Toggle for OpenClaw - Turn your work activity into structured AI context.
by•
The context layer for OpenClaw. Your AI agent finally knows what you've been working on. ToggleX streams structured work context from your browser to your agent — projects, sessions, decisions, intent. Same agent, same prompt, completely different output. No more re-explaining yourself. No stale estimates. Your Claw starts every session knowing exactly where you left off.
5 min setup. 30-day free trial. No card required. Use promo code.
Replies
Hey PH 👋 — Joe (@rolodexter), Aleks, and Matt (@matias_papaleo) here, and we made ToggleX.
We built this because we kept watching @OpenClaw agents give stale, hallucinated recaps of actual work. The agent wasn't dumb — it was blind. No visibility into what had actually happened across sessions.
ToggleX fixes that. It streams real browser sessions into your agent as structured context — projects, focus scores, context switches. Your Claw stops guessing and starts knowing.
The moment it clicked for us: the agent came back with "594 minutes tracked, 519 min work, 75 min breaks — here's exactly what I can't confirm without the API key being set." It knew its own data limits. That's when we knew this was real.
Happy to answer anything — especially from OpenClaw users already running always-on setups. That's exactly who we built this for.
PS One more thing worth mentioning — ToggleX is built by GLIK AI, a privacy-first AI research lab. We're SOC 2 Type 2 in progress, working with Vanta for continuous compliance monitoring. Real-time security posture publicly visible here: https://app.vanta.com/rivalz.ai/trust/8ye1fzqonaxfgotf2l6xr2
@billchirico Sure — here are three concrete ones:
Standup prep: Without ToggleX, ask your Claw "what did I do yesterday?" and it asks you to explain. With ToggleX, it tells you: "3 deep work sessions, 4.8h total, you shipped X, reviewed Y, left Z open" — ready to paste.
Priority management: Without context, your agent gives you a generic framework. With ToggleX, it knows the landing page deploy has been stalled for 2 days and the Kalshi integration has an open bug mid-flow — so it tells you which to close first and why.
Automation discovery: Because ToggleX builds a history of your actual behavior, you can ask "what repetitive stuff am I doing that you could automate?" and your agent finds real patterns — like noticing you manually copy GitHub PR comments into Notion every morning and proposing a pipeline to do it for you.
The common thread: the agent stops asking you for context and starts working from verified state. We’ve got real production screenshots here if you want to see it: https://buff.ly/SldvSLX
💬 Join the beta group: https://buff.ly/MPI2hbm
🔧 ClawHub skill: https://buff.ly/M5gJJ5v
🌐 Landing page: https://buff.ly/bjvycfA
@billchirico just Openclaw seeing what i'm working on is already massive, just tested it out
@billchirico @frertommy That reaction is exactly why we built it. The first time your Claw answers "what did I work on today?" without you typing a word — that's the moment. Would love to hear what it surfaces for you as you use it more. Drop into the beta group if you want to compare notes with others running it: https://buff.ly/MPI2hbm
This is awesome, how well does it understand what i do during the day?
@frertommy Great question. It doesn’t “interpret” you psychologically — it sees structured browser signals in real time (sessions, time spent, context switches, project clusters) and builds a behavioral baseline from that.
So instead of guessing, your agent can reference what actually happened during the day. Same prompt, same model — just grounded in live data. If you’re curious, we’ve got real production screenshots here:
https://buff.ly/SldvSLX
And we’re running a small beta group for OpenClaw users here if you want to poke around or ask deeper questions:
https://buff.ly/MPI2hbm
Would love to have you in there. 🙏🙏
What's the lag behind data consumption by the extension and delivery to the agent?
@aidun Data is collected and sent every 5 minutes, with 1-2 minutes to process. Your agent has fresh, structured context within 5-7 minutes of any activity.
For an always-on context layer, that's a pretty tight loop.
Adjust Page Brightness - Smart Control
you guys will crush it
@kshitij_mishra4 Appreciate it — means a lot on launch week. Try it out and let us know what your agent surfaces. The first session is always the most surprising.
Is there any sensitive data being sent? what does "sessions" means?
is it just the web history being sent?
What if you log into bank website etc?
@stefano_marchetti Great question!
We’re not transmitting full browsing sessions, storing raw page history, or capturing credentials. “Sessions” refers to structured behavioral metadata (e.g., time buckets, tab/domain activity, context switches) — not full page contents or form inputs.
Sensitive domains like banking and private accounts are excluded by design, and the goal isn’t surveillance — it’s generating structured, inspectable context for agent workflows within clear trust boundaries.
Happy to clarify anything more specific.