Alternatives
Products that do what Calibra: Cut Robot Training Costs does
Find bad data. Train on less. Save GPU.
- 1
Train robot policies with up to 75% less data
Aug 2026 · calibrarobotics.com
- 2
We are exploring how teams can automatically audit data quality, detect problematic demonstrations, and build smaller, high-quality training sets before spending GPU time. We are looking for design partners to help shape the Calibra.
11d ago · calibrarobotics.com
- 3CW
Creator here. I built ChartGPU because I kept hitting the same wall: charting libraries that claim to be "fast" but choke past 100K data points. The core insight: Canvas2D is fundamentally CPU-bound. Even WebGL chart libraries still do most computation on the CPU. So I moved everything to the GPU via WebGPU: - LTTB downsampling runs as a compute shader - Hit-testing for tooltips/hover is GPU-accelerated - Rendering uses instanced draws (one draw call per series) The result: 1M points at 60fps with smooth zoom/pan. Live demo:…
Jan 2026 · github.com
- 4EF
I’ve been building Echo (https://echo.tracerml.ai/), an experiment in making one AI system out of a pool of open-weight models rather than choosing a single model and using it for every task. It started with a simple experiment. I took a group of models, including GLM-5.2, Kimi K2.7 and others, and ran them on the same evaluations. Then I measured what would happen if, for each problem, you somehow knew in advance which models would be useful and how their outputs should be combined. That hypothetical system performed substantially better than any individual model in the pool.…
Jul 2026
- 5IM
2023 · vram.asmirnov.xyz
- 6
- 7
- 8CT
Hi HN! I'm Ben, the solo founder of Calibre Analytics: https://calibreapp.com. Calibre monitors websites and applications in a clean-room testing environment from all over the world. Up until January Calibre has been an "inbetween other things" / evenings / holidays kind of project. (Only, oops—I did that for four years.). Last year I knuckled down to get into the position where I could work on it full time. I've spent the last 8 weeks working on "Test profiles" (The launch post is here: https://medium.com/get-calibre/announcing-test-profiles-and-...)…
2017 · calibreapp.com
- 9
- 10
- 11
- 12
- 13IR
Jul 2026 · github.com
- 14PR
I built this because I couldn't find honest numbers on how well VLA models [1] actually work on commercial tasks. I come from search ranking at Google where you measure everything, and in robotics nobody seemed to know. PhAIL runs four models (OpenPI/pi0.5, GR00T, ACT, SmolVLA) on bin-to-bin order picking – one of the most common warehouse operations. Same robot (Franka FR3), same objects, hundreds of blind runs. The operator doesn't know which model is running. Best model: 64 UPH. Human teleoperating the same robot: 330. Human by hand: 1,300+. Everything is public – every run with…
Mar 2026 · phail.ai
- 15TB
After training calculator agent via RL, I really wanted to go bigger! So I built RL infrastructure for training long-horizon terminal/coding agents that scales from 2x A100s to 32x H100s (~$1M worth of compute!) Without any training, my 32B agent hit #19 on Terminal-Bench leaderboard, beating Stanford's Terminus-Qwen3-235B-A22! With training... well, too expensive, but I bet the results would be good! *What I did*: - Created a Claude Code-inspired agent (system msg + tools) - Built Docker-isolated GRPO training where each rollout gets its own container - Developed a multi-agent…
2025 · github.com
- 16CB
Hey HN, we're excited to share Cua-Bench ( https://github.com/trycua/cua ), an open-source framework for evaluating and training computer-use agents across different environments. Computer-use agents show massive performance variance across different UIs—an agent with 90% success on Windows 11 might drop to 9% on Windows XP for the same task. The problem is OS themes, browser versions, and UI variations that existing benchmarks don't capture. The existing benchmarks (OSWorld, Windows Agent Arena, AndroidWorld) were great but operated in silos—different harnesses,…
Jan 2026 · github.com
- 17CA
We've been building SensorSurf and are thrilled to share our beta with the robotics community: https://github.com/SensorSurf/agent. SensorSurf is an open source platform that makes it easy for robotics engineers to collect and search data from their fleet. You can define triggers for when to record data (e.g. emergency stop) and capture the moments leading up to the event with rolling buffers. We integrate directly with ROS. Drop our agent into your system, and start collecting data! ================= What prompted me to found this company: > I was a perception engineer…
2023 · sensorsurf.com
- 18
- 19TA
Hi HN, I’m Ben, founder of K-Scale Labs (YC W24). Last year, I wanted to buy a humanoid robot that I could hack on, but the few options for sale were either too expensive, proprietary, or had a limited SDK. We set out to build an affordable humanoid robot using off-the-shelf components that can be built and shipped today, capable of running modern machine learning models, and make it completely open-source for developers like me. Today, we’re releasing our reinforcement learning library and sim2real pipeline for people who want to train policies for humanoid robots. If you have a computer,…
2025 · github.com
- 20
Train robot brains without demos on one GPU
Jun 2026 · app.notion.com
- 21MD
We’re excited to share ML-Dev-Bench, a new open-source benchmark that tests AI agents on real-world ML development tasks. Unlike typical coding challenges or Kaggle-style competitions, our benchmark simulates end-to-end ML workflows including: - Dataset handling and preprocessing - Debugging model and code failures - Implementing new model architectures - Fine-tuning and improving existing models With 30 diverse tasks, ML-Dev-Bench evaluates agents across critical stages of ML development. To complement this, we built Calipers, a framework that provides systematic performance evaluation and…
2025 · github.com
- 22IG
Mar 2026 · github.com
- 23RA
We built RapidFire AI, an open-source Python tool to speed up LLM fine-tuning and post-training with a powerful level of control not found in most tools: Stop, resume, clone-modify and warm-start configs on the fly—so you can branch experiments while they’re running instead of starting from scratch or running one after another. - Works within your OSS stack: PyTorch, HuggingFace TRL/PEFT), MLflow. - Hyperparallel search: launch as many configs as you want together, even on a single GPU - Dynamic real-time control: stop laggards, resume them later to revisit, branch promising configs in…
Sep 2025 · github.com
- 24TD
2019 · scale.ai
Ranked by how close each launch is in meaning, then by votes. Refine with a description →