An experiment in giving coding agents long-term memory
Persistent memory for coding agents when Cursor and Devin already dominate this space.
A queryable long-term memory for AI coding agents — the two-tier fix for the context-window wall
Persistent memory for coding agents when Cursor and Devin already dominate this space.
Active memory extraction with GRPO beats passive transcription on LOCOMO benchmarks.
Demand-paging memory for agents beats context window limits that break Cursor and Devin.
Hierarchical scopes let teams share code style rules across agents.
Memory plugin for OpenClaw — useful if you use OpenClaw, which most don't.
File-based AI memory with no databases, but Mem0 and LangChain already do this.