pluginadvancedOpenCLAW

OpenCLAW v2026.3.7-beta.1: Modular Agent Context with ContextEngine Plugins

The latest OpenCLAW update lets you create smarter AI agents by controlling exactly what information they remember and use. This makes them more efficient and customizable for specific tasks, like customer support, by ensuring the AI always has the right context without needing a complete system rebuild.

AI SETUP PROMPT

Paste into Claude Code or Codex CLI — it will scan your project and set everything up

# Install & Configure: OpenCLAW v2026.3.7-beta.1: Modular Agent Context with ContextEngine Plugins

## What This Is
The latest OpenCLAW update lets you create smarter AI agents by controlling exactly what information they remember and use. This makes them more efficient and customizable for specific tasks, like customer support, by ensuring the AI always has the right context without needing a complete system rebuild.

Source: https://stormy.ai/blog/2026-gtm-playbook-openclaw-ai-agents

## Before You Start

Scan my workspace and analyze:
- The project language, framework, and directory structure
- Existing agent configuration (check for .claude/, .codex/, CLAUDE.md, settings.json, commands/, skills/ directories)

Then ask me before proceeding:
1. Do I need to configure any service credentials for this plugin (database, API keys, etc.)?
2. Should this be project-scoped or global?

## Source Access Note

The source URL (https://stormy.ai/blog/2026-gtm-playbook-openclaw-ai-agents) may not be directly accessible from the terminal. Use the Reference Implementation and Additional Context sections below instead. If you need more details, ask me to paste relevant content from the source.

## What to Implement

This is an **Agent Plugin** — typically an MCP server or capability bundle.

- Install any required npm/pip packages from the source repository
- Register the MCP server in `.claude/settings.json` under the `mcpServers` key with the correct command and args
- Configure any required environment variables or credentials
- Verify the server starts correctly by checking its expected output

## Additional Context

- Scan the user's workspace for an existing OpenCLAW installation. If found, pull the latest changes to update to version v2026.3.7-beta.1. If not found, clone the OpenCLAW repository from its official GitHub source.
- Locate or create the environment configuration file (e.g., .env). Verify the presence of LLM provider API keys (OpenAI, Anthropic, Google, Cohere) and configure OpenCLAW's dual-engine routing. If keys are missing, prompt the user to add them.
- Create a new TypeScript file ('plugins/customContext.ts') to demonstrate the new functionality. Implement a boilerplate ContextEngine plugin that hooks into the 'assemble' lifecycle step, adding a console log to show that custom context processing is being triggered before the prompt is sent to the LLM.

## Guidelines

- Adapt everything to my existing project — do not assume a specific stack or directory layout
- Review any fetched code for safety before installing or executing it
- After setup, run a quick verification and show me a summary of exactly what was installed, where, and how to use it

2,703 charactersCompatible with Claude Code & Codex CLI

MANUAL SETUP STEPS

01Scan the user's workspace for an existing OpenCLAW installation. If found, pull the latest changes to update to version v2026.3.7-beta.1. If not found, clone the OpenCLAW repository from its official GitHub source.
02Locate or create the environment configuration file (e.g., .env). Verify the presence of LLM provider API keys (OpenAI, Anthropic, Google, Cohere) and configure OpenCLAW's dual-engine routing. If keys are missing, prompt the user to add them.
03Create a new TypeScript file ('plugins/customContext.ts') to demonstrate the new functionality. Implement a boilerplate ContextEngine plugin that hooks into the 'assemble' lifecycle step, adding a console log to show that custom context processing is being triggered before the prompt is sent to the LLM.

FIELD OPERATIONS

RAG-powered Documentation Bot

Build an OpenCLAW agent that uses a custom ContextEngine plugin to perform Retrieval-Augmented Generation. The `ingest` hook adds new documents to a vector store, and the `assemble` hook retrieves relevant chunks to add to the prompt context for answering questions about a technical knowledge base.

Long-term Conversation Agent

Develop an agent with a ContextEngine plugin that uses the `compact` hook to summarize the conversation history periodically. This allows the agent to maintain a coherent dialogue over days or weeks without exceeding the model's context window, storing the summaries in a persistent memory.

STRATEGIC APPLICATIONS