OpenViking

OpenViking

OpenViking is an open-source context database designed specifically for AI agents.

Agent SkillDevOpen source
Type
Agent Skill
Open source
Yes
GitHub Stars
★ 26.0k
Source
skill-github

Overview

OpenViking is an open-source context database designed for AI agents (such as openclaw). It unifies the management of agent context (memory, resources, and skills) through a filesystem paradigm, enabling hierarchical context passing and self-evolution. Developers can build an agent's 'brain' just like managing local files, solving context fragmentation issues, reducing token consumption, improving retrieval effectiveness, and supporting visualized retrieval traces and automatic session management.

Capabilities

  • Unified management of memory, resources, and skills
  • Hierarchical context loading to reduce token consumption
  • Directory-based recursive retrieval to improve retrieval effectiveness
  • Visualized retrieval traces to observe context
  • Automatic session management for context self-iteration

Use cases

Memory management for AI agentsContext management during long-running tasksContext storage and retrieval in multi-turn conversationsSkill management and invocation for AI agents

Setup

Requires: Python 3.10 或更高版本Rust ToolchainC++ 编译器稳定网络连接
pip install openviking --upgrade --force-reinstall

This information was compiled by AI from public sources and may contain inaccuracies — please refer to the source.

FAQ

Which operating systems does OpenViking support?

Supports Linux, macOS, and Windows.

What model capabilities does OpenViking require?

Requires VLM models and Embedding models.

Related skills