Benchmarking suite for evaluating agentic and roleplay capabilities of small VLLMs
Cross-referenced across 55 tracked directories
#2594
Popularity Rank
1 / 55
Listed In
Emerging
Adoption Stage
9/6/2026
First Seen
Recently added to the ecosystem
A simplified AI Agent framework for learning Claude Code architecture
Unified LLM usage management — API proxy, session diagnostics, multi-CLI orchestration. Mirror Agent open-network DLC.
Zero-to-production AI agent deployment framework
Ambuj Agrawal, Garima Luthra
Universal record-and-replay for LLM agents.