Winnow
Keep the signal. Drop the noise.
What it does
Winnow compresses RAG prompts before they hit your LLM, cutting token costs 50%+ while preserving meaning. Uses question-guided filtering + LLMLingua-2 for semantic accuracy. Key features: • FastAPI server with OpenAI-compatible proxy • Batch compression API • Question-aware filtering keeps answer-relevant tokens • Docker self-hosting, pip-installable SDK • MIT licensed
Does the same job
all alternatives →- DADemystifying Advanced RAG Pipelines2023 · github.com · ▲131
I've built an advanced RAG (Retrieval-Augmented Generation) pipeline from scratch to demystify the complex mechanics of modern LLM-powered Question Answering systems. This repository features: -- An implementation of a sub-question query engine from scratch to answer complex user questions. -- Illustrative explanations that unveil the inner workings of the system. -- An analysis of the challenges I faced while working with the system, like prompt engineering and cost estimation. -- Qualitative comparison with similar frameworks like LlamaIndex, offering a broader perspective. Key Takeaway:…
- ATA tool to benchmark LLM APIs (OpenAI, Claude, local/self-hosted)2025 · llmapitest.com · ▲55
I recently built a small open-source tool to benchmark different LLM API endpoints — including OpenAI, Claude, and self-hosted models (like llama.cpp). It runs a configurable number of test requests and reports two key metrics: • First-token latency (ms): How long it takes for the first token to appear • Output speed (tokens/sec): Overall output fluency Demo: https://llmapitest.com/ Code: https://github.com/qjr87/llm-api-test The goal is to provide a simple, visual, and reproducible way to evaluate performance across different LLM providers, including…
TextCompressor Apr 2026 · textcompressor.unmutedlive.com · ▲2Reduce your LLM API bill 11–45% with zero code changes
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
Launched alongside, March 2026
the whole month →
Switch from ChatGPT to Claude with import memory feature
AI · Mar 2026 · claude.com
