, a skim is enough: it does point out the gotchas for some common problems, but the algebra may not help you further.
But like, what is it? Odd that this reached #1 on HN. The README is pretty bare outside of installation instructions and a link to "Cordis", which is "A Meta-Framework of Spatiotemporal Composability." and "under active development. The API is not yet stable and may change without notice.".
New coding harness that seems to have some novel concepts and one of the pretty cool things on their landing page for it here: https://deepseek.com/harness/en/ is the Every Run is Traceable view:
"Everything the model sees is recorded in an append-only session log: system prompts, reasoning, tool calls and results, subagent scheduling, and every context injection. In the Trajectory view, you can inspect these records by source. Resume, fork, search, and replay all operate on the same event stream."
Seems pretty helpful - have sort of wanted something similar (I use Pi).
They also released this research paper that backs their whole plugin composability system that seems pretty cool: https://github.com/cordiverse/paper
I thought the harness was mainly a TAI (tangible AGENT interface). Its a harness for the agent, not a user interface. That is bolted on top of the harness.
1. it's built for async
2. runs everywhere
3. interpreted, making it fast to iterate on
4. decent performance
5. most popular language, llms are decent at writing it
An additional benefit of interpreted, I think, is to make plugins easier to distribute and incorporate. With a compiled language you’d need message passing or something.
aren't 3 and 4 a tradeoff though? Yes you have 3 but "decent performance" cannot be an extaled value as compared to "runs everywhere". If its used as a counter balance to 3 then it shouldn't be its own unique point basically saying 4 is true despite 3 in this case.
This line of thinking I feel like assumes it's the only program running on your computer. Using less of my CPU and memory means my computer can do more things in parallel, or even run more instances of the harness. My laptop is sweating when I got 5+ claude code sessions running.
yeah fair enough, my entire point is not about the application itself but the contradiction on using superlative terms for all points but a compromising/normal term for one. Like if performance is not revelant why include it in the list of benefits.
JVM apparently has the advantage that nobody under the age of 40 wants to touch it anymore. I admit I haven't worked in it in 20 years, but I do think it's a marvel of engineering and unfairly maligned. It used to be my career but I wanted to be closer to the metal.
Having Oracle's tramp-stamp on it may have been the final kiss of death in terms of totally-superficial "coolness" factor.
Probably for the ease of coding extensions — which strikes me as outdated thinking: if it’s open source and you’re outsourcing the coding to LLMs, why not use a compiled, safe language?
There’s an interesting counter example for DeepSeek called CodeWhale, though:
I'm not sure why specifically Javascript instead of something like Python or other options, but using an interpreted environment minimizes the friction for implementing extension systems, which are an important feature in AI harnesses.
Python basically requires containers unless you are OK with it bit-rotting every six months or so. At least, this used to be the case for trivial python, and recently was the case for stuff that uses cuda.
I stopped paying attention the third time they redefined matrix arithmetic semantics. That happened to be around the 100th time I was sent a script and it only ran on the author’s machine. Maybe they will fix it some day. When they do, I will not believe it.
In contrast, TS has a much nicer type system and better async support. It runs well on web, mobile, desktop and server. Yes, sometimes you have to ship node.js or a whole web browser, but the tooling for that is slightly less insane than the analogous tooling for python.
Its language interoperability story is slightly nicer too (invoke native code, or use wasm). It’s UI story is much, much better since it reuses all the web stuff.
Pip practically invented the supply chain attack; npm perfected it. That’s probably a draw.
Of course, if you care about performance, then other choices make more sense. If you’re training a model then python probably still wins, but very few customers have a $1M+ machine.
`uv` helps but it's new, and I don't think it has the same mindshare yet on "I just globally want to install this thing that needs an interpreter/runtime", so Python probably just doesn't come first to mind.
I'd put it on this. In my experience Python is fine for scripting your own machine but an obnoxious platform to distribute code on. It's very fragile to version changes, in both directions; I don't know how many things I've seen that only run on 3.10, not 3.9 or 3.11. Its packaging system is global by default which only compounds this because everything needs a specific version but they're all dumped in the same place. And it tends to have a lot of native code as dependencies, leading to all the issues of needing to either have the right build environment or a runtime environment that's already been built for.
Is there a comparison of harness somewhere? Like, the same prompt to the same model, but with different harnesses, and comparing the quality of the results.
I am trying to run as much as possible only on free software, so I always only used Zed plugged with anthropic models, but I am wondering what is the quality of Zed harness compared to the one of claude code or pi or others... I would love some feedback.
Tangential but, are there benchmarks out there on how languages affect latent spaces and performance of these models?
This other day I was looking at that “caveman” skill, and was shocked to see it evolved to become a company, and, in one of its modes, the highest form of compression seems to be “Wenyan” which is Classical Chinese.
There are lots of papers on the topic. I think the best summary is "it's complicated". Typically models perform slightly better in English, typically best in either professional English or very rude English. Though this varies by model, not all react well to rude English, and I wouldn't be surprised if Chinese was on the rise
Also, "less tokens" is not always straight forward. I doubt it's a coincidence that the cavemen skill (or now proxy, I guess) has lots of numbers, but not a single benchmark on model performance or actual per-task token savings
For example one paper I remember found that without CoT, just stating your prompt twice increases model performance. With CoT, the same function is served by the CoT restating the important parts of your question. Something about which tokens can affect which other tokens in attention implementations
I hear that often but to me it does not feel like it. I built my own framework around pi.dev harness and run all kind of different LLMs with it. Sometimes also use the vendor harnesses and they don't feel better adapted.
i've been using Cascade (a third party harness) since the 3 week period in 2023 when it was hot. I think it's called something else now. Devin? Things got confusing there for a second and I stopped paying attention.
Anyway very happy with it, I use it as a plugin to RubyMine and Webstorm.
One of the primary advantages is being able to choose your model - and it often has free deals for newer models that are running promotions. Whenever I switch to Claude Code it seems clunky. Would rather use Claude with Cascade.
I use OpenCode and I like knowing the direct token spend for doing tasks. A healthy repo can get a lot done with Luna + fresh context. Then I can spend $1-$2 a day when I'm doing development, and costwise honestly it beats a $200 / month plan.
I also just do a bit of hand-coding to guide the agent still.
I worry the $200 / month plans are loss-leaders encouraging you to maximize token usage to churn out slop, rather than thoughtfully use coding agents in a way that still engages your brain, and produces good software.
In the age of LLMs, if your new hires are pushing npm slop, with all the cargo culting and security pwn issues it brings, your hiring process has failed you
«It uses an architecture where everything is a plugin» Ok, that's enough for me. I have developped over the year a plugin fatigue.
Every product relying on "community plugins" for their features implies it works fine the 6 first months, then it's a nightmare of incompatible, deprecated, incompatible plugins, with no consistency and no governance.
I understand how attractive it can be to companies to think, hey, let's make a very small product and rely on other people to make features, and I hope it works, but I'm personally staying away from that.
The landing page provides more context than GitHub: https://deepseek.com/harness/en/
The documentation, built from repo, is available here: https://deepseek-harness.github.io/deepseek-harness/en/guide... (I find the development and reference sections easier to read and navigate)
I think the github readme repo is more for people who heard about it, but you're absolutely right, it is lacking in context and explanation.
this should be the link!
yeah, a rare thing.
I have read the underlying paper, and found it may be useful, but not that useful.
For those who want to know what it achieves: it adds hot-reload and dynamic enable/dispose capabilities to a plugin system, like the one in Pi agents, though they push the boundaries further, to the UI components and so on.
For those who want to know what it does: if you have some PLT knowledge, ask your agent to explain the algebra to you better; for those who aren't familiar, the framework requires each plugin to provide how it initializes and how it destructs (like C++'s RAII, Rust's Drop trait and so on), and the runtime will then properly handle the lifecycle events and the common pitfalls. In addition, it provides a clean way to declare the dependencies between plugins, and the runtime will also properly process the lifecycle changes on a broader plane.
I think it's worth reading if you are not familiar with OSGi, iPOJO, React's useEffect and so on (which the paper itself mentions); for others, a skim is enough: it does point out the gotchas for some common problems, but the algebra may not help you further.
For all the high-powered theory it looked just like every other harness! I was expecting more.
If anybody has tried it, does it let you preview components in any frontend framework with perfect fidelity? That would be a big win.
Uh, it’s big idea is a destructor? This is considered significant in 2026 and the era of vibe coding?
Don’t sell it short, it’s big idea is also to support dependency injection style explicit linkage between dynamically added components.
But like, what is it? Odd that this reached #1 on HN. The README is pretty bare outside of installation instructions and a link to "Cordis", which is "A Meta-Framework of Spatiotemporal Composability." and "under active development. The API is not yet stable and may change without notice.".
New coding harness that seems to have some novel concepts and one of the pretty cool things on their landing page for it here: https://deepseek.com/harness/en/ is the Every Run is Traceable view:
"Everything the model sees is recorded in an append-only session log: system prompts, reasoning, tool calls and results, subagent scheduling, and every context injection. In the Trajectory view, you can inspect these records by source. Resume, fork, search, and replay all operate on the same event stream."
Seems pretty helpful - have sort of wanted something similar (I use Pi).
They also released this research paper that backs their whole plugin composability system that seems pretty cool: https://github.com/cordiverse/paper
is it just for coding? the docs don't mention code, just "agents"
Seems like Agentsview, but built in and likely less features(at least, as of now): https://github.com/kenn-io/agentsview
> A Meta-Framework of Spatiotemporal Composability
Good to know I was not the only one confused. Reads like word salad!
A "harness" is basically what you call Claude Code and such, i.e. a TUI to run the agent.
TUI?
Aren't VS Code, Claude Code, Hermes Agent, Goose or Letta harnesses, but with UI, too?
Can be a TUI, can be a GUI.
VSCode at least is a GUI
Which it’s kind of strange VSCode ghcp lacks basic attributes like context % used compared to some TUIs where it’s default.
There is a round icon at the right bottom, where white arc is how much context used - hover for extra info.
I thought the harness was mainly a TAI (tangible AGENT interface). Its a harness for the agent, not a user interface. That is bolted on top of the harness.
Hacker News will mindlessly upvote anything they see as a threat to US AI labs. It's not more complicated than it having "DeepSeek" in the name.
Is there a reason why so many of these agent harness are written in node.js?
Because:
1. The first significant agentic harness was made by Anthropic.
2. One of the most senior developers of client-side software at Anthropic is Felix Rieseberg. He is one of the original creators of Electron. [1]
3. After Claude Code blew up, everyone else copied Anthropic.
---
1: https://daringfireball.net/2026/07/claudes_criminally_bad_ma...
1. it's built for async 2. runs everywhere 3. interpreted, making it fast to iterate on 4. decent performance 5. most popular language, llms are decent at writing it
An additional benefit of interpreted, I think, is to make plugins easier to distribute and incorporate. With a compiled language you’d need message passing or something.
dynamic linking was invented pretty long time ago
You know that dlopen does not compare.
aren't 3 and 4 a tradeoff though? Yes you have 3 but "decent performance" cannot be an extaled value as compared to "runs everywhere". If its used as a counter balance to 3 then it shouldn't be its own unique point basically saying 4 is true despite 3 in this case.
when you're waiting for network or LLM inference the raw performance doesn't matter at all
This line of thinking I feel like assumes it's the only program running on your computer. Using less of my CPU and memory means my computer can do more things in parallel, or even run more instances of the harness. My laptop is sweating when I got 5+ claude code sessions running.
Is it actually claude using those CPU cycles though, or the agent running test suites and what not?
Honestly I would not be surprised when it actually IS claude using those resources... It is very clearly vibed
You would think raw performance wouldn't be a problem given most of whats happening is waiting for network calls and streaming tokens.
But modern bloat manages perfectly well to make apps that wait for network calls run poorly enough to give you a bad experience.
This is so very, very incorrect.
yeah fair enough, my entire point is not about the application itself but the contradiction on using superlative terms for all points but a compromising/normal term for one. Like if performance is not revelant why include it in the list of benefits.
JVM has real and virtual threads and arguably just as good if not better on all these points.
(I actually have/am writing a harness in Java fwiw, but mostly as a hobby/experimentation)
JVM apparently has the advantage that nobody under the age of 40 wants to touch it anymore. I admit I haven't worked in it in 20 years, but I do think it's a marvel of engineering and unfairly maligned. It used to be my career but I wanted to be closer to the metal.
Having Oracle's tramp-stamp on it may have been the final kiss of death in terms of totally-superficial "coolness" factor.
But have you considered that java is gross and nodejs is sexy?
Probably for the ease of coding extensions — which strikes me as outdated thinking: if it’s open source and you’re outsourcing the coding to LLMs, why not use a compiled, safe language?
There’s an interesting counter example for DeepSeek called CodeWhale, though:
https://github.com/Hmbown/CodeWhale
Also isn't OpenAI's Codex written in Rust?
Codex, Kiro, Grok Build. Pi has a clone in Rust too.
I don’t think so it’s an npm package iirc
you can install binaries with npm too, not just limited to js
I'm not sure why specifically Javascript instead of something like Python or other options, but using an interpreted environment minimizes the friction for implementing extension systems, which are an important feature in AI harnesses.
Python basically requires containers unless you are OK with it bit-rotting every six months or so. At least, this used to be the case for trivial python, and recently was the case for stuff that uses cuda.
I stopped paying attention the third time they redefined matrix arithmetic semantics. That happened to be around the 100th time I was sent a script and it only ran on the author’s machine. Maybe they will fix it some day. When they do, I will not believe it.
In contrast, TS has a much nicer type system and better async support. It runs well on web, mobile, desktop and server. Yes, sometimes you have to ship node.js or a whole web browser, but the tooling for that is slightly less insane than the analogous tooling for python.
Its language interoperability story is slightly nicer too (invoke native code, or use wasm). It’s UI story is much, much better since it reuses all the web stuff.
Pip practically invented the supply chain attack; npm perfected it. That’s probably a draw.
Of course, if you care about performance, then other choices make more sense. If you’re training a model then python probably still wins, but very few customers have a $1M+ machine.
`uv` helps but it's new, and I don't think it has the same mindshare yet on "I just globally want to install this thing that needs an interpreter/runtime", so Python probably just doesn't come first to mind.
I'd put it on this. In my experience Python is fine for scripting your own machine but an obnoxious platform to distribute code on. It's very fragile to version changes, in both directions; I don't know how many things I've seen that only run on 3.10, not 3.9 or 3.11. Its packaging system is global by default which only compounds this because everything needs a specific version but they're all dumped in the same place. And it tends to have a lot of native code as dependencies, leading to all the issues of needing to either have the right build environment or a runtime environment that's already been built for.
TypeScript is great and its ecosystem is easy to work within.
I gotta same problem.
npm as a distribution tool works well and typescript has types.
Any reason why it should not be written in nodejs?
Might be easier to do cross platform.
Skill issue. Their models don't work for serious programming so everyone just copies Electron apps from each other.
The Cordis plugin architecture is interesting
https://github.com/cordiverse/paper
[delayed]
Is there a comparison of harness somewhere? Like, the same prompt to the same model, but with different harnesses, and comparing the quality of the results. I am trying to run as much as possible only on free software, so I always only used Zed plugged with anthropic models, but I am wondering what is the quality of Zed harness compared to the one of claude code or pi or others... I would love some feedback.
Tangential but, are there benchmarks out there on how languages affect latent spaces and performance of these models?
This other day I was looking at that “caveman” skill, and was shocked to see it evolved to become a company, and, in one of its modes, the highest form of compression seems to be “Wenyan” which is Classical Chinese.
Should I get started on learning Chinese?
There are lots of papers on the topic. I think the best summary is "it's complicated". Typically models perform slightly better in English, typically best in either professional English or very rude English. Though this varies by model, not all react well to rude English, and I wouldn't be surprised if Chinese was on the rise
Also, "less tokens" is not always straight forward. I doubt it's a coincidence that the cavemen skill (or now proxy, I guess) has lots of numbers, but not a single benchmark on model performance or actual per-task token savings
For example one paper I remember found that without CoT, just stating your prompt twice increases model performance. With CoT, the same function is served by the CoT restating the important parts of your question. Something about which tokens can affect which other tokens in attention implementations
Bad timing: https://xcancel.com/deepseek_ai/status/2087864589895798968
Why is this bad timing?
And that's it, that's the last lab releasing models worth coding with that didn't have a first party harness that its models are trained to use.
Tracing what it actually did. Who would have thought that's a good idea, instead of trying to obfuscate everything.
I'm curious what peolle are finding with first party vs 3red party harnesses for coding.
Do the first party harnesses really have an advantage when paired with the maker's model?
I hear that often but to me it does not feel like it. I built my own framework around pi.dev harness and run all kind of different LLMs with it. Sometimes also use the vendor harnesses and they don't feel better adapted.
i've been using Cascade (a third party harness) since the 3 week period in 2023 when it was hot. I think it's called something else now. Devin? Things got confusing there for a second and I stopped paying attention.
Anyway very happy with it, I use it as a plugin to RubyMine and Webstorm.
One of the primary advantages is being able to choose your model - and it often has free deals for newer models that are running promotions. Whenever I switch to Claude Code it seems clunky. Would rather use Claude with Cascade.
I use OpenCode and I like knowing the direct token spend for doing tasks. A healthy repo can get a lot done with Luna + fresh context. Then I can spend $1-$2 a day when I'm doing development, and costwise honestly it beats a $200 / month plan.
I also just do a bit of hand-coding to guide the agent still.
I worry the $200 / month plans are loss-leaders encouraging you to maximize token usage to churn out slop, rather than thoughtfully use coding agents in a way that still engages your brain, and produces good software.
Good idea, ugly landing page
if it's not better than omp im not trying it
How will you know if it's better or not without trying it?
What's its best feature?
it looks like we're leaving md files and instead use cordis plugins ?
In the age of LLMs, if your new hires are pushing npm slop, with all the cargo culting and security pwn issues it brings, your hiring process has failed you
oof