标签：token-optimization

A fuzzy linter for coding agents. It checks the code your agent writes against your team's best practices while the agent is still working, not at code review.

Zero-dependency System 1 decision engine, calibrated guardrails, and token optimization client for Jev (TypeSafe AI)

OpenCode v1 + v2 plugin: prune stale tool calls and truncate bulky tool results from the outgoing request using TypeSafe Jev decisions (verbatim compaction, no summarization).

Dynamic context filter for Pi Coder using Jev by TypeSafe to save 75%+ on context tokens.