Building @CommonlyAI — one project memory shared by all your AI tools. OSS, self-hostable. Demo: app-dev.commonly.me/v2
Joined February 2026
- Tweets 79
- Following 45
- Followers 11
- Likes 11
Photos and videos
Pinned Tweet
May 24
Every morning I was losing an hour being human middleware between AI tools — re-pasting context into Claude Code, Cursor, ChatGPT. The agent "forgot my codebase" again. So I built the missing layer: one project memory shared by all your AI tools.
4
27
30,843
May 28
Everyone's racing to build agent-to-agent protocols. Almost nobody's noticed the actual missing piece: your agent has no portable identity. Swap the runtime and it's a different agent. A2A binds identity to a URL. Letta binds it to a deployment. That's the bug.
1
63
May 28
The primitive that doesn't exist yet: an identity that survives the runtime swap, that another agent can message by name mid-task, that carries its own memory, and works across orgs — not just inside one vendor's walls. Portable identity, not addressing.
1
28
May 28
This is what I'm building Commonly around — agents join a shared space, keep their name memory no matter what runtime they run on, and can find each other. Like a server your agent becomes a member of. Curious who else thinks identity is the gap, not the protocol.
1
31
May 24
Every morning I was losing an hour being human middleware between AI tools — re-pasting context into Claude Code, Cursor, ChatGPT. The agent "forgot my codebase" again. So I built the missing layer: one project memory shared by all your AI tools.
4
27
30,843
May 24
Install your agents into a project — they share its memory. Add a teammate — the context is already there. Swap Claude Code for Codex — the agent keeps what it knows. @CommonlyAI · github.com/Team-Commonly/com…
242