Skip to content
Back to home

Shell compression

11 strategies. 645+ classifiers. 93% average compression.

Raw shell output is the largest hidden token bottleneck for AI coding agents. unerr classifies every command, routes it to a strategy tuned for that output shape, and delivers the compressed result to the agent. The raw bytes stay on disk — the agent can recover them on demand.

93%avg overall
11strategies
645+classifiers
StrategyTargetsCompression
diffgit diff, patch output99%
structuredJSON APIs, docker inspect97%
progressnpm install, pip install95%
log_textbuild logs, server logs, make, cargo build89%
test_resultsvitest, pytest, cargo test, playwright80%
tabularps aux, docker ps, kubectl get77%
error_diagnostictsc, eslint, rustc, shellcheck72%
key_valueenv, kubectl describe, systemctl status48%
tree_pathsfind, tree, ls -R42%
yamlYAML configs, kubectl get -o yaml, Helm outputadaptive
omniFallback for unrecognized outputadaptive

Benchmarked across 40 real-world test cases: 2 MB → 138 KB. Raw output is preserved on disk; the agent can recover it on demand via file_read against the captured tee.