Memori launches agent-native persistent memory infrastructure using structured knowledge graphs from agent trace data
By
Gordon Tindall
Needed another two minutes in the oven. A half-baked bagel.
Summary
Memori is a new agent-native memory infrastructure that enables AI agents to create structured, long-term persistent memory directly from agent trace data — including execution paths, tool results, workflow steps, outcomes, and decision-making logic — rather than relying solely on conversation history. It replaces flat markdown memory files with a structured knowledge graph. Benchmark results show 81.95% accuracy on LoCoMo using only 1,294 tokens per query (roughly 5% of full-context cost), saving users 95%+ on inference spend. The project has 15K GitHub stars and 200,000+ downloads.
Key quotes
· 3 pulledMemori brings the long-term persistent memory and unlike traditional memory systems that rely primarily on long-form natural language conversation history, Memori enables agents to automatically create structured, long-term memory directly from the agent trace
Memori replaces flat markdown memory files with a structured knowledge graph that captures facts, decisions, outcomes
81.95% accuracy on LoCoMo using only 1,294 tokens per query, roughly 5% of full-context cost, saving users 95%+ on inference spend
You might also wanna read
YourMemory: Open-source persistent memory layer for AI agents using Ebbinghaus forgetting curve
YourMemory is an open-source persistent memory layer for AI agents that implements Ebbinghaus forgetting curve decay to mimic human memory.
github.com·1mo ago
DiffMem: Git-Based Differential Memory System for AI Agents
DiffMem is a proof-of-concept project that implements a git-based memory storage system for AI agents and conversational systems. It uses Ma
github.com·9mo ago
Robot Memory System Enables AI Robots to Learn from Past Experiences
Robot Memory (robotmem) is a persistent memory system for AI robots that enables robots to learn from past experiences. The system stores ep
github.com·2mo ago
Agent-kernel: Minimal Tool for Adding Stateful Memory to AI Coding Agents
Agent-kernel is a minimal open-source tool that adds stateful memory to AI coding agents. It enables agents to remember conversations betwee
github.com·2mo ago
GibRAM: In-Memory Knowledge Graph Server for RAG and GraphRAG Workflows
GibRAM is an open-source in-memory knowledge graph server designed for retrieval augmented generation (RAG) and GraphRAG workflows. It combi
github.com·4mo ago
δ-mem: A Compact Online Memory Mechanism for Efficient Long-Context LLM Processing
The article presents δ-mem, a lightweight memory mechanism for large language models that augments frozen full-attention backbones with a co
arxiv.org·15d ago