Nasiko launches open runtime for agents, cutting input tokens 42% via tool-output compression

socialwithaayan · x · 2026-11-17

Nasiko launched an Open Runtime platform for managing AI agents, centered on TokenOps: discover every agent across the company, show spend per team/model/agent, alert at 80% of budget and pause agents at the limit — deployed with one command, no SDK or migration.

Its key feature is compressing tool outputs (logs, search results, records) before the model reads them. In a 50-question test over real system logs with gpt-4o, compression cut input tokens from 617,202 to 357,958 (-42%) and cost per correct answer from $0.037 to $0.022 (-40%), with log accuracy unchanged (44/50) but record-lookup accuracy slightly down (100/102 → 96/102). It also offers an agent gateway for model routing and tool-permission controls.

Original post →

More from coding & agent

coding & agent channel →