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
AWS Activate CreditsCredits that fuel your startup’s next milestone
Promoted
Lovely product! absolutelt loved the thought behind it and the problem it is trying solve for people who build with ai. Best wishes @justindsouza and team :)
@whatshivamdo Really appreciate the kind words Shivam! Glad to hear your liking the product, please keep the feedback coming :) Check out our Github and definitely join our discord community: https://github.com/Asymptote-Labs/agent-beacon
Sharing this with my builder friends asap
@shushantlakhyani so glad to hear that Shushant! Thank you and let me know what you think of the project :) https://github.com/Asymptote-Labs/agent-beacon
Congrats on your launch!
@tessak22 thank you Tessa! Appreciate the kind words. I'd love your feedback on Beacon if you check it out :) https://github.com/Asymptote-Labs/agent-beacon
@justindsouza You got it! I was actually just looking at your website and really excited about it all. I've been writing my own workarounds for self-training so I am always up for better ways of doing things. I will definitely share feedback after I dive in.
@tessak22 thank you for your continuous support, Tessa. you're the 🐐
Ours is one `CLAUDE.md` in the repo and `AGENTS.md` just points to it, so every agent reads the same file and a change goes through a commit like any other code. When I approve a memory in Beacon, can it land as a file in the repo so a teammate sees it in the PR?
@julien_zammit using those markdown files is definitely a useful baseline for sharing memories and context across agents! With Beacon, you get all that cross-harness compatibility out of the box too. And yeah, when you approve a memory or skill in Beacon it lands as a file that can be checked in via a PR.
We actually also just shipped a Beacon Team plan so you can share agent sessions, memories, skills + findings across your team! Let me know what you think, happy to personally onboard you: https://beacon.sh/pricing
Love that memory travels across agents like Claude Code and Cursor, so every session makes the next one smarter instead of starting from zero.
@ilko_kacharov 100% Ilko! Glad that our approach with Beacon resonates with you. If you get a chance, please upvote our launch and I'd love your feedback on the project as well: https://github.com/Asymptote-Labs/agent-beacon
@ilko_kacharov exactly! help us spread the word on X, repost this