internal/

Package agentbench runs multi-turn harness benchmarks aligned with industry agent/memory/tool evaluation shapes (LoCoMo-style memory, multi-hop QA, τ-bench-style domain end state, plan+interrupt, web-augmented).

Package exa is a minimal REST client for Exa Search (https://api.exa.ai).

Package testkit provides shared test doubles for harness and server integration tests.