Wiki Memory

Karpathy's LLM Wiki as Agent Memory - Agentic AI Foundation (AAIF)

At work, I’m building agents to handle various operational tasks and have found Karpathy’s LLM Wiki design to be an excellent solution for implementing most ty…

The Shape of Memory Benchmarks

Why the familiar memory benchmarks are outdated, how the agent-native work looks today and why design your own.

Jürgen Leschner on Twitter / X

Making organizational memories == agent memories is the unlock. https://t.co/Tk9fV17iny— Jürgen Leschner (@jldec) July 28, 2025

Agent Memory Patterns

A short HOW TO guide for agent memory systems. Especially the difference between blocks, files and skills.

Memory Models: Towards Agents That Learn

Agents that truly learn from experience will be powered by memory models: models that create and curate token-space memory across model generations, trained with memory-native RL.

Building napkin - a memory system for agents

A decade of information retrieval and three years of agent harness engineering, poured into a local-first knowledge system that avoids vector search entirely.

LLM Wiki v2 — extending Karpathy's LLM Wiki pattern with lessons from building agentmemory

LLM Wiki v2 — extending Karpathy's LLM Wiki pattern with lessons from building agentmemory · GitHub

AI Agent Memory: Complete Guide & Architecture

AI agent memory: what it is, how it works, architecture, memory types, and how to add persistent long-term context.

Ambient Associative Memory

Most agent memory waits to be queried. Ambient memory runs on every tool call — past lessons surface on their own, no rules list required.

A-MEM: Agentic Memory for LLM Agents

While large language model (LLM) agents can effectively use external tools for complex real-world tasks, they require memory systems to leverage historical experiences. Current memory systems enable basic storage and retrieval but lack sophisticated memory organization, despite recent attempts to incorporate graph databases. Moreover, these systems' fixed operations and structures limit their adaptability across diverse tasks. To address this limitation, this paper proposes a novel agentic memory system for LLM agents that can dynamically organize memories in an agentic way. Following the basic principles of the Zettelkasten method, we designed our memory system to create interconnected knowledge networks through dynamic indexing and linking. When a new memory is added, we generate a comprehensive note containing multiple structured attributes, including contextual descriptions, keywords, and tags. The system then analyzes historical memories to identify relevant connections, establishing links where meaningful similarities exist. Additionally, this process enables memory evolution - as new memories are integrated, they can trigger updates to the contextual representations and attributes of existing historical memories, allowing the memory network to continuously refine its understanding. Our approach combines the structured organization principles of Zettelkasten with the flexibility of agent-driven decision making, allowing for more adaptive and context-aware memory management. Empirical experiments on six foundation models show superior improvement against existing SOTA baselines. The source code for evaluating performance is available at https://github.com/WujiangXu/A-mem, while the source code of the agentic memory system is available at https://github.com/WujiangXu/A-mem-sys.

robot.wtf — Memory for agents in a wiki for humans

Free, git-backed wiki hosting with native MCP support and semantic search. Sign in with Bluesky, create a wiki, connect your AI agents.

Persona

A user-memory system for AI agents. 2022–2026. Memory is going beyond schemas, ontologies, Graph RAG, and vector DBs — computers can talk now.

Why AI Coding Agents Forget — And How ArcticMem Fixes It

Explore ArcticMem, Snowflake’s persistent semantic memory system for AI coding agents. See how dual-tier memory improves benchmark pass rates to 73%.