Agentset
APIs for building AI chat and search
What it does
Open-source RAG infrastructure that survives production workloads. Upload documents, query via API, get answers with sources. Hybrid search, multimodal, complex reasoning - all included. Model-agnostic. Used by 1,500+ teams in medical AI, legal tech, enterprise search.
Does the same job
all alternatives →
- AOAgentset – Open-source RAG with vector DB, embeddings, and API built-inOct 2025 · github.com · ▲6
Hi HN, We built one of the largest RAG set-ups that exist toady with Usul.ai (6B tokens). We started by using langchain and llamaindex, they were able to get us to a prototype in a couple of days, but took 3 months of taking pieces apart and optimizing them to make it perform well at such large scale. We put all of these learning into an MIT licensed open-source project — Agentset. Our goal to let people get production quality RAG w/o having to understand or optimize the underlying pieces. It supports 22 file formats, agentic search, deep research, citations, and a UI out of the box.…
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 · 19d 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
