Activity2Context-for-openclaw

Name: Activity2Context-for-openclaw
Author: lattice1992

by lattice1992

Verified

Real-time context layer that converts user activity into actionable signals for OpenClaw.

105stars

1forks

PowerShell

Installation

# Add to your Claude Code skills
git clone https://github.com/lattice1992/Activity2Context-for-openclaw

Getting Started

Guides for using ai agents skills like Activity2Context-for-openclaw.

Caveman: Cut Claude Token Use by 65%
How agent-side prompt compression works, when to use it, and when not to.
What is an AI Skills Marketplace?
Definitions, how marketplaces work, and how to choose between them in 2026.
Getting Started with AI Skills

Security ReportVerified

Last scanned: 5/30/2026

{
  "issues": [],
  "status": "PASSED",
  "scannedAt": "2026-05-30T16:57:33.476Z",
  "npmAuditRan": true,
  "pipAuditRan": true
}

README.md

Frequently Asked Questions

What is Activity2Context-for-openclaw?

Activity2Context-for-openclaw is an open-source ai agents skill for AI coding assistants such as Claude Code, Codex CLI, and ChatGPT, built by lattice1992. Real-time context layer that converts user activity into actionable signals for OpenClaw. It has 105 GitHub stars.

Is Activity2Context-for-openclaw safe to use?

Yes. Activity2Context-for-openclaw passed SkillsLLM's automated security scan — a dependency vulnerability audit plus prompt-injection heuristics — with no high-severity issues. You can read the full report in the Security Report section on this page.

How do I install Activity2Context-for-openclaw?

Clone the repository with "git clone https://github.com/lattice1992/Activity2Context-for-openclaw" and add it to your Claude Code skills directory (see the Installation section above).

What programming language is Activity2Context-for-openclaw written in?

Activity2Context-for-openclaw is primarily written in PowerShell. It is open-source under lattice1992 on GitHub, so you can review or fork the full source.

Are there alternatives to Activity2Context-for-openclaw?

Yes. SkillsLLM lists many other AI Agents skills you can browse and compare side by side. Open the AI Agents category from the badge at the top of this page, or use the Related Skills and comparison links further down to weigh Activity2Context-for-openclaw against similar tools.

Agentic AI for Beginners

Build your first AI agent from scratch - tool use, ReAct pattern, memory, deployment

41 minBeginner

Comments (0)

to leave a comment.

No comments yet. Be the first to share your thoughts!

Related Skills

superpowers

by obra

An agentic skills framework & software development methodology that works.

234,966

vorn AuraPlayer

Activity2Context for OpenClaw

Chinese version: README.zh-CN.md

Imagine an agent that can "see what you see and track what you do."

When you want fast execution, you only provide the goal. You do not need to repeatedly feed background context every turn.

What problem does it solve?

Context gaps: you just edited files and read pages, but the agent does not know.
Repetitive briefing: you keep re-explaining what you were doing.
Token waste: raw behavior logs are noisy and expensive if sent directly to models.

How it works

Activity2Context is a Runtime Hook, not a Skill.

Pipeline:

Capture: continuously record local activity (browser, document, app).
Aggregate: compress raw streams into structured entities.
Inject: before each chat turn, inject activity2context/memory.md into the OpenClaw system prompt.

What is captured (current)

Browser: page title, URL, focus duration, last active time.
Document: file path, edit count, last active time.
App: app name, window title, focus duration, last active time.

Outputs:

Raw stream: <workspace>/.openclaw/activity2context_behavior.md
Injected memory: <workspace>/activity2context/memory.md
Structured memory: <workspace>/activity2context/memory.semantic.json

Common concerns

1) Will token cost increase a lot?

Usually no. Only aggregated memory.md is injected, not full raw logs. Entity count is capped and ranked by recency/activity.

2) Is it safe for privacy?

By default, data is generated and stored locally. However, if you use cloud models, injected memory.md content is sent with prompts to your model provider. For sensitive environments, prefer local models or narrower capture scope.

3) Will it hurt performance?

The runtime is lightweight (polling + periodic aggregation). Raw logs are capped and trimmed, preventing unbounded I/O growth.

4) Will the logs grow indefinitely??

Raw log cap: observer.maxBehaviorLines (default 5000).
Auto-trim on startup to keep only the latest N lines.
Injected file is aggregated memory, not full raw logs.

Quick Start (Windows)

From repo root:

powershell -ExecutionPolicy Bypass -File .\install\windows\install.ps1 -Workspace "$PWD"

If your OpenClaw workspace is different from the current folder:

powershell -ExecutionPolicy Bypass -File .\install\windows\install.ps1 -Workspace "C:\path\to\your\workspace"

Control commands:

$env:USERPROFILE\.activity2context\activity2context.cmd status
$env:USERPROFILE\.activity2context\activity2context.cmd start
$env:USERPROFILE\.activity2context\activity2context.cmd stop
$env:USERPROFILE\.activity2context\activity2context.cmd index

Quick Start (macOS)

From repo root:

bash ./install/macos/install.sh --workspace "$PWD"

Control commands:

~/.activity2context/activity2context status
~/.activity2context/activity2context start
~/.activity2context/activity2context stop
~/.activity2context/activity2context index

Required macOS permissions:

Accessibility (foreground app/window detection)
Automation (read Chrome/Edge/Brave/Safari URL)
Python 3 (/usr/bin/python3)

OpenClaw Integration (core)

You only need memory.md injection. No Skill file is required.

openclaw config set hooks.internal.enabled true --strict-json
openclaw config set hooks.internal.entries.bootstrap-extra-files.enabled true --strict-json
openclaw config set "hooks.internal.entries.bootstrap-extra-files.paths[0]" "activity2context/memory.md"

More details: integrations/openclaw/README.md

Configuration

Config file:

~/.activity2context/config.json

Templates:

config/activity2context.example.json
config/activity2context.macos.example.json

Key parameters:

observer.pollSeconds
observer.browserThreshold
observer.browserUpdateInterval
observer.appThreshold
observer.appUpdateInterval
observer.maxBehaviorLines (default 5000)
indexer.intervalSeconds
indexer.minDurationSeconds
indexer.maxAgeMinutes
indexer.maxTotal
indexer.maxWeb
indexer.maxDoc
indexer.maxApp
indexer.semanticOutput (structured JSON output path)
indexer.appAliases (normalize process names, optional type hints)

Uninstall

Windows:

powershell -ExecutionPolicy Bypass -File .\install\windows\uninstall.ps1

macOS:

bash ./install/macos/uninstall.sh

Keep data but remove runtime:

powershell -ExecutionPolicy Bypass -File .\install\windows\uninstall.ps1 -KeepData

bash ./install/macos/uninstall.sh --keep-data