TiDB X is an object-storage-native, elastic, and multi-tenant SQL engine designed specifically for AI agent workloads with query-based billing.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install tidb-x
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install tidb-x using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is TiDB X?
TiDB X represents a shift in database architecture designed for the AI era, where context and agent memory become structured data. It is a distributed SQL engine that uses S3 object storage as its primary source of truth, offering infinite scalability and high durability. For developers building with Openclaw Skills, TiDB X provides a MySQL-compatible interface that handles everything from session context to multi-agent coordination without the complexity of traditional database management.
This system is built for high-concurrency and bursty traffic patterns typical of autonomous agents. By decoupling compute from storage, it allows for stateless scaling and provides a unique Request Unit (RU) billing model. This ensures that your Openclaw Skills only incur costs when queries are actually executed, making it perfect for sprawling agentic ecosystems where many databases might sit idle for periods.
TiDB X Use Cases
- Persistent agent memory for support bots and personal assistants
- Append-only session context storage for long-running coding or research tasks
- Multi-agent task queues to prevent duplicate work in parallel workflows
- Auditable decision logging for explainable AI and provenance tracking
- Real-time blockchain event indexing and DeFi portfolio tracking for Web3 agents
How TiDB X Works
- The AI agent or application sends a standard MySQL-compatible SQL query to a stateless TiDB Server.
- The TiDB Server parses and optimizes the query, utilizing a TiKV hot cache to ensure fast acknowledgment of writes.
- Data is persisted to S3 Object Storage, which serves as the durable, infinite source of truth for the entire system.
- Background tasks such as compaction and DDL operations are handled by an isolated pool, ensuring they never block active queries.
- The system utilizes RU metering to attribute costs per query, ensuring efficient resource utilization for all Openclaw Skills.
TiDB X Setup
To provision a free, ephemeral TiDB Cloud Zero instance for testing your Openclaw Skills, run the following command:
curl -s -X POST "https://zero.tidbapi.com/v1alpha1/instances" -H "Content-Type: application/json" -d '{"tag":"my-agent"}' | tee tidb-zero.json
To install this skill into your local environment, use:
mkdir -p ~/.openclaw/skills/tidb-x && curl -so ~/.openclaw/skills/tidb-x/SKILL.md https://raw.githubusercontent.com/siddontang/tidb-x-skill/main/SKILL.md
TiDB X Data Schema & Taxonomy
TiDB X organizes data using standard relational tables with enhanced JSON support for flexible agent metadata. Below are common schemas used in Openclaw Skills implementation:
| Table Name | Purpose | Key Columns |
|---|---|---|
agent_memory |
Long-term state | tenant_id, content, tags (JSON) |
agent_context |
Session history | session_id, step, type, tokens |
tasks |
Multi-agent queue | task_key, status, claimed_at |
chain_events |
Web3 Indexing | tx_hash, chain, decoded_args (JSON) |
TiDB X Advanced Features
- Pluggable Index Engines (TiCI) supporting Columnar, Inverted, and Vector search for advanced AI retrieval
- Serverless Request Unit (RU) billing for precise cost attribution and zero-cost idling
- Massive DDL performance capable of processing up to 5.53M rows per second
- Multi-tenant isolation for secure data separation across different users or agent instances
- Seamless S3 integration that treats object storage as the primary network backbone rather than just backup
SKILL.md
Loading
Related Openclaw Skills
Claw Memory
A secure, shared persistent memory service designed to help AI agents like OpenClaw store and retrieve context across different sessions and platforms.
Ringg Voice Agent
A high-performance voice automation skill that enables Openclaw agents to make, manage, and analyze AI-powered phone calls via Ringg AI.
Ohio State University API Skill
A comprehensive interface to fetch public data from The Ohio State University Content APIs, including transit, dining, and academic resources.
Apple Calendar CLI
A command-line interface for macOS that enables AI agents to programmatically manage Apple Calendar events using EventKit and structured JSON.
Luna Calorie Tracker
An AI nutrition assistant that uses vision analysis to log calories and macros directly from food photos.
AI Tech Lead & Architect
A sophisticated AI orchestration skill that applies strict Context Engineering and a four-phase methodology to deliver maintainable, secure, and architecturally sound code.
Featured*
