Ratel, give agents unlimited tools and skills without context bloat
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…
In plain words
Ratel is an open-source library that enables AI agents to access a full catalog of tools and skills without loading them all into context at once. It dynamically selects only relevant tools for each interaction, reducing context bloat, hallucinations, and token costs. Built for SaaS companies and developers deploying complex agents in production, Ratel allows teams to expand agent capabilities without performance degradation or prohibitive expenses.
written from the facts on this page · September 2026
From the sources
In the maker’s words, at launch
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
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 27d ago · cactuscompute.com
Launched alongside, July 2026
the whole month →- IR
I might be the only SRE on Earth with his own bowling center. It's a more in-depth gig than you'd think. My family and I bought an abandoned 8-lane bowling center in the rural mid-west. In our small town there weren't many recreation options for families. You've heard of a food desert? This is an R&R desert. It had been abandoned for a good reason. The roof leaks, the electrical system was constantly surging, and my 70-year-old bowling equipment (still) doesn't work perfectly. The system that keeps your score is particularly interesting to me. It's the thing you watch during your game, but…
Life & fun · Jul 2026
- EElevators▲1,680
Life & fun · Jul 2026 · john.fun
- 1W18 Words▲1,160
Life & fun · Jul 2026 · 18words.com
- BA
Over the past few months, our team has been building more and more slidedecks using web frontend technologies with coding harnesses like Claude Code, but a common complaint is to make even small edits we need to edit the code either manually or via the harness. To avoid this loop, I ended up creating Bento, a single HTML file with everything you need in a slide tool including animations and shared editing. There's no install or cloud login, everything works offline. The default deck is around 560 KB and it doesn't need to fetch anything once you got it. Open it in a browser and then you can…
Dev tools · Jul 2026 · bento.page
- GG
A few days ago I found myself trying out GLM 5.2 and was really positively impressed. The capabilities and security I was getting from this LLM are similar to those I've gotten from models like Claude or GPT, and this really surprised me. But then I thought, "I wonder how it would work on a normal computer like mine," and above all, "I wonder if it would work without going into OOM on a computer like mine." So I started working with the help of agents to test this possibility. I started converting the model to int4, understanding MTP usage, and if possible implementing DSA for long context.…
AI · Jul 2026 · github.com
