First-Person Agent Memory Bench. 10 Categories including fact recall, multi-hop links, temporal reasoning, fact overwrites, speaker traps, refusal, credibility, and agentic tool usage. 540K token / 60 session corpus, all in first person. Dynamic output-answer-key portion. Comprehensive report with visuals and miss breakdown.
Cross-referenced across 55 tracked directories
#2875
Popularity Rank
1 / 55
Listed In
Emerging
Adoption Stage
8/26/2026
Created
10
GitHub Stars
8/27/2026
Last Commit
Recently added to the ecosystem
bytedance
The Open-Source Multimodal AI Agent Stack: Connecting Cutting-Edge AI Models and Agent Infra
Erick Friis <[email protected]>
Building applications with LLMs through composability
Joao Moura <[email protected]>
Cutting-edge framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks.
...moreIan Webster <[email protected]>
Python wrapper for the promptfoo CLI - LLM testing, red teaming, and security evaluation