agent memory / context database
OpenViking is a self-evolving context database for AI agents that unifies memory, knowledge RAG, and skills behind a virtual filesystem with tiered (L0/L1/L2) loading and debuggable retrieval trajectories.
Solves the same problem with a different architecture or at a different layer. Expect to rewrite the integration.
choose when you need simple session-capture/compression memory for Claude or agents without a filesystem context model.
Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More
choose for a lightweight, widely-deployed memory API with extraction pipelines rather than a virtual-filesystem context store.
Universal memory layer for AI Agents
choose for an MIT-licensed, benchmark-optimized memory system if you favor permissiveness.
The best-benchmarked open-source AI memory system. And it's free.
choose for knowledge-graph-based long-term memory instead of a file-like context store.
Cognee is the open-source AI memory platform for agents. Give your AI agents persistent long-term memory across sessions with a self-hosted knowledge graph engine.
choose for a fast, locally-hostable memory API with an app UI if you don't need the filesystem protocol.
Memory and context engine + app that is extremely fast, scalable, and can be run fully locally. The Memory API for the AI era.
choose for team-level memory assets with governance rather than a personal context store.
TencentDB Agent Memory is a team-level memory hub for AI Agents — turning conversations, docs, and code into four reusable memory assets (Chat Memory, Skill, LLM-Wiki, Code-Graph) that are governed, shared, and equipped across agents and frameworks.
choose for a Python memory layer that learns from agent trajectories.
Hindsight: Agent Memory That Learns
choose for a serverless, Rust-based single-file memory layer that replaces RAG pipelines.
Memory layer for AI Agents. Replace complex RAG pipelines with a serverless, single-file memory layer. Give your agents instant retrieval and long-term memory.
choose for enterprise-grade structured memory infrastructure rather than a filesystem abstraction.
Memori is agent-native memory infrastructure. A LLM-agnostic layer that turns agent execution and conversation into structured, persistent state for production systems. Built for enterprise, Memori works with the data infrastructure you already run, no rip-and-replace, and deploys across managed cloud, single-tenant cloud, VPC, and on-premises.
choose when local-first Markdown and user-owned portable memory are more important than a virtual filesystem protocol.
One portable memory layer for every AI agent: local-first, Markdown-native, user-owned, and self-evolving across apps, tools, and workflows.
choose for a lightweight memory library when you want to embed stateful memory directly.
Memory library for building stateful agents
choose for a memory management kit from the AgentScope ecosystem.
ReMe: Memory Management Kit for Agents - Remember Me, Refine Me.
choose for a scalable, extensible universal memory layer with flexible storage backends.
Universal memory layer for AI Agents. It provides scalable, extensible, and interoperable memory storage and retrieval to streamline AI agent state management for next-generation autonomous systems.
choose for a research-oriented agentic memory implementation with an MIT license.
A-MEM: Agentic Memory for LLM Agents
choose when you need a JVM-native (Java) memory engine for agents.
Self-evolving cognitive memory and context engine for AI agents in Java. Empowering 24/7 proactive agents like OpenClaw with understanding and SOTA performance.
choose for a TypeScript-first portable memory engine with MCP/CLI adapters.
Portable semantic memory for AI agents: core engine, TypeScript SDK, framework adapters, MCP server, CLI, and host plugins.
choose for a self-evolving memory OS with hybrid retrieval and skill reuse.
Self-evolving memory OS for LLM & AI Agents: ultra-persistent memory, hybrid-retrieval, and cross-task skill reuse, with 35.24% token savings and DeepSeek Harness support.
choose for a simple REST/knowledge-graph persistent memory service exposed via MCP.
Open-source persistent memory for AI agent pipelines (LangGraph, CrewAI, AutoGen) and Claude. REST API + knowledge graph + autonomous consolidation.
An earlier or more limited way to do the job. Still the right call when you need something small, proven, or CPU-only.
choose when you specifically need memory for AI coding agents.
#1 Persistent memory for AI coding agents based on real-world benchmarks
choose when skills, not general RAG/memory, are the primary context you need to store.
Agent Skills as a Memory Layer
choose for a lightweight knowledge-graph memory plugin inside DeepSeek Harness/OpenClaw.
Deepseek Harness、Openclaw知识图谱记忆插件。2026年4月受邀发布在清华大学讨论会。Knowledge Graph + Memory；Knowledge Graph Context Engine for OpenClaw — extracts structured triples from conversations, compresses context 75%, enables cross-session experience reuse
These projects were analysed and named OpenViking among their alternatives. The relationship is not symmetric — how OpenViking rates them is a separate judgement, made when OpenViking is analysed in its own right.
calls OpenViking “Use it if you want an AGPL-3.0 context database that unifies memory, RAG, and skills.”
Memory and context engine + app that is extremely fast, scalable, and can be run fully locally. The Memory API for the AI era.
calls OpenViking “if you want a single self-evolving context database that fuses memory, RAG, and skills.”
TencentDB Agent Memory is a team-level memory hub for AI Agents — turning conversations, docs, and code into four reusable memory assets (Chat Memory, Skill, LLM-Wiki, Code-Graph) that are governed, shared, and equipped across agents and frameworks.
calls OpenViking “Self-evolving context database unifying agent memory, RAG, and skills.”
Self-evolving memory OS for LLM & AI Agents: ultra-persistent memory, hybrid-retrieval, and cross-task skill reuse, with 35.24% token savings and DeepSeek Harness support.
calls OpenViking “Choose it if you want a self-evolving context database that unifies memory, RAG, and skills in one Python package.”
Cognee is the open-source AI memory platform for agents. Give your AI agents persistent long-term memory across sessions with a self-hosted knowledge graph engine.
calls OpenViking “Use if you need a self-evolving Python context database that unifies memory, RAG, and skills at scale.”
#1 Persistent memory for AI coding agents based on real-world benchmarks
calls OpenViking “Choose if you want a single AGPL-licensed context database that unifies memory, knowledge RAG, and skills, rather than a separate memory layer.”
Memori is agent-native memory infrastructure. A LLM-agnostic layer that turns agent execution and conversation into structured, persistent state for production systems. Built for enterprise, Memori works with the data infrastructure you already run, no rip-and-replace, and deploys across managed cloud, single-tenant cloud, VPC, and on-premises.
calls OpenViking “choose it when you want one system that combines agent memory, RAG, and skills.”
One portable memory layer for every AI agent: local-first, Markdown-native, user-owned, and self-evolving across apps, tools, and workflows.
calls OpenViking “Choose when you want a context database that unifies agent memory, knowledge RAG, and skills under AGPL instead of a pure memory library.”
Memory library for building stateful agents