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
duy anh nguyen
Hi Product Hunt Community, Having received positive feedback from the community since launching ByteRover, we have decided to open-source our core AI engine - memory layer. This version Cipher got a major upgrade since latest version of Byterover, rolled out last month, with improved memory search tool, and faster memory creation. Especially this time, we open-source it so that developers can self-host, contribute and use it dynamically. Key feature of Cipher: 🧠 Auto-generates coding memories that grow with your codebase 🔌 Works with any IDE — including modern models like QwenCode, Trae, Kimi K2, Kiro — not just VS Code, Cursor, or GitHub Copilot 🔁 Seamless memory + context switching across IDEs đŸ‘„ Share AI coding memories across your team in real time 🧬 Dual Memory Layer: System 1: Programming concepts, business logic, past interactions System 2: Reasoning steps behind the model’s code generation âšĄïž Zero-config installation on your IDE With 1 month of work putting into this project, we hope this enables more developers and researchers to build advanced coding agents and drive innovation forward together. Would love your feedback, contribution and support if ByteRover brings you value 🙌
Nguyễn CĂŽng Nam Anh
Hi Product Hunt, We are excited to contribute to community an opensource memory layer for coding agents. It would be nice if we receive contribution from community to improve memory layer, because it helps vibe coders more efficiently. Would love your feedback đŸ«¶đŸ»
BĂči LĂȘ ChĂ­ BáșŁo

Interesting, isn't that is what Byterover already doing? Do I need to install Cipher if I already have Byterover?

duy anh nguyen

@builechibao Great question! This is the open-source core of the AI engine that powers Byterover. We wanted to give back to the community so anyone can self-host or customize the memory layer for their own projects. You don’t need to install Cipher if you’re happy with Byterover, but now you have the flexibility to use or adapt it however you want. More updates for Byterover are coming soon—likely next week. Thanks for your interest!

Tim Boulay

Impressive work! đŸ”„

Byterover adds real memory to AI coding agents, making them smarter across sessions and teams. The IDE integrations and open-source Cipher engone are impressive.

Excited to see how this evolves—especially for larger codebases and team workflows. Congrats on the launch!

duy anh nguyen

@tim_bou Thanks so much, Tim! Really appreciate your kind words and support. We’re excited about what’s ahead and can’t wait to share more updates as ByteRover grows. Stay tuned, and thanks again for cheering us on!

Nguyễn CĂŽng Nam Anh
@tim_bou Thank you a lot. We would love your contribution
Nima Aksoy

Nice work Duy, Cipher looks solid. We’re curating top dev tools at bestofweb .site, would be great to include ByteRover there too.

duy anh nguyen

@nimaaksoy Thanks Nima! That would be awesome—really appreciate you considering ByteRover for bestofweb.site. Let me know if you need any info or assets from our side!

Van de Vouchy

Congrats! Self-hosting an AI memory engine like Kimi K2 requires powerful hardware and DevOps skills. How do you plan to help users manage these high infrastructure demands and setup complexity

duy anh nguyen

@vouchy Thanks so much for your thoughtful question! 😊

Cipher is the open-source AI engine powering ByteRover. Our goal with Cipher is to give users maximum flexibility for integrating agentic memory layers into their own products. For anyone who prefers not to handle the infrastructure or DevOps complexity themselves, ByteRover offers a managed cloud version of Cipher—so you can just focus on building, and we take care of the rest!

Really appreciate your interest—let me know if you have more questions or want to try it out!

Bieber

Congratulations! I happened to be troubled by the problem that cloude code couldn't obtain the context of the cursor. It was very timely!

Nguyễn CĂŽng Nam Anh
@bieber_chen yea, you can host cipher as mcp server so that cursor can connect
Dhruv Maradiya

Excited to see this in action

Nguyễn CĂŽng Nam Anh
@dhruvmaradiya thank you a lot. We would love your feedback and contribution also. Looking forward to your application with cipher đŸ™ŒđŸ»
Udit Akhouri

Huge respect to the team — love the idea of memory layers that travel with the dev, across tools and teams. The System 1 / System 2 framing is particularly clever.

Quick question: as you scale adoption across larger teams or contributors, how are you thinking about support or real-time guidance? Especially when something breaks deep in context memory?

We’ve been thinking a lot about this space — launching soon on PH with Exthalpy, a live AI video agent to help users in those critical stuck moments. Would love your support when we go live 🙌

All the best,

Udit (fellow PH builder)

Nguyễn CĂŽng Nam Anh
@udit_akhouri yea sure, it's such a good use case. Because codebase will be more larger by time, and later user wilk take time to adopt with huge project. Go for it my friend, we are looking for your product launch.
Sania Zahid
Amazing!!👏 Congratulations to the launch!🎉 This tool must has immense potential for streamlined development and enhanced AI capabilities. Kudos to the team for pushing the boundaries of innovation! đŸ‘đŸ’»
duy anh nguyen

@sania_zahid Thank you so much for your kind words and support! We're thrilled you see the potential in ByteRover and appreciate your encouragement. Stay tuned—lots more innovation ahead!

Nguyễn CĂŽng Nam Anh
@sania_zahid thank youu. We would love your feedback
Frédérick Tubiermont

Hi, like the reggae vibe of your gradient palette ;) đŸȘŽ

Nguyễn CĂŽng Nam Anh
@adsy_me thank you a lotttt
Tran Tien
Crazy team, always deliver
Nguyễn CĂŽng 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 CĂŽng 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 CĂŽng 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 CĂŽng 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
Launching soon!

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

Savvas Konsta
interested concept! congratulations 🎉