found the perfect use case for @typesafeai Jev:
instant compaction
in 2026, why is compaction still a summarization prompt?
Jev can make it instant by scoring every tool call and dropping what’s irrelevant
you can also use Jev to cut costs and token usage!
make your agents more efficient by compacting shell and large file output before it reaches the LLM
passing only necessary tokens to the model and carrying fewer tokens through the rest of the conversation
Jev’s context window is only 32k tokens while a Claude conversation can reach 200k tokens or more!
For compaction, we need to get creative in how to fit up to 200k tokens in the state
How it works:
found the perfect use case for @typesafeai Jev:
instant compaction
in 2026, why is compaction still a summarization prompt?
Jev can make it instant by scoring every tool call and dropping what’s irrelevant
If you’re a Claude code user and feeling the FOMO, I’ve built gpt-live (voice) for Claude
Now you can control Claude sessions and run your entire computer by talking to it
