Lifecycle-Aware Memory for long-horizon LLM agents — 66.05% on PaperBench, 94.66% on SurveyBench, 10 peer-reviewed acceptances at FSE/ICML/TOSEM/AEI/ICoGB
Categories & Topics
Repository Stats
Related Tools
agentic-stack
One brain, many harnesses. Portable .agent/ folder (memory + skills + protocols) that plugs into Claude Code, Cursor, Windsurf, OpenCode, OpenClaw, Hermes, or DIY Python — and keeps its knowledge when you switch.
AlayaWorld
Full-stack open-source interactive long-horizon world model.
awesome-ai-agent-papers
A curated collection of AI agent research papers released in 2026, covering agent engineering, memory, evaluation, workflows, and autonomous systems.
boop-agent
iMessage personal agent: choose Claude Agent SDK (Claude Code) or Codex app-server runtime (Codex/ChatGPT), with memory, sub-agents, automations, integrations.
deep-swe
Measuring frontier coding agents on original, long-horizon engineering tasks
Engram
Engram enhances memory capabilities in large language models by using a scalable lookup method. This approach improves performance and efficiency, making it easier to access and utilize conditional information for various applications.