Mindstone Rebel

AI workspace for agents that know your work and ask first

Productivity

Developer Tools

Artificial Intelligence

GitHub

Visit WebsiteSee on Product HuntGithub ⧉

@melissanthi_papacharalampous1 The “ask first” layer is the strongest part for me. Agents become much more useful when they can work freely on low-risk tasks, but pause before actions that touch email, shared spaces, or anything sensitive. That middle ground between locked-down and fully autonomous feels like where real trust starts.

If I’m understanding this right, the local-first/customisable thing makes sense, especially if the point is not getting stuck inside one AI vendor’s way of working.

One thing I’m wondering though is what happens once this moves from one person using it to a small team using it. If people start adapting their own workflows, connectors and approval rules, do you risk everyone ending up with slightly different ways of working?

Is there a way to share the setups that work well without making it feel like one central locked-down workspace again? Curious how you’re thinking about that.

The planner/worker/background-safety-classifier split is a genuinely interesting routing decision. When the safety classifier and planner disagree on risk - does planner intent override a conservative flag, or does the classifier always win?

What kinds of actions can Rebel actually execute today, like email and calendar, or internal app automations?

"Ask first" is probably the right default. The challenge is that the more context an agent has, the more confident people become in its actions. Have you found a point where users start approving things without really reviewing them? Curious how you're thinking about trust calibration over time.

"For all of it, not one task" is the right framing, most AI tools

optimize for single workflows and break the moment your work spans

multiple systems.

How does Rebel decide what needs approval vs what can run autonomously?

The friction between trust and speed is where most agentic tools either

slow you down or scare you.

Congrats to the whole Mindstone team, this is a serious piece of work! Really like the approval layer being impact-aware, writing to a shared space treated as riskier than a private one is the kind of detail most agent tools never bother with. We've been building an agent that takes real actions and know the gate is the hardest thing to get right, too loose and its dangerous, too tight and nobody uses it. Rebel learns rules from approvals instead of re-asking forever and you clearly ran this on a lot of real work - very impressive. Another great thing is tool-level permissions like an email MCP that can draft but not send - IMO exactly the granularity people actually need. Nicely done!

The 'asks first' framing is smart — most AI agents just barge ahead and you find out later it did the wrong thing. Is this confirmation step configurable, or always-on by default?

Tried out Rebel across our internal ops and the approval gating is the part that actually changed how we work — most agent setups force you to choose between "full autonomy and pray" or "so locked down it's useless," and the ask-first middle ground is what finally let us point agents at real workflows instead of toy demos. The fact that it's aware of the original query when deciding what's risky (sending an email is fine if I asked for it, sketchy if I asked for research) is a small detail that removes a ton of approval fatigue in practice. Pairing that with model choice + local-first means we're not re-architecting every time a provider changes pricing or limits. Genuinely useful! thanks

Strong angle, and the maker replies show you've thought about the hard part. One thing I'd add from doing this on customer-facing work: the risk with ask-first isn't only where you draw the line, it's approval fatigue. If the agent interrupts too often, people start rubber-stamping every prompt and the gate quietly stops protecting anything. Two things seem to matter most: making each approval information-rich enough to decide in a couple of seconds (what it's about to do, why, and the source it's acting on), and the auto-updating rules you mentioned so it stops re-asking about things someone has already approved a dozen times. Get those right and ask-first scales; get them wrong and it becomes click-through noise. Curious whether Rebel surfaces the "why" and the source inline at the approval moment. Congrats on the launch.

the approval checks for sensitive actions is something more agent tools should be doing. most platforms either give the agent full access or keep it so restricted it can't do anything useful. that middle ground where the agent works freely on low risk stuff but pauses for human approval on anything sensitive is how you actually get teams to trust agents with real workflows. curious how granular the approval rules are, can you set different thresholds per agent or per action type?

The ask-first posture is important. For small teams, the useful split is usually reversible vs irreversible actions: summarize, draft, search, and organize can move fast; writes to customers, CRM, payments, deploys, or files that other systems trust need a visible checkpoint and a trace.

The 'ask first' principle is something we've had real debates about internally. Autonomous agents that act without confirmation can compound errors in ways that are hard to recover from, especially in stateful workflows. What's your approach to calibrating when the agent should interrupt vs. proceed? Does it use confidence thresholds, or is it more rule-based?

Nice approach. How's conflicting context handled when agents pull from multiple different projects?

Love the Fair Source approach. Curious why did you choose fair source over fully open source for Rebel, and what feedback have you received so far from developers?

Since it's local-first with model choice, can the approval checks for sensitive actions run entirely on a local model, or does the gating logic still require a cloud model call?

where exactly do you draw the line between what a small team can adapt freely vs what needs a commercial licence? Asking because that clarity is usually what makes or breaks adoption for us.

My favourite thing about Rebel is the way the memory works - learns as you go, and shares its memories with other Rebels (e.g. throughout your company).

The interesting part is how it works to judge which memories should be shared and with whom, and which should be kept private. And it asks if it's unsure.

A bit of personal context on why I care about this so much.

I don't use Rebel as a demo environment. I run a large part of my work through it.

Most days, that means speaking rather than typing: meeting prep before important calls, catching the follow-ups I would otherwise delay, pulling together context from email, calendar, Slack, docs and old conversations, drafting things in my voice, and challenging assumptions before something goes to a customer, investor or the team.

The shift for me has not just been "the same work faster", but more that I can now do work at the level I always wanted, but often did not have the time or attention for. Better prep. Better follow-through. More context. Less living out of my head.

This is also why fair source matters to me.

If an agent is going to sit this close to my actual work (memory, tools, approvals, the messy context of their day) trust cannot just be a brand promise. People should be able to inspect it, run it themselves, and understand the boundaries.

Rebel started as my own operating system for work, and I wouldn't be able to do my job without it today. Opening it up feels like the right next step.