GitHub · Python
dshakes/distil
Compression with a quality contract — cache-aware, causally-pruned LLM context compression for agentic runtimes, certified non-inferior across 7 domains. Works with any SDK.
- Stars
- 21
- Forks
- 3
- Stars gained in 24 hours
- 0
- Forks gained in 24 hours
- 0
Topics: agents, ai-infrastructure, anthropic, context-compression, cost-optimization, llm, llmops, openai, prompt-caching, token-optimization
Latest data point: Nov 21, 2026 · 21 stars · 3 forks