https://github.com/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.

agents ai-infrastructure anthropic claude-code conformal-prediction context-compression cost-optimization llm llmops mcp openai prompt-caching token-optimization

Last synced: 25 Jul 2026

https://github.com/dshakes/lantern-legal

Last synced: 10 Jul 2026

https://github.com/dshakes/firstpass

Route every LLM request to the cheapest model that provably passes your quality gate — with a signed, tamper-evident receipt for every decision. Proof over prediction.

agents ai-agents cost-optimization inference llm llm-router observability proxy reliability rust

Last synced: 10 Jul 2026

https://github.com/dshakes/lantern

Production runtime for AI agents — run the whole stack locally with one command, ship to your own cloud. Real WhatsApp/Slack/voice/web channels, multi-LLM routing, durable workflows, cost forecasting, eval-in-CI, and verifiable receipts. Apache-2.0.

agent-framework ai-agents firecracker go llm mcp multi-tenant observability rust self-hosted typescript workflow-engine

Last synced: 10 Jul 2026

https://github.com/dshakes/homebrew-tap

Homebrew tap for Distil — compression with a quality contract

Last synced: 10 Jul 2026

https://github.com/dshakes/kage-landing

Kage landing page — private AI, household-grade

Last synced: 10 Jul 2026