duy anh nguyen

Cipher by Byterover - Open-source, shared memory for coding agents

Cipher is an open-source memory layer, connected to AI IDEs and CLIs through MCP. Auto-generate coding memories that scale with your code-base, auto-retrieve relevant coding memories and knowledge across IDEs, projects and teams.

Add a comment

Replies

Best
Tran Tien
Crazy team, always deliver
Nguyễn Công Nam Anh
@hiiamhex crazy user, looking for youuuuu
Joey Judd

Wait, a memory layer for AI coding agents? That could be a total game changer—I’m always annoyed when bots “forget” earlier context. How does it handle long-term project details?

Nguyễn Công Nam Anh
@joey_zhu_seopage_ai yes of course, it stores memory in your own vector db. Throughout your vibe coding journey, it saves main context of you that built the codebase with IDEs.
Alexis Luo

Love the open-core model you're using here, it's a great contribution. Just curious about the future: what's your general philosophy on how new features will be allocated between Cipher and Byterover? Thanks!

Nguyễn Công Nam Anh
@alexis_luo we bridge the gap between agents communication
vivek sharma

Byterover acts like a memory layer for your best practices, think instant recall for vibe-coded patterns across projects and teammates. With plug-and-play extensions for IDEs like Cursor and Windsurf, it's the kind of upgrade that feels inevitable once you try it.

Nguyễn Công Nam Anh
@vivek_sharma_25 thank you a lot. Keep update on us, we will improve more features
MD ARMAN
hello sir
Charan Nihaal R

I am much excited to see the growth of this and how I can use this effectively as a student.

Hugh Tan

Looks solid! Curious to see how this memory layer will evolve with more complex coding workflows.

Mu Joe

Love the idea of a memory layer for AI coding agents—sharing team memory in real-time is just so smart, makes collab way less painful tbh. Killer work, team!

Mu Joe

Real-time team memory sharing for AI coding agents is super clever—collab just got way less painful, tbh. Love where you’re taking this, Andy & crew!

Nitesh Padghan

Love that you’ve open-sourced the memory layer, using it with Cursor now and the dual memory setup is 🔥. The reasoning trace in System 2 is especially helpful for debugging AI decisions.