CalibratedDecisions.

Repo · Context & memory

defrag

Research tool for telling a coding agent's user when compacting is safe — at the quiet point between tasks, not when the context is nearly full: it…

Open github.com ↗

From the repository

Tells a coding agent's user when compacting is safe: between tasks, not at the context limit.

How builders describe it

Research tool for telling a coding agent's user when compacting is safe — at the quiet point between tasks, not when the context is nearly full: it extracts checkpoints from real sessions, lets you label them, and replays them against judges with TypeSafe Jev as the first production judge (plus…

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