Launched this week
MakersClaw
Hire AI employees that live in your Slack, Teams, Telegram
569 followers
Hire AI employees that live in your Slack, Teams, Telegram
569 followers
Hire AI employees that run 24/7 in their own container with their own memory. One-click into your Slack, Telegram, or Teams. Pre-built for support, sales, research, SEO, or anything you write yourself. Pay per call for the tools they use.
how long-term memory works here? Are agents remembering across weeks/months or just retaining recent context?
MakersClaw
@himani_sah1 Long-term. Memory lives in a postgres-backed store inside each employee's pod and persists indefinitely. A conversation you had three months ago is still retrievable when relevant. This isn't a sliding window of recent context. The retrieval is dynamic. The agent pulls the slice of memory that's relevant to the current message instead of stuffing the whole history into the prompt every time. Files you upload become part of the long-term knowledge too.
GrowMeOrganic
How do you prevent agents from becoming expensive when connected to lots of tools? BTW, congrats on the launch.
MakersClaw
@iamanantgupta Thanks! Two cost dimensions in our setup. Infrastructure (pod and storage) is a flat monthly per employee, predictable regardless of how many tools you connect. Inference is pay-as-you-go from a wallet you top up, at provider cost. Tools themselves don't generate ongoing cost. Cost shows up only when the agent uses one, and even then it's the inference of the decision drawn from the same wallet. You control the ceiling: top up with what you're willing to spend, and the agent works inside that budget.
ConnectMachine
The SEO template caught my attention. Does it actually execute workflows or mostly generate content?
MakersClaw
@syed_shayanur_rahman What the SEO template actually does well is keyword brainstorming, content briefs, topical clustering, competitor analysis (Moltis can use a browser to read competitor pages), and drafting outlines or full articles in your brand voice. It can also schedule and send outreach emails through Gmail or Outlook if you've connected them. The MCP layer is the extension path. So deeper SEO automation (paid SEO APIs, CMS publishing, etc.) becomes available as those MCPs are added.
Congrats on the launch!
If I had to run 20 tasks/day pertaining to PA - would it cost me more than Claude's current API?
MakersClaw
@vishnu_anand1 Honest answer, probably yes, but for a reason.
Direct Claude API costs you only tokens. MakersClaw adds a flat monthly subscription per employee for the infrastructure (the pod, persistent memory, channels, integrations, file system, everything that makes it an agent rather than a raw API). Inference itself is at provider cost.
If you just want 20 prompts a day, Claude API direct is cheaper. If you want those tasks to run on a schedule and stay context-aware across days, that's what the subscription pays for.
@sachinsharma makes sense. Thank you
Asteroid
This looks really cool, congratulations on launching! what's next for your roadmap?
MakersClaw
@joe_hewett Thanks! Two directions we're most excited about.
The skills marketplace keeps compounding as makers publish private and public skills. Every employee on the platform gets sharper as that pool grows. Same with the integration set on the MCP layer where we keep adding more apps and channels, so one OAuth gets you plugged in across your stack.
What's been pulling our attention lately is a MakersClaw API / MCP layer that would let you bring your own skills and tools into the platform. If you've already built agent skills locally (in Claude Code, Cursor, your own runtime, anywhere), you'd be able to drop them into an employee slot in one move (Making a local agent online and running 24/7).
AI teammates living where you already work, rather than another dashboard to check, feels like the right direction. Bookmarking this one.
MakersClaw
Super cool idea. I think the pay-per-call tool model is great.
MakersClaw
@adam_maceachern1 thank you, I think it makes it easier to keep adding more while keeping an eye on real spends