Nasiko 推出开源 Agent 运行时平台,通过模型路由和上下文压缩减少 50% token 消耗
做 Agent 的团队都怕 token 账单失控,这个 Nasiko 在 SWE 基准上砍了 50% 用量,还带按团队设预算和权限的功能。一条命令就能装到现有 Agent 底下,想管成本和模型路由的话可以先试试看。
Nasiko 发布了一个面向 AI Agent 管理的开源 Runtime 平台,官方称在标准 SWE 基准测试上减少了 50% 的 token 消耗。
平台的工作方式是坐在现有 Agent 之下:为每个 Agent 自动选择合适的模型、压缩上下文并进行缓存,同时通过 agent gateway 做模型路由。治理方面,它支持按 Agent、按团队设置工具访问权限和预算。
对开发者来说,安装只需一条命令,不改变现有工作流。这类"token 运维"(tokenops)产品瞄准的是 Agent 大规模部署后成本失控的痛点,与 LangSmith 等 Agent 观测工具相比更侧重成本控制和权限治理。
If you build and manage agents, the goal is to spend smarter on tokens. To solve this, Nasiko picks the right model for each agent, compresses context, and caches. They report 50% fewer tokens on standard SWE benchmarks. It sits under your existing agents and installs with one command. bit.ly/nasikolaunch Nasiko @nasikolabs Nasiko - Open Runtime platform for managing AI agents. See every agent. Cut token spend by up to 50%. Route to the right model with the agent gateway. Govern tool access. Set permissions and budgets per agent, per team. One command. Same workflow. Open Runtime for agents starts now. First, every token. Next, every action! Start Free: buff.ly/k79CiWW #ai #tokenops #openruntime #agents
This report is categorized under AITOP's "Products" desk. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows. Key entities and technical topics under continuous tracking include Nasiko, agents, token optimization, model routing.
Source attribution: curated from elvis (@omarsar0).