CalibratedDecisions.

Repo · Context & memory

jev-tokensaver

Claude Code and Cowork pre-reader: a local jev CLI, MCP server and skill that let TypeSafe Jev read long test logs, big files and candidate-file…

Open github.com ↗

From the repository

Cut Claude Code & Cowork token use with TypeSafe Jev: prune long output, find the relevant lines, rank files. Fail-open, secrets-scrubbed.

How builders describe it

Claude Code and Cowork pre-reader: a local jev CLI, MCP server and skill that let TypeSafe Jev read long test logs, big files and candidate-file lists (prune, find, rank, map) and pass Claude only the relevant lines — lossless, fail-open, secrets scrubbed locally.

The decision Jev makes

Keep or discard a tool result, or answer whether a stopping condition is met.

Where it fits

Agents drown in their own context. These projects use Jev to decide what to keep, what to drop and when a loop is actually finished. All 117 context & memory projects →

Related projects