# Distil — compression with a quality contract

Distil is a cache-aware, causally-pruned context compressor for LLM agentic
runtimes. It compresses input and output context, certifies that the agent's
decisions are statistically unchanged (non-inferiority test), and is the only
compressor that proves its guarantees rather than assuming them. Zero runtime
dependencies. Works as an HTTP proxy for Anthropic, OpenAI (Chat Completions +
Responses API), and Google Gemini; in-process client wrap for the Anthropic
SDK; framework hooks for LiteLLM/LangChain/LangGraph. Graded on SWE-bench Verified: 42.0% task success
vs 39.2% full context (paired non-inferiority certified; superiority not
significant). 83.2% savings at 0% decision-change rate on a live head-to-head.

## Key sources

README (canonical overview, install, head-to-head table, security):
https://github.com/dshakes/distil/blob/main/README.md

CHANGELOG (per-version feature list):
https://github.com/dshakes/distil/blob/main/CHANGELOG.md

THREAT_MODEL.md (what distil protects against and explicitly does not):
https://github.com/dshakes/distil/blob/main/THREAT_MODEL.md

docs/EVALUATION.md (evaluation methodology, what the numbers mean):
https://dshakes.github.io/distil/EVALUATION.md

benchmarks/README.md (reproducible head-to-head harness):
https://github.com/dshakes/distil/blob/main/benchmarks/README.md

## Site pages

Getting started (install, quickstart, wrap presets, proof ledger):
https://dshakes.github.io/distil/getting-started.html

Architecture (module map, tier model, cert loop, OTel, Proof Ledger):
https://dshakes.github.io/distil/architecture.html

CLI reference (every subcommand, flags, sample output):
https://dshakes.github.io/distil/cli.html

Deploy & Security (topologies, encrypt-at-rest, gateway keys, OTel session id):
https://dshakes.github.io/distil/deploy-security.html

FAQ (decision-equivalence, nightly gate, OpenAI/Gemini adapters, troubleshooting):
https://dshakes.github.io/distil/faq.html

Benchmark (certified compression frontier, live head-to-head):
https://dshakes.github.io/distil/benchmark.html

Reproduce the numbers (all CI gates, real-model grading, scorecard):
https://dshakes.github.io/distil/benchmarks.html

Compare (distil vs LLMLingua-2 vs Headroom):
https://dshakes.github.io/distil/compare.html

Techniques (tiers, causal pruning, query-aware salience, learned keep-model):
https://dshakes.github.io/distil/techniques.html

Concepts (DERC certificate, conformal risk control, trajectory certificate):
https://dshakes.github.io/distil/concepts.html
