zjunlp/MemTrace

Comprehensive LLM Error Analysis and Reporting

AgenTracer: A Lightweight Failure Attributor for Agentic Systems

Open-source evaluation suite for memory-augmented LLM systems

Code for MemoryBench: A Benchmark for Memory and Continual Learning in LLM Systems

The official repo of the paper: $delta$-mem: Efficient Online Memory for Large Language Models

Evaluation and Tracking for LLM Experiments and AI Agents

Mapping out the "memory" of neural nets with data attribution

GateMem: a benchmark and evaluation toolkit for memory governance in multi-principal shared-memory LLM agents.