Open Source Agent Memory Tools
Agent memory is the set of methods and systems that let AI agents retain useful information beyond a single interaction. It can preserve conversation details, user preferences, project knowledge, decisions, and prior results, helping agents maintain continuity and avoid repeating work. Memory systems may organize information as searchable records, summaries, knowledge graphs, or other structured context, and retrieve relevant details when needed.
Open source tools in this area range from session-history search and persistent stores to retrieval systems and knowledge graphs. When choosing one, consider how it stores and retrieves data, its integrations with agent frameworks, privacy and deployment requirements, license, documentation, and maintenance activity. These tools can help developers building coding agents, teams creating long-running assistants, and researchers exploring how agents use context over time.
8 repositories · updated September 24, 2026
Utopia: The Open-Source Enterprise World Model for Knowledge Engineering
Utopia is the world's first open-source enterprise world model, built with Rust. It provides a unique foundation for knowledge engineering, featuring a bitemporal knowledge graph that evolves with new information and supports robust reasoning and decision-making. Designed for self-hosting, Utopia offers companies full control over their knowledge foundation and compliance audit trails.
Open Index: A Deterministic Memory Layer for Your AI Agents
Open Index is a powerful tool for building domain-specific, accurate, and structured data that AI agents can effectively operate on. It enables the creation of a "brain," a searchable and continuously improving context graph tailored to any domain. This system ensures agents have access to reliable, up-to-date information, enhancing their capabilities and decision-making processes.
ai-memory: Long-Term Memory Solution for AI Coding Agents
ai-memory is a robust solution providing long-term memory for AI coding agents, enabling seamless handoffs between different agent vendors and machines. It ensures that project knowledge, failed approaches, and open questions persist, facilitating collaborative development and continuous progress across various tools and teams. Built in Rust, this open-source project offers a reliable and transparent way to manage agent memory.
Magic Context: Unbounded, Self-Managing Memory for AI Coding Agents
Magic Context is a powerful GitHub repository that provides unbounded, self-managing memory for AI coding agents. Acting as the 'hippocampus' for agents, it ensures continuous learning and recall across sessions without disruptive context compaction. This tool, part of CortexKit, allows agents to build lasting project knowledge and maintain context efficiently.
deja-vu: Retroactive Memory for AI Coding Agents
deja-vu is a powerful local-first tool that provides retroactive memory for AI coding agents, indexing past coding sessions from various agents, even those from before installation. This Go binary allows agents to recall relevant information without needing an LLM or embeddings by default. It enhances agent performance by providing context at the point of action, preventing repeated mistakes and improving efficiency.
OpenViking: A Self-Evolving Context Database for AI Agents
OpenViking is an open-source context database designed for AI agents, unifying agent memory, knowledge RAG, and skills into a virtual filesystem. It allows agents to browse their context deterministically using familiar commands like `ls` and `tree`. This innovative approach aims to enhance agent performance and reduce token spend by loading content in tiered layers.
Agent-Memory: Persistent Memory for AI Coding Agents
Agent-Memory provides persistent memory for AI coding agents, ensuring they remember past interactions and learned patterns across sessions. Built on the iii engine, it eliminates the need for re-explaining context, significantly improving agent efficiency and reducing token usage. This solution integrates seamlessly with various agents, offering a robust memory management system.
Memori: Agent-Native Memory Infrastructure for LLM Production Systems
Memori provides agent-native memory infrastructure, offering an LLM-agnostic layer that transforms agent execution and conversations into structured, persistent state. Designed for enterprise use, it seamlessly integrates with existing data infrastructure and supports various deployment environments, ensuring robust memory management for AI agents.