File contents Roadmap
This document outlines the development roadmap for OpenViking.
Completed Features
Core Infrastructure
Three-layer information model (L0/L1/L2)
Viking URI addressing system
Dual-layer storage (AGFS + Vector Index)
Async/Sync client support
Resource Management
Text resource management (Markdown, HTML, PDF)
Automatic L0/L1 generation
Semantic search with vector indexing
Resource relations and linking
Retrieval
Basic semantic search (find)
Context-aware search with intent analysis (search)
Session-based query expansion
Reranking pipeline
Session Management
Conversation state tracking
Context and skill usage tracking
Automatic memory extraction
Memory deduplication with LLM
Session archiving and compression
Skills
Skill definition and storage
MCP tool auto-conversion
Skill search and retrieval
Configuration
Pluggable embedding providers
Pluggable LLM providers
YAML-based configuration
Server & Client Architecture
HTTP Server (FastAPI)
Python HTTP Client
API Key authentication
Client abstraction layer (LocalClient / HTTPClient)
Future Plans
CLI
Complete command-line interface for all operations
Distributed storage backend
Multi-modal Support
Intelligent parsing and access for multi-modal resources (images, video, audio, etc.)
Directory storage structure for multi-modal resources
Context Management
Propagation updates when context is modified
Version management and rollback for context (git-like)
Resource Node Access Control
Multi-Agent / Multi-User support
Role-based isolation design
Access control and permission design for resource directory nodes
Ecosystem Integration
Popular Agent framework adapters
Plugin system for custom components
We welcome suggestions and feedback in issues.
Contributing
We welcome contributions to help achieve these goals. See Contributing for guidelines.
1 --- 2 name: 2710-03-roadmap-e2d1b116 3 description: Roadmap 4 --- 5 # Roadmap 6 7 This document outlines the development roadmap for OpenViking. 8 9 ## Completed Features 10 11 ### Core Infrastructure 12 - Three-layer information model (L0/L1/L2) 13 - Viking URI addressing system 14 - Dual-layer storage (AGFS + Vector Index) 15 - Async/Sync client support 16 17 ### Resource Management 18 - Text resource management (Markdown, HTML, PDF) 19 - Automatic L0/L1 generation 20 - Semantic search with vector indexing 21 - Resource relations and linking 22 23 ### Retrieval 24 - Basic semantic search (`find`) 25 - Context-aware search with intent analysis (`search`) 26 - Session-based query expansion 27 - Reranking pipeline 28 29 ### Session Management 30 - Conversation state tracking 31 - Context and skill usage tracking 32 - Automatic memory extraction 33 - Memory deduplication with LLM 34 - Session archiving and compression 35 36 ### Skills 37 - Skill definition and storage 38 - MCP tool auto-conversion 39 - Skill search and retrieval 40 41 ### Configuration 42 - Pluggable embedding providers 43 - Pluggable LLM providers 44 - YAML-based configuration 45 46 ### Server & Client Architecture 47 - HTTP Server (FastAPI) 48 - Python HTTP Client 49 - API Key authentication 50 - Client abstraction layer (LocalClient / HTTPClient) 51 52 --- 53 54 ## Future Plans 55 56 ### CLI 57 - Complete command-line interface for all operations 58 - Distributed storage backend 59 60 ### Multi-modal Support 61 - Intelligent parsing and access for multi-modal resources (images, video, audio, etc.) 62 - Directory storage structure for multi-modal resources 63 64 ### Context Management 65 - Propagation updates when context is modified 66 - Version management and rollback for context (git-like) 67 68 ### Resource Node Access Control 69 - Multi-Agent / Multi-User support 70 - Role-based isolation design 71 - Access control and permission design for resource directory nodes 72 73 ### Ecosystem Integration 74 - Popular Agent framework adapters 75 - Plugin system for custom components 76 77 We welcome suggestions and feedback in issues. 78 79 --- 80 81 ## Contributing 82 83 We welcome contributions to help achieve these goals. See [Contributing](contributing.md) for guidelines.
commit 7719966b2a
Frequently asked questions How do I install the 2710 03 Roadmap E2d1b116 skill? Run npx skillmds@latest add tools-only/2710-03-roadmap-e2d1b116 in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.
What does the 2710 03 Roadmap E2d1b116 skill do? Roadmap It is listed under Product & Planning on SkillMD.
Is 2710 03 Roadmap E2d1b116 safe to use? This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.
Which AI agents work with 2710 03 Roadmap E2d1b116? This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.
Is 2710 03 Roadmap E2d1b116 free to use? Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.
Who published 2710 03 Roadmap E2d1b116? tools-only (@tools-only) published this skill. Their other Agent Skills are listed on their SkillMD profile.
tools-only