Contextberg

Turn your work into AI agent memory, served over MCP

Productivity

Time Tracking

Artificial Intelligence

Visit WebsiteSee on Product Hunt

Congrats, @screenest_ai. Persistent memory for agents is the piece nobody's solved cleanly yet. Most workflows still require you to re-explain the whole codebase every new session. The passive capture approach makes sense, but I keep thinking about what gets indexed. If it's pulling from all your open files in the background, there has to be some kind of data boundary. Does the memory stay local, or does it leave the machine at any point?

The MCP angle is smart , instead of re-explaining context every session, agents just pull what they need. Curious how Contextberg handles sensitive data that shows up in screen recordings, like passwords or private chats. Also wondering if there's any control over what gets stored vs ignored. This could genuinely change how I use Claude Code day-to-day.

The five-sensor architecture is thoughtfully constructed, and I can see why each signal was included. The keystroke layer in particular raises an interesting design tension that I'd love to understand better.

Screenshots, browser history, app usage, and agent conversations already reconstruct a remarkably complete picture of work context. What specific inference does keystroke data enable that the other four sensors cannot provide? I ask because in my experience building internal activity trackers, the keystroke layer consistently became the most contested component in security reviews, even with exclusion rules in place.

I may be missing a nuance in how the keystroke signal gets processed or weighted against the visual and behavioral signals. Would be curious to hear how the team thinks about the marginal utility of keystroke capture relative to its privacy surface.

Local-first with MCP is an interesting architecture choice, but there's a tension worth exploring: MCP servers are process-local, so when Claude Code or Cursor spins up a new session, it reads from Contextberg's MCP endpoint. Does the memory retrieval happen on every session start, or is it query-driven? And how do you handle the case where two different agents (say, Claude Code and Cursor running simultaneously) are both reading from the same memory store, Do they see the same context snapshot, or does Contextberg maintain per-agent memory streams?

Persistent context across agent sessions is one of those things that sounds simple but completely changes what's possible, it's the difference between a smart tool and an actual teammate. The MCP approach is the right bet; curious how you're thinking about privacy boundaries for teams vs. individual devs.

I think memory/context is becoming one of the biggest bottlenecks for AI agents. The model can be smart, but if it forgets the project every session, the user still does the real work.

How do you think guys about privacy and user control with screen/browser history being part of the memory layer?

The passive capture approach is what makes this architecturally different from most memory tools I've seen... instead of explicitly saving context like most MCP memory layers do, Contextberg just watches and builds it automatically. I've been thinking about this exact tradeoff while working on my own memory system: explicit memory gives you cleaner, more intentional retrieval but passive capture catches the stuff you'd never think to save yourself.

Curious how you're handling the signal-to-noise problem though.. screen and browser history is extremely noisy. Are you doing any relevance filtering before storing, or does everything go in and the retrieval layer handles pruning? Because in my experience with ChromaDB retrieval, garbage-in-garbage-out hits hard when the vector store gets polluted with irrelevant chunks.

Interesting idea, especially the focus on Windows developers since most AI memory tools seem Mac-first. One thing I’m curious about: how are privacy and data controls handled when Contextberg watches screens, browser history, and agent conversations? It would be useful to have very granular controls over what gets stored or excluded.