Hacker News: jack1689

New comment by jack1689 in "Show HN: Ratel, give agents unlimited tools and skills without context bloat"

jack1689 — Tue, 28 Jul 2026 20:47:13 +0000

thank you for your feedback! I see your point, and we keep asking this thing ourselves.

If this was just some sort of static retrieval, I'd agree with you. But the truth is that we're tackling something more fundamental: improving and evolving it over time, through adaptive scoring and self-improvement.

Also being able of vibe coding it doesn't mean you should: delegating this to a library means delegating the maintenance of this piece of code (which is not trivial, in our opinion).

Anyway, we'll talk about how we tackle self learning loops with it, so stay tuned! :)

What kind of agent are you building btw?

New comment by jack1689 in "Show HN: Ratel, give agents unlimited tools and skills without context bloat"

jack1689 — Thu, 16 Jul 2026 18:03:56 +0000

Hey, yes it's on the same family for sure! The difference is that it works with anything, not just MCPs, and it runs in-process without any additional infra (which usually isn't the case for other RAG solutions). Happy to hear your feedback if you try it out :)

New comment by jack1689 in "Show HN: Ratel, give agents unlimited tools and skills without context bloat"

jack1689 — Thu, 16 Jul 2026 17:58:25 +0000

Hey guys, fair callout, but no AI involved, promise! You're right that some comments look off and someone's farming karma for sure. We see genuine traffic to the repo anyway, so people is checking it out!

Critical feedback is what we're here for, so fire away if you have anything :)

New comment by jack1689 in "Show HN: Ratel, give agents unlimited tools and skills without context bloat"

jack1689 — Thu, 16 Jul 2026 17:40:53 +0000

Thank you! Right now we're adding some frameworks adapters to lower the adoption friction, and pushing deeper on new algorithms on the retrieval side. More languages support is not on the radar yet, but we accept contributions! :)

New comment by jack1689 in "Show HN: Ratel, give agents unlimited tools and skills without context bloat"

jack1689 — Thu, 16 Jul 2026 17:27:15 +0000

Thank you! Let us know how it works if you try it out :) of course real world is another story, but we agree benchmarks are amazing indeed!

New comment by jack1689 in "Show HN: Ratel, give agents unlimited tools and skills without context bloat"

jack1689 — Thu, 16 Jul 2026 17:05:43 +0000

Yes! I should have mentioned in the original post. It was actually built in Typescript at first, but then the performance were not good enough for production use cases. With Rust the footprint was way lower, and we managed tear the latency down from 200ms to 20ms for a single search

New comment by jack1689 in "Show HN: Ratel, give agents unlimited tools and skills without context bloat"

jack1689 — Thu, 16 Jul 2026 16:38:58 +0000

Would love to hear your feedback if you can try it. We initially rolled out BM25 for tool search as it worked best for us internally. Recently rolled out also embeddings and an hybrid option that is being tested in production as we speak

Show HN: Ratel, give agents unlimited tools and skills without context bloat

jack1689 — Thu, 16 Jul 2026 16:11:13 +0000

Hi HN! We're Giacomo and Roberto, authors of Ratel (https://github.com/ratel-ai/ratel)

We used to help SaaS companies build agents on top of their products. Whenever we wanted to expand the agents’ complexity/scope, by adding more and more tools and instructions, we always run in the same issue: context bloat, with frequent hallucinations and sky high token bills. So we started constantly engineering the agents, dynamically loading tools, splitting them into subagents, inventing our own way to support skills

And that's exactly when we started building Ratel: a library to let your agent keep its full catalog of tools and skills, but progressively disclosing only the few that actually matter for each turn. Now you can grow your agent's capabilities without breaking it or taking out a loan for it

People are already using it in production, with a user cutting their token cost up to 81% in the first month without compromising the accuracy

We support both keyword and semantic retrieval, all in-process and without any additional infra. Open source, framework-agnostic, exposes OpenTelemetry metrics, available for Typescript and Python

Benchmarks: https://benchmark.ratel.sh

Some cool things we did with this:

• One team's agent had up to 300+ tools dynamically loaded into context. Ratel cut their token cost 81% in month one. • Another team split into several subagents instead, one agent per task. It worked, until the swarm got slow and expensive. We fixed this with our skills.

We're both here all day. Tear it apart, especially if you're an AI or SWE running agents in production

Comments URL: https://news.ycombinator.com/item?id=48936491

Points: 23

# Comments: 20

Anthropic, Blackstone bet the next trillion-dollar AI business is implementation

jack1689 — Wed, 15 Jul 2026 13:18:30 +0000

Article URL: https://techcrunch.com/2026/07/15/anthropic-blackstone-bet-the-next-trillion-dollar-ai-business-is-implementation-not-models/

Comments URL: https://news.ycombinator.com/item?id=48920435

Points: 6

# Comments: 2

New comment by jack1689 in "The Reverse Information Paradox"

jack1689 — Tue, 14 Jul 2026 15:26:56 +0000

The common fear is that the giant AI labs that sell proprietary models are somehow acting like Trojan horses. I feel the real question is how can we effectively prevent that, yet having best in class inference? Are open source models the endgame then?

The Reverse Information Paradox

jack1689 — Tue, 14 Jul 2026 15:26:56 +0000

Article URL: https://snscratchpad.com/posts/reverse-information-paradox/

Comments URL: https://news.ycombinator.com/item?id=48908306

Points: 3

# Comments: 1

Anduril CEO Warns AI and Defense Valuations Are Becoming Dangerously Overvalued

jack1689 — Mon, 13 Jul 2026 12:45:03 +0000

Article URL: https://finance.yahoo.com/technology/ai/articles/anduril-ceo-warns-ai-defense-180112499.html

Comments URL: https://news.ycombinator.com/item?id=48891865

Points: 6

# Comments: 0

Open source AI matters more than ever, according to Hugging Face's Clem Delangue

jack1689 — Mon, 13 Jul 2026 12:42:49 +0000

Article URL: https://techcrunch.com/podcast/open-source-ai-matters-more-than-ever-according-to-hugging-faces-clem-delangue/

Comments URL: https://news.ycombinator.com/item?id=48891832

Points: 1

# Comments: 0

New comment by jack1689 in "Central Banks Are Joining the AI Bubble Debate"

jack1689 — Thu, 09 Jul 2026 18:15:03 +0000

Wondering whether they are more worried about security concerns given the latest model releases (see European Central Bank about Mythos) or a potential bubble and how/if they can do something about it

Central Banks Are Joining the AI Bubble Debate

jack1689 — Thu, 09 Jul 2026 18:15:03 +0000

Article URL: https://www.forbes.com/sites/ronschmelzer/2026/07/08/central-banks-are-joining-the-ai-bubble-debate/

Comments URL: https://news.ycombinator.com/item?id=48850210

Points: 1

# Comments: 1

New comment by jack1689 in "AI Tokenomics: How to tokenmin while ROImaxxing"

jack1689 — Wed, 08 Jul 2026 07:38:20 +0000

I feel like 12 months ago it was just about "we just need the next great model" and now we are seeing how there is a lot of infra to be built around these models to avoid ROI negative tokenmaxing outcomes

AI Tokenomics: How to tokenmin while ROImaxxing

jack1689 — Wed, 08 Jul 2026 07:38:20 +0000

Article URL: https://mmc.vc/research/ai-tokenomics-how-to-tokenmin-while-roimaxxing/

Comments URL: https://news.ycombinator.com/item?id=48828788

Points: 3

# Comments: 1

New comment by jack1689 in "US manufacturers' energy costs soar because of AI data center demand"

jack1689 — Wed, 08 Jul 2026 06:38:15 +0000

I have been hearing a lot about "AI will help us create greener energy" with the promise to sort of close the loop (linking here one from MIT I came across a while ago: https://news.mit.edu/2025/how-ai-can-help-achieve-clean-ener...)

Wondering: 1) How? 2) Is the balance gonna be actually positive or will manufacturers and customers pay the bill for it as you say?

Why the rise of open source AI isn't hurting Anthropic yet

jack1689 — Tue, 07 Jul 2026 23:06:37 +0000

Article URL: https://techcrunch.com/2026/07/07/why-the-rise-of-open-source-ai-isnt-hurting-anthropic-yet/

Comments URL: https://news.ycombinator.com/item?id=48825221

Points: 3

# Comments: 0

New comment by jack1689 in "Zuckerberg says AI agent development going slower than expected"

jack1689 — Mon, 06 Jul 2026 02:25:48 +0000

Yeah totally feel you on this one! To avoid it or at least limit that I usually ask it to create external memories, clearing the context window and leaving just a trace to recall the memory created for that run. I hope it might help!