lattice1992

lattice1992 / Activity2Context-for-openclaw

Public

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

ai-agent context-awareness context-engineering context-injection llm
30
11
89% credibility
Found Mar 26, 2026 at 30 stars -- GitGems finds repos before they trend. Get early access to the next one.
Sign Up Free
AI Analysis
PowerShell
AI Summary

Activity2Context monitors macOS user activities like browser tabs, app usage, and document changes to generate a concise summary injected into OpenClaw AI prompts for better context awareness.

How It Works

1
📰 Discover the helper

You hear about Activity2Context, a quiet background tool that helps your AI assistant remember what you've been doing on your computer without you repeating yourself.

2
📥 Get it ready

Download the folder and run the simple Mac setup script to place it on your computer.

3
🔧 Allow watching

Give your Mac permission to notice which apps, web pages, and files you're using, so it can track your recent work safely.

4
🔗 Link to your AI

Tell your OpenClaw AI to include the activity summary in its chats, like adding a helpful note.

5
▶️ Turn it on

Start the watcher with a simple command, and it runs quietly, building a short list of your recent focuses.

🎉 Smarter chats

Now your AI knows you've been reading docs or editing files, saving you time and making conversations flow naturally.

Sign up to see the full architecture

4 more

Sign Up Free

Star Growth

See how this repo grew from 30 to 30 stars Sign Up Free
Repurpose This Repo

Repurpose is a Pro feature

Generate ready-to-use prompts for X threads, LinkedIn posts, blog posts, YouTube scripts, and more -- with full repo context baked in.

Unlock Repurpose
AI-Generated Review

What is Activity2Context-for-openclaw?

This PowerShell repo builds a real-time context engine for OpenClaw, capturing your browser tabs, document edits, and app focus to generate concise activity summaries. It solves context gaps in agent chats—no more repeating what you just read or edited—by injecting a capped "memory.md" file into OpenClaw prompts via hooks. Install via bash on macOS or PowerShell on Windows, then control it with CLI commands like start, stop, status, and index.

Why is it gaining traction?

Unlike verbose logging tools, it aggregates noisy activity into ranked, token-efficient signals, keeping prompts lean while delivering real-time context awareness. Developers dig the always-on runtime that works without skills or per-turn feeds, plus semantic JSON for tools. At 30 stars, it's pulling interest on real time GitHub for OpenClaw users tired of blind agents.

Who should use this?

OpenClaw builders on macOS needing real-time context for coding sessions, like tracking VS Code edits or Stack Overflow reads during debugging. Agent hackers integrating local activity into prompts for tourism recommenders or surgery sims. Skip if you're on Linux or prefer cloud telemetry.

Verdict

Solid early experiment for OpenClaw context injection—great docs and config tuning—but low 0.9% credibility score and 30 stars signal immaturity; test in non-prod first. Worth a spin if you're deep in real-time context projects. (198 words)

Sign up to read the full AI review Sign Up Free

Similar repos coming soon.