Long Context Bench

Benchmark compressed context against summary, direct retrieval, and provider-context baselines without enabling product integration

jmagly Updated 229 repo stars
AIWG — multi-agent AI framework, one
source of truth; network connecting AI tools

File contents

Long-Context Compression Benchmark

Run aiwg context-bench run <fixture.json> on real AIWG task families. Record quality, exact-recovery failures, latency, memory, and provider-realizable constraints for all four required strategies.

Product integration remains blocked unless compressed skim plus exact recovery beats the strongest quality baseline without increasing exact-recovery failures. Preserve weak and failed results in the report.

@implements #2046

jmagly/aiwg commit 4b9524a6a3

Frequently asked questions

npx get-skill add jmagly/long-context-bench-2