Skip to content

Releases: BADJAB22/leo-optima

v1.0.26: The Intelligent LLM Cost-Reduction Layer

17 Feb 03:04
@BADJAB22BADJAB22
v1.0.26
6707d21

Choose a tag to compare

View all tags
v1.0.26: The Intelligent LLM Cost-Reduction Layer Latest
Latest

🦁 LEO Optima v1.0.26

We are excited to announce the official release of LEO Optima v1.0.26! This version solidifies the core engine as a robust, production-ready orchestration layer for your AI stack.

🚀 Key Features

  • Adaptive Semantic Cache: Slashes latency and costs by serving semantically similar queries from a local vector store.
  • Request Deduplication: Automatically batches concurrent identical requests to prevent redundant API calls.
  • Prompt Slimming: Intelligent NLP-based token reduction to save on input costs without losing context.
  • Multi-Provider Support: Unified interface for OpenAI, Anthropic, Gemini, and local LLMs.
  • Byzantine Consensus: Cross-model verification for high-stakes queries to ensure maximum reliability.
  • Kadropic Analytics Dashboard: Real-time monitoring of USD savings, token optimization, and routing intelligence.

🛠️ Installation

git clone https://github.com/BADJAB22/leo-optima.git
cd leo-optima
docker compose up --build -d

🔌 Integration

Change your base_url to http://localhost:8000/v1 and start saving immediately!

Maintained by Kadropic Labs.
Built with precision for the global developer community.

Assets 2
Loading