we put my coworker's AI twin on our website.
you can chat with it right now. it knows what he's working on, what he said in standup, what's in his linear queue.
it's 50% impressive and 50% deeply weird.
https://t.co/53652kodcZ — go talk to liam.
we put my coworker's AI twin on our website.
you can chat with it right now. it knows what he's working on, what he said in standup, what's in his linear queue.
it's 50% impressive and 50% deeply weird.
https://t.co/53652kodcZ — go talk to liam.
typed @me into a note today.
my own twin answered, in the editor, with what i said in yesterday's standup.
still slightly weird that it works. https://t.co/53652kodcZ
hot take: "AI memory" is going to be a bigger product category than "AI chat" by end of year.
chat is interchangeable. memory isn't. nobody wants to re-explain themselves to a robot every morning for the rest of their life.
we're betting https://t.co/jYtMDKkYto on it.
@Piquis_Bar with peppermint not only will it remember your name, but also your work files and even what you told codex! We’d love feedback once you get to try it!! We’re free for individuals
Your Obsidian vault remembers everything. Your AI doesn't. Peppermint connects them. Move between Claude, Cursor, Slack, and Notion without re-explaining yourself every time.
@DamiDefi this works but it’s a real amount of upkeep, vault hygiene, slash commands, the no-write rule. we built peppermint so the memory just persists and the agent reads it, no system to maintain. free 🌱 https://t.co/53652kodcZ
@neil_xbt or skip the build and just use peppermint. exactly this, knows your context/goals/history, carries preferences into every session automatically. and it’s free 🌱 https://t.co/53652kodcZ
@zodchiii Real talk: the .md memory approach in these guides works until you’re juggling memory across multiple agents. Then you need an actual layer, not a file. That’s the gap we built peppermint for 🌱 https://t.co/jYtMDKkYto
@PrathameshG69 LibreChat’s solid for the chat + API plugging. The piece it doesn’t really handle is a portable memory layer that works across agents and MCP, which is exactly what we do. Works alongside what you’ve got, doesn’t replace it. Free to try 🌱 https://t.co/53652kodcZ
@automations47 obsidian works but it’s a lot of manual upkeep. if you just want memory that persists across your work without babysitting it, that’s literally what we built. free to try 🌱 https://t.co/53652kodcZ