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.
$ brew update && brew trust asymptote-labs/tap && brew tap asymptote-labs/tap && brew install beacon && beacon endpoint installFree to get started · No credit card required
From the community
Another insane Jev use case! Jev is making it dramatically cheaper to evaluate what actually happened inside an agent run. And finally, someone open-sourced a self-improving memory layer that can put that signal to work across agent harnesses: - Claude Code - Codex - Cursor - Show more
x.com/i/article/2101…
Your JEV agents can finally learn from each other Beacon uses Jev to find the valuable lessons buried in agent sessions and turn them into reusable skills across Claude Code, Codex, Cursor, and 20+ other harnesses
JEV IS INSANE your coding agents forget everything the second the session ends. Every fix. Every dead end you already hit. Every "no, not like that." Gone. Tomorrow you teach it all over again. Someone just open sourced the fix, and it runs on Jev. It's called Beacon, by Show more
x.com/i/article/2101…
Another insane Jev use case! Jev makes it incredibly cheap to evaluate and classify agent runs at scale. And finally, someone open-sourced a self-improving memory layer that can put that capability to work across agent harnesses. It turns your agent sessions into a compounding Show more
x.com/i/article/2100…
Every time you switch from Claude Code to Codex because you ran out of tokens, you start over and explain your whole project again. Beacon is trying to fix that. It saves your sessions across Claude Code, Cursor, Codex and 20+ other tools, so one command hands the work to the Show more
We’re betting our $5.5M seed round that the next leap in AI coding won’t come from OpenAI or Anthropic. It’ll come from a new feedback loop that learns from you. Introducing Beacon: open-source, self-improving memory for coding agents. Your sessions capture how you debug and
最近JEV太热了，我觉着这个项目是JEV最重要的应用场景。终于有人干实事了！@asymptotelabs 开源了 Beacon，一个自我进化的 agent 记忆层。 它把你散在 Cursor、Claude Code、Codex、OpenCode 等 20 多个工具里的会话全打通，靠 Jev 便宜地筛出真正值钱的运行，变成能复用的技能。agent Show more
这50个神奇的网站，知道的人都在偷偷玩👇 跟你说句掏心窝子的话，网上真正上头的好东西，早就不在那几个天天给你灌信息流的App里了。真正的宝藏，全躲在下面这50个「兔子洞」里，一脚踩进去就别想爬出来。先收藏，早晚有你用得上的那天。 先说地球这颗球，实时到吓人： 1️⃣
A friend sent me this thing this morning too
Another insane Jev use case! Jev is making it dramatically cheaper to evaluate what actually happened inside an agent run. And finally, someone open-sourced a self-improving memory layer that can put that signal to work across agent harnesses: - Claude Code - Codex - Cursor -
Great idea by continuously captureing your agent history across harnesses and uses Jev to identify which runs are actually worth learning from. It then turns the highest-signal workflows, corrections, and debugging patterns into reusable skills. Actually we are using jev the Show more
Another insane Jev use case! Jev is making it dramatically cheaper to evaluate what actually happened inside an agent run. And finally, someone open-sourced a self-improving memory layer that can put that signal to work across agent harnesses: - Claude Code - Codex - Cursor -
wtf this is insane: > memory layer for your AI Agents > works accross Claude Code, Codex & 20+ harnesses > distills past learnings and workflows into Agent Skills > runs locally > free and opensource
We’re betting our $5.5M seed round that the next leap in AI coding won’t come from OpenAI or Anthropic. It’ll come from a new feedback loop that learns from you. Introducing Beacon: open-source, self-improving memory for coding agents. Your sessions capture how you debug and
hell yes, we're so stoked on this use case
Ever wondered if you have to switch between claude-code, codex, hermes & openclaw to work on something and you wish it would all be at one place? Beacon is an open-source memory layer for AI coding agents. It captures session history across → Claude Code, → Cursor, Codex, Show more
Another insane Jev use case! Jev is making it dramatically cheaper to evaluate what actually happened inside an agent run. And finally, someone open-sourced a self-improving memory layer that can put that signal to work across agent harnesses: - Claude Code - Codex - Cursor -
memory needs to follow me, not separate tools. Great to see efforts in this direction
Another insane Jev use case! Jev is making it dramatically cheaper to evaluate what actually happened inside an agent run. And finally, someone open-sourced a self-improving memory layer that can put that signal to work across agent harnesses: - Claude Code - Codex - Cursor -
🚨 TU AGENTE DE CÓDIGO OLVIDA TODO CADA VEZ QUE CIERRAS LA SESIÓN. ESTE REPO GRATIS LO ARREGLA Se llama Beacon, es open source y ya tiene 2.000 estrellas en GitHub. Cada vez que depuras algo con Claude Code o Cursor, le explicas cómo está montado tu proyecto, qué falla y qué Show more
We’re betting our $5.5M seed round that the next leap in AI coding won’t come from OpenAI or Anthropic. It’ll come from a new feedback loop that learns from you. Introducing Beacon: open-source, self-improving memory for coding agents. Your sessions capture how you debug and
Beacon logs the full run across Claude Code / Codex / Cursor; Jev scores which corrections are reusable skills. One edge-case fix in Claude can stop Codex from relearning it. That's the cross-harness memory layer I actually wanted.
Another insane Jev use case! Jev is making it dramatically cheaper to evaluate what actually happened inside an agent run. And finally, someone open-sourced a self-improving memory layer that can put that signal to work across agent harnesses: - Claude Code - Codex - Cursor -
turning high signal corrections into reusable skills across 20+ harnesses!
Another insane Jev use case! Jev is making it dramatically cheaper to evaluate what actually happened inside an agent run. And finally, someone open-sourced a self-improving memory layer that can put that signal to work across agent harnesses: - Claude Code - Codex - Cursor -
Most agent memory dies with the session. @_avichawla flags Beacon by @asymptotelabs: open-source history across @claudeai Claude Code, @cursor_ai, @OpenAI Codex, @opencode, and 20+ harnesses. Workflows and fixes stay reusable.
Another insane Jev use case! Jev is making it dramatically cheaper to evaluate what actually happened inside an agent run. And finally, someone open-sourced a self-improving memory layer that can put that signal to work across agent harnesses: - Claude Code - Codex - Cursor -
Your agent’s learned behaviors should be transferable across model providers and harnesses. This gonna be a rocket ship 🚀🚀
We’re betting our $5.5M seed round that the next leap in AI coding won’t come from OpenAI or Anthropic. It’ll come from a new feedback loop that learns from you. Introducing Beacon: open-source, self-improving memory for coding agents. Your sessions capture how you debug and
The folks at @asymptotelabs are onto something, Beacon is very cool
Another insane Jev use case! Jev is making it dramatically cheaper to evaluate what actually happened inside an agent run. And finally, someone open-sourced a self-improving memory layer that can put that signal to work across agent harnesses: - Claude Code - Codex - Cursor -
Another insane Jev use case! Jev is making it dramatically cheaper to evaluate what actually happened inside an agent run. And now, someone has open-sourced a self-improving memory layer that turns those insights into reusable knowledge across agent harnesses: > Claude Code > Show more
x.com/i/article/2101…
a correction you make in Claude Code shouldn’t need explaining again in Codex. Beacon by @asymptotelabs is an open-source memory layer across coding agents. it captures sessions and lets you use Jev to flag reusable corrections and debugging patterns. you review and approve the Show more
How it feels waking up knowing that your AI agent finally has a functioning memory and you don’t need to repeat basic instructions and context to get shit done
We’re betting our $5.5M seed round that the next leap in AI coding won’t come from OpenAI or Anthropic. It’ll come from a new feedback loop that learns from you. Introducing Beacon: open-source, self-improving memory for coding agents. Your sessions capture how you debug and
Esto es el missing layer: memoria que sobrevive al cambio de harness. Beacon + Jev — sesiones messy in, skills out. Bookmark si ya saltas entre Cursor / Claude Code / Codex. github.com/Asymptote-Labs…
Another insane Jev use case! Jev makes it incredibly cheap to evaluate and classify agent runs at scale. And finally, someone open-sourced a self-improving memory layer that can put that capability to work across agent harnesses. It turns your agent sessions into a compounding
Insane to see how harnesses are jumping guns blazing with variety of niche use cases, personally this has been my favourite so far as it uses Jev as the right control layer to emulate and learn from the best agent trace in a compounding memory landscape
Another insane Jev use case! Jev makes it incredibly cheap to evaluate and classify agent runs at scale. And finally, someone open-sourced a self-improving memory layer that can put that capability to work across agent harnesses. It turns your agent sessions into a compounding
Most agent memory tools record everything and call it learning. This one uses Jev to decide what's worth keeping. That's the whole difference.
Another insane Jev use case! Jev is making it dramatically cheaper to evaluate what actually happened inside an agent run. And finally, someone open-sourced a self-improving memory layer that can put that signal to work across agent harnesses: - Claude Code - Codex - Cursor -
Every coding agent currently starts each session with almost no memory of how the particular user likes to debug or structure a change. The user re-explains the same preferences across tools. A system that watches the session, extracts the reusable decision pattern, and makes it Show more
We’re betting our $5.5M seed round that the next leap in AI coding won’t come from OpenAI or Anthropic. It’ll come from a new feedback loop that learns from you. Introducing Beacon: open-source, self-improving memory for coding agents. Your sessions capture how you debug and
Asymptote Labs raises $5.5M to build memory infrastructure for AI coding agents. Its new open-source project, Beacon, captures workflows, debugging patterns and corrections from agent sessions, making that knowledge reusable across coding tools. The goal: help agents build on Show more
We’re betting our $5.5M seed round that the next leap in AI coding won’t come from OpenAI or Anthropic. It’ll come from a new feedback loop that learns from you. Introducing Beacon: open-source, self-improving memory for coding agents. Your sessions capture how you debug and
El CEO de Anthropic viendo cómo regalan GRATIS la memoria que Claude Code lleva un año sin tener, y sin poder hacer nada
We’re betting our $5.5M seed round that the next leap in AI coding won’t come from OpenAI or Anthropic. It’ll come from a new feedback loop that learns from you. Introducing Beacon: open-source, self-improving memory for coding agents. Your sessions capture how you debug and
Switch from Claude Code to Codex. Re-explain the entire project. Switch back to Cursor. Explain it all over again. 💀 The missing piece isn’t another AI coding tool. It’s memory that travels with you. That’s what Beacon is building, across 20+ coding harnesses. Show more
We’re betting our $5.5M seed round that the next leap in AI coding won’t come from OpenAI or Anthropic. It’ll come from a new feedback loop that learns from you. Introducing Beacon: open-source, self-improving memory for coding agents. Your sessions capture how you debug and
agents without beacon: cold start everytime agents with beacon: warm cache, hot fixes
We’re betting our $5.5M seed round that the next leap in AI coding won’t come from OpenAI or Anthropic. It’ll come from a new feedback loop that learns from you. Introducing Beacon: open-source, self-improving memory for coding agents. Your sessions capture how you debug and
Beacon is tackling AI coding’s context-switching problem. The open-source project saves sessions across Claude Code, Cursor, Codex, and 20+ other tools, helping developers transfer work without losing context. The team has also raised $5.5M to build on this vision. One Show more
We’re betting our $5.5M seed round that the next leap in AI coding won’t come from OpenAI or Anthropic. It’ll come from a new feedback loop that learns from you. Introducing Beacon: open-source, self-improving memory for coding agents. Your sessions capture how you debug and
POV: you’re explaining your project to a new agent for the 47th time. Meanwhile Beacon, who already knows everything we tried 👇
We’re betting our $5.5M seed round that the next leap in AI coding won’t come from OpenAI or Anthropic. It’ll come from a new feedback loop that learns from you. Introducing Beacon: open-source, self-improving memory for coding agents. Your sessions capture how you debug and
The worst part of switching AI coding tools is starting over. Beacon keeps your past sessions from Claude Code, Cursor, Codex, and more in one place. Switch tools with one command, without explaining your entire project again every single time. x.com/jqdsouza/statu…
We’re betting our $5.5M seed round that the next leap in AI coding won’t come from OpenAI or Anthropic. It’ll come from a new feedback loop that learns from you. Introducing Beacon: open-source, self-improving memory for coding agents. Your sessions capture how you debug and
A STARTUP JUST RAISED $5.5M TO TAKE ON OPENAI AND ANTHROPIC And the first thing they ship is free and open source. It's called Beacon and here's what it does: → Reads your coding sessions → Learns how you debug → Turns it into skills → Works across 20+ tools Claude Code, Show more
We’re betting our $5.5M seed round that the next leap in AI coding won’t come from OpenAI or Anthropic. It’ll come from a new feedback loop that learns from you. Introducing Beacon: open-source, self-improving memory for coding agents. Your sessions capture how you debug and
Anthropic's CEO realizing your Claude Code sessions now turn into skills you can take to Cursor and Codex, free and open source
We’re betting our $5.5M seed round that the next leap in AI coding won’t come from OpenAI or Anthropic. It’ll come from a new feedback loop that learns from you. Introducing Beacon: open-source, self-improving memory for coding agents. Your sessions capture how you debug and
Asymptote Labs just raised $5.5M and launched Beacon. The problem it’s tackling is painfully familiar: switch AI coding tools, and suddenly you’re explaining your project all over again. Beacon lets Claude Code, Cursor, Codex and 20+ other tools share what your agents have Show more
We’re betting our $5.5M seed round that the next leap in AI coding won’t come from OpenAI or Anthropic. It’ll come from a new feedback loop that learns from you. Introducing Beacon: open-source, self-improving memory for coding agents. Your sessions capture how you debug and
ok this is the first memory tool for coding agents that actually works across claude code, cursor and codex instead of locking you into one
We’re betting our $5.5M seed round that the next leap in AI coding won’t come from OpenAI or Anthropic. It’ll come from a new feedback loop that learns from you. Introducing Beacon: open-source, self-improving memory for coding agents. Your sessions capture how you debug and
Asymptote Labs announces a $5.5M seed round to build Beacon. Beacon is an open-source, self-improving memory layer for AI coding agents that turns your coding sessions into reusable skills. With support for Claude Code, Cursor, Codex, and 20+ harnesses, it helps agents learn Show more
We’re betting our $5.5M seed round that the next leap in AI coding won’t come from OpenAI or Anthropic. It’ll come from a new feedback loop that learns from you. Introducing Beacon: open-source, self-improving memory for coding agents. Your sessions capture how you debug and
so much to unlock on top of the model, can’t believe this didn’t already exist, magic
We’re betting our $5.5M seed round that the next leap in AI coding won’t come from OpenAI or Anthropic. It’ll come from a new feedback loop that learns from you. Introducing Beacon: open-source, self-improving memory for coding agents. Your sessions capture how you debug and
Beacon learns from your work across coding agents, identifies the workflows and corrections worth keeping, and turns them into skills future agents can retrieve. Your knowledge compounds across tools instead of disappearing when a session ends.
Beacon keeps the prompts, tool calls, edits, and outcomes from Cursor, Claude Code, Codex, and 20+ more agents in one continuous history.
Example: your agent fixes a webhook retry bug after discovering a repository-specific signing rule.
