HOT RADAR
agentHEAT 8.7°

AI CURATED HOT STORY · 11/21/2026

MachinePulse Open-Sources Browser Agent Framework and 31B Decision Model

1 reports archived1 independent sourcesupdated 11/21/2026, 17:52:00
Synthesis & Latest Updates
1 Sources Cross-Validated

MachinePulse AI has open-sourced Karpo Decision 31B, a low-latency decision model for agents, alongside the karpo-browser framework, a 27B Act action model, and the KBB evaluation set. On Browserbase Benchmark v2, the stack reports 89% average success at 201 seconds per task and $0.096 model cost per task, roughly 1.9x faster and about one-thirteenth the cost of the Claude Fable 5.2 setup.

LATEST/MachinePulse AI has open-sourced Karpo Decision 31B, a low-latency decision model for agents, alongside the karpo-browser framework, a 27B Act action model, and the KBB evaluation set. On Browserbase Benchmark v2, the stack reports 89% average success at 201 seconds per task and $0.096 model cost per task, roughly 1.9x faster and about one-thirteenth the cost of the Claude Fable 5.2 setup.

Hourly heat curve

10 fully observed hours
Now
8.7
Peak
10.723:00
24h change
–

The line compares only sources observed throughout; gap hours are interpolated to keep the trend continuous.

Coverage timeline

Total 1 reports · Latest first
  1. 量子位 (微信公众号)T2·78 pts
    • Karpo Decision 31B targets high-frequency, low-latency agent decisions, runs on a single RTX PRO 6000, and reports a 94 ms median response on public requests
    • karpo-browser uses a System 1 + System 2 architecture with a 27B Act action model and the KBB web-action evaluation set
    • On Browserbase Benchmark v2 it reports 89% success, 201 seconds per task, and $0.096 model cost per task, well ahead of the Claude Fable 5.2 setup