Jev in production › Agent context and memory

agent-fastpath

Jev decides which files a coding agent reads during triage via an MCP decision layer; benchmark shows file triage reads 408 tokens instead of 35,256 for the same task (author).

Open on GitHub ↗

408 tokens instead of 35,256measured against a baseline, as published by the source
Use
Agent context and memory
Industry
Developer tools
Form
Open-source tool
Stage
In production
Listed
2026-10-19
Found via
github
Repository
abhishekswe/agent-fastpath
Stars
6
Forks
2
Last push
2026-10-31
Language
TypeScript
License
MIT
agent-fastpath screenshot
docs/preview.png in the abhishekswe/agent-fastpath README, MIT; shown from GitHub.

The README opens with

A Jev MCP server: a decision layer for your coding agent, built on TypeSafe Jev (System One model). Ship gates, risk checks, file triage, and browser verification, with typed, calibrated answers.

Website: abhishekswe.github.io/agent-fastpath. See how it decides, real example responses, and setup for 12 coding agents.

Coding agents like Claude Code, Codex, and Cursor spend context and time on small decisions: is this CI log ready to ship, which of these 40 files handle auth, did the page actually say "Order confirmed". agent-fastpath answers them with typed, calibrated results in milliseconds to a couple of seconds, and hands control back when it is not sure.

Badge

For the project's own README, linking back here:

Listed in Jev in production

Also used for agent context and memory