ReasoningBank introduces memory-aware test-time scaling for AI agents by storing reasoning traces from both successes and failures, enabling self-evolution through experience.
The awesome-agent-evolution repo organizes 50+ open-source projects into a clear taxonomy of AI agent self-evolution and infrastructure layers, offering a practical ecosystem map for developers.
LycheeMemory offers a lightweight semantic memory system for LLM agents, cutting token use by 71% and costs by 55% compared to native memory, with SQLite + LanceDB backend and REST/MCP APIs.
