prompt-caching
Multi-turn agent loops cost O(N²). Burnless makes them O(N). 88% cheaper at turn 10. MIT, provider-agnostic.
Secure Personal AI Research Kit - Multi-provider LLM web interface with MCP tool integration
Auto-optimize LLM prompt caching. Save 60-90% on Claude, GPT & Gemini API costs with one line of code.
Context compiler for agentic AI — token budgets, cache-aware adapters, pytest-style eval layer, JIT references. Framework-agnostic, local-first, deterministic
Agentic-AI framework w/o the headaches
