Launching today
beacon.sh
Open-source self-improving memory for AI coding agents
577 followers
Open-source self-improving memory for AI coding agents
577 followers
Beacon turns agent sessions across Claude Code, Cursor, Codex, OpenCode, and 20+ other harnesses into a compounding knowledge layer, so every agent starts smarter than the last. It captures every agent trace across your environment and turns activity into clear operational visibility. Get started for free at beacon.sh
Launch Team / Built With
Dropbox SignSimple, secure eSignatures for the way your team works.
Promoted
Love it. Makes tokens last longer without the friction of my agents needing to load the whole context from scratch.
@juampihernandez exactly Juampi! I'd love your feedback on the product and would be super grateful for an upvote on our launch :) https://github.com/Asymptote-Labs/agent-beacon
Losing context across chats is one of the most frustrating things I encounter.
And as such, Beacon looks like a promising tool in that direction.
All the best for the launch!
@sumitsaurabh927 totally agree! This was easily the biggest pain-point that caused us to build Beacon out in public. Would really appreciate your support with an upvote, and I'd love your feedback on the project Sumit: https://github.com/Asymptote-Labs/agent-beacon
Nice! love the idea
i am always switching between Cursor and Claude so this is very helpful so they both have reusable skills and memories
@thisiskp_ Thanks KP! Portability of context + memories + skills across harnesses was one of the biggest principles behind Beacon, so I'm really glad to hear that particular feature resonated with you :)
I like this. Developers won't have to repeat the same context every time they start a new agent session, Wishing you guys lots of success. @beacon.sh
@deepaksingh09 spot on! help us spread the word on X, repost this
@deepaksingh09 thanks for the kind words Deepak! I'd love to get your feedback on Beacon :) Check out our repo and don't forget to star! https://github.com/Asymptote-Labs/agent-beacon
Congrats on the launch! I'm tired of re-explaining my codebase every time I open a new agent session, so memory that carries over between tools is very welcome, and it's great that it's open source.
@ephraimduncan oss ftw! make sure to star this repo, and curious to have your feedback if you have the chance to play around with @beacon.sh
@ephraimduncan thank you Ephraim! So glad the product resonates with you. Definitely check out our open source project and let me know what you think (don't forget to star!) :) https://github.com/Asymptote-Labs/agent-beacon
Wow, this is something i needed from long time. Switch from AI tool to tool the memory of those tools are quite act differently. Beacon has been sorted this out. Contrates on your launch and ideas. Its really solves the problem that many have. I'll surely look deep into it.
@rakesh_nakrani1 Thanks Rakesh! Really glad to hear our approach with Beacon resonates with you.
I'd love to get your feedback on the product! Check out our GitHub repo here (don't forget to star!): github.com/Asymptote-Labs/agent-beacon
@rakesh_nakrani1 thank you for your support, Rakesh! help us spread the word on X, repost this
Really cool. I jump between T3 Code, Cursor and Codex, so this is great. Also open source. 🔥
@catalinmpit We love OSS! I definitely think this would be a superpower for your cross-harness workflows Catalin. With Beacon your memories + context are instantly portable :)
@catalinmpit oss ftw!