R_REDDYX.XYZ
AITypeScript★ 38

agentic-in/inferoa

Inference Agent Tokenmaxxing

Agentic-in/inferoa is a framework for creating agents optimized for inference with Tokenmaxxing technology, providing high efficiency when working with large language models.

// KEY FEATURES

  • Tokenization with adaptive Tokenmaxxing compression to reduce computational load
  • Flexible TypeScript architecture with plug‑in module support for various LLMs
  • Automatic batching and prompt caching to speed up inference
  • Built-in metrics and real-time performance logging
#agent#agent-harness#agentic-ai#harness-engineering#inference#kvcache#llm#token#tokenmaxxing
Open on GitHub →

New repositories every 30 minutes

REDDYX AI scans GitHub 24/7 and ships the best AI/ML/Web3 projects to Telegram.

Join on Telegram
← Full catalog·Full index

// SIMILAR REPOSITORIES

Llama2 Assembly★ 38Personal AI agent with memory★ 38vLLM for RTX 2080Ti★ 38Self-hosted LLM gateway★ 38Dual-Clock Euler Sampler★ 38Persistent Agent Memory Store★ 38

← FULL CATALOG

agentic-in/inferoa — Inference Agent Tokenmaxxing