Store secrets, long-term memory, and daily logs in a persistent Convex backend instead of volatile local files.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install convex-backend
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 convex-backend 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 Convex Backend?
The Convex Backend skill provides AI agents with a managed, cloud-based storage layer. By integrating directly with Convex, this skill allows Openclaw Skills to move beyond local file storage, enabling durable agent memory that survives restarts and providing a secure environment for sensitive credentials. It is designed to support both single agents and complex multi-agent orchestrations that require a shared source of truth.
This integration uses the standard Convex MCP server, meaning it can operate independently of any specific management platform while still offering real-time visibility and structured data handling. It ensures that your Openclaw Skills have access to professional-grade backend infrastructure with minimal configuration overhead.
Convex Backend Use Cases
- Persisting agent memory and user preferences across different sessions or container restarts.
- Managing sensitive API keys and tokens securely via cloud-hosted environment variables.
- Maintaining a structured, append-only daily log for audit trails and agent progress tracking.
- Sharing data and secrets across multiple agents working within the same organization or project.
How Convex Backend Works
- The skill establishes a connection using the stock Convex MCP server and validates the local CONVEX_DEPLOY_KEY.
- A preflight check is performed via mcporter to ensure all required tools and schemas are accessible to the runtime.
- The agent deploys the necessary backend components to the user's Convex project to enable custom memory and logging functions.
- During operation, the agent uses the convex.run tool to add facts, preferences, and decisions to long-term memory.
- Secrets are managed through a hierarchical fallback system (Agent-specific > Shared Default) using Convex environment variable tools.
- At the end of each session, the skill automatically generates and appends a summary to the structured daily logs in the cloud.
Convex Backend Setup
To integrate this with your Openclaw Skills, follow these steps:
- Create a Convex account and project at convex.dev.
- Obtain your Development deploy key from the Convex dashboard.
- Add the key to your environment or provide it when prompted:
# Add to your local .env file
CONVEX_DEPLOY_KEY=your_deploy_key_here
CONVEX_DEPLOYMENT=your_deployment_name
- Deploy the required backend components from the skill directory:
cd ~/.openclaw/skills/convex-backend
npx -y convex@latest deploy
- Ensure your MCP configuration includes the Convex server:
{
"mcpServers": {
"convex": {
"command": "npx",
"args": ["-y", "convex@latest", "mcp", "start"]
}
}
}
Convex Backend Data Schema & Taxonomy
The skill organizes data into structured categories to optimize retrieval for Openclaw Skills.
| Data Type | Field | Description |
|---|---|---|
| Memory | type |
Categorized as fact, preference, decision, or note. |
| Memory | content |
The actual string data to be remembered. |
| Memory | tags |
Array of strings for improved searchability and filtering. |
| Daily Logs | date |
ISO format date for session tracking. |
| Daily Logs | content |
Markdown-formatted summary of activities and blockers. |
| Secrets | name |
Prefixed keys (e.g., AGENT_ID_KEY) for environment variable isolation. |
Convex Backend Advanced Features
- Hierarchical Secret Resolution: Automatically falls back from agent-specific overrides to global shared defaults for API keys.
- Automated .env Migration: Offers a safe, two-phase process to move local secrets into the secure Convex cloud backend.
- Custom Logic Extensibility: Supports adding user-defined Convex functions and tables without interfering with the core Openclaw Skills integration logic.
- Smart Continuity: Performs a session startup checklist that loads recent memories and the previous day's log to ensure the agent has immediate context.
- Cron Migration Support: Provides a guided workflow to refactor local background tasks into robust Convex crons.
SKILL.md
Loading
Related Openclaw Skills
LaunchThat OpenClaw Connector
A specialized bridge for connecting OpenClaw VPS instances to LaunchThatBot with secure authentication and event reporting.
Apple Mail Management Expert
An AI-powered assistant for Apple Mail that automates inbox triage, organization, and productivity workflows to help you reach inbox zero.
Apple Mail Skill
A specialized automation skill for AI agents to programmatically access and read emails from the native Apple Mail application on macOS.
Multi-Viewpoint Debates
An AI-driven framework for stress-testing decisions by spawning conflicting agent personas to expose blind spots through debate.
GitOps Team Operations by LaunchThatBot
A role-based GitOps skill that enables AI agents to function as junior contributors or senior maintainers within GitHub repositories.
Convex Backend
A persistent, cloud-based storage solution for AI agent memory, logs, and secrets using a managed Convex backend.
Featured*
