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.
More from coding & agent
- LuthorSQL: a 7B one-pass text-to-SQL gate that cuts agent API costs 33.3% — Ibrahim Memon · 2026-11-17
- HTTP 200 doesn't mean success: production lessons from an Azure AI translation workflow — WirelessLife · 2026-11-17
- LlamaIndex launches ParseBench-2 Metric Lab for customizable parser rankings — llama_index · 2026-11-17
- LlamaIndex's ParseBench Metric Lab ranks 19 doc parsers by your business needs — llama_index · 2026-11-17
- MIRIX-2.0 multi-agent memory system tops LoCoMo at 91.4%, beats best baseline by 14.3 points — _akhaliq · 2026-11-17
- Google's Nov 10 Core Update: early data shows YMYL site down ~60%, affiliate template pages hit — gaganghotra_ · 2026-11-17