Curated systems, benchmarks, and papers etc. on memory for LLMs/MLLMs --- long-term context, retrieval, and reasoning.
On-device context engine and memory for AI agents. Claude Code and OpenClaw. Hooks + MCP server + hybrid RAG search.
🌿 Prune your AI agent's context window. Reduce token usage by 70-95% with hierarchical memory. Replace flat MEMORY.md with a bonsai-shaped domain tree. Progressive disclosure, zero dependencies. Works with OpenClaw and any LLM agent framework.
Get started with Novyx Core in 5 minutes
Optimize AI agents' context by pruning and structuring memory hierarchies to reduce token use and improve efficiency across LLM frameworks.
Context hygiene for agentic coding. Save and resume Claude Code/Codex sessions.
Desktop Extension for Novyx MCP — one-click install for Claude Desktop
Persistent memory for OpenClaw agents with time-travel rollback, audit trails, and knowledge graph. The only memory skill where you can undo mistakes.
An open-source notes app where your AI actually remembers you. Markdown, wiki-links, knowledge graph, voice capture, 18+ AI providers, persistent memory. Desktop + cloud.
Persistent memory system for Claude Code. One SQLite file, one mind.
Secure memory & context optimization MCP plugin for Claude Code. Drop-in replacement for context-mode with credential isolation, SSRF protection, MemGPT-style persistent memory, and hybrid BM25+vector search. 77 security tests, zero cloud sync.
Novyx Core documentation — docs.novyxlabs.com
🧠 Enhance AI agents with long-term memory and self-evolution using this lightweight, high-performance knowledge base middleware built in Go.
🧠 Discover and explore memory mechanisms for Large and Multimodal Language Models through curated systems, benchmarks, and research papers.
Add a description, image, and links to the ai-agent-memory topic page so that developers can more easily learn about it.
To associate your repository with the ai-agent-memory topic, visit your repo's landing page and select "manage topics."