Dev ships Chrome extension driving WebMCP tools with small model Jev, splitting agent workloads
_AustinCalvert_ · x · 2026-09-22
Developer sarahedo released a Chrome extension that drives any site's WebMCP tools from a side panel: on every keystroke it picks the relevant page tool, fills in arguments, and reports its confidence — demoed doing grocery shopping.
Quoting the demo, GautamSW7 argues this clarifies Jev's role: not replacing frontier models, but handling fast, repetitive agent decisions while reserving frontier models for deeper reasoning or generation. The agent stack may end up being about matching the right intelligence to each decision rather than one model doing everything.
Related event: Dev Builds Chrome Extension Pairing Small Model with WebMCP(2 posts)→
More from coding & agent
- Building a (deliberately unsafe) restricted shell MCP server for local coding agents — ag789 · 2026-09-22
- Rumor: OpenAI, Anthropic, and Cognition to launch personal agent platforms within a month — altryne · 2026-09-22
- One test decides if you need an AI agent: if you can write the steps down, you don't — Virtual_Hair_1987 · 2026-09-22
- Teknium merges fix for Hermes Agent Desktop failing to resolve model-provider plugins — Teknium · 2026-09-22
- 90s multi-agent systems offer a lesson: model memory as belief, not centralized truth — nptacek · 2026-09-22
- Grok 4.7 jumps to 46.3% on CursorBench and 64% on EEBench, keeping the same $2/$6 per million token pricing — FinanceYF5 · 2026-09-22