volcengine/OpenViking
OpenViking is an open-source context database designed specifically for AI Agents(such as openclaw). OpenViking unifies the management of context (memory, resources, and skills) that Agents need through a file system paradigm, enabling hierarchical context delivery and self-evolving.
Building AI Agents often means wrestling with fragmented memories, resources, and skills. OpenViking addresses this by providing a unified 'context database' that organizes all the information your AI Agent needs, much like a file system. It helps developers who are creating sophisticated AI Agents to manage and deliver context efficiently, making their Agents smarter and more capable.
7,606 stars. Used by 1 other package. Actively maintained with 376 commits in the last 30 days. Available on PyPI.
Use this if you are developing AI Agents and struggle with organizing and delivering the various types of context (like memory, skills, and data) your agents need to perform complex, long-running tasks.
Not ideal if you are looking for a general-purpose database or a traditional vector database for simple information retrieval without the complexities of AI Agent context management.
Stars
7,606
Forks
541
Language
Python
License
Apache-2.0
Category
Last pushed
Mar 13, 2026
Commits (30d)
376
Dependencies
38
Reverse dependents
1
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/rag/volcengine/OpenViking"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Featured in
Recent Releases
Related tools
MemoriLabs/Memori
SQL Native Memory Layer for LLMs, AI Agents & Multi-Agent Systems
mem0ai/mem0
Universal memory layer for AI Agents
zjunlp/LightMem
[ICLR 2026] LightMem: Lightweight and Efficient Memory-Augmented Generation
MemTensor/MemOS
AI memory OS for LLM and Agent systems(moltbot,clawdbot,openclaw), enabling persistent Skill...
agentscope-ai/ReMe
ReMe: Memory Management Kit for Agents - Remember Me, Refine Me.