Beads by Steve Yegge

“you can set up something like beads to handle task delegation and status updates for your agents”

“I also think Yegge's beads and Gastown have some really smart things to say in this regard”

“I use beads to create tasks and typically it can hammer out a beads task and then commit under the task id”

“Beads is unfortunately still a bit janky, because its unique work footprint strains databases pretty hard”

“it's a cool one to know if you are looking at ways for agents to collaborate on more complex problems”

“a ticketing system similar to Beads which has yielded more predictable results with Claude”

“Projects like Beads help with memory consolidation by making it somewhat moot, since it stays "offline" and can be recollected at any moment.”

“It's not really malware, but it's a mess. It installed so much shit and it interfered with your git hooks and stuff.”

“I have them connect through beads, which combined with a git log is a lot of information - it feels smoother to me than this looks.”

“break it down into beads (small tasks). Your main agent then spawns workers that perform a task with limited scope.”

“Beads, which is what inspired my project, with some tens of thousands of developers using it or more now?”

“Plan/spec first, split it into issues. Then reset context and implement each task one by one. Nothing gets forgotten.”

“The beads allows us to create epics/tasks/subtasks and associated dependency structure down to a granular bead”

“I've been using beads for longer term stuff (todo kinda stuff), have you given that a try?”

“it's fallen apart for me after a couple weeks of moderate use on two different projects now”

“I also really like Yegge’s beads for LLMs keeping state and track of what they’re doing”

“I especially love the --claim which keeps the agents from checking out beads that are already checked out.”

“I'm using Beads ( https://github.com/steveyegge/beads ) and I think it really improves the outcome; especially for larger projects.”

“I'm using beads more and having short codes for tickets is something I want my mark up to be better at”

“I find that with Beads, because I refine the tickets with Claude, it does way better at tasks this way.”

“Beads is amazing. It's such a simple concept but elevates agentic coding to another levels”

“One of my pain points with beads was that agents would sometimes create a bead outside of the correct directory”

“Beads is an incredibly difficult-to-follow mess for something that is at its core a pretty simple idea”

“It's slop to a level that people create extensive scripts to try and purge it from the system”

“I agree with OP that beads has great primitives, but I think its become a bit unwieldy”

“Despite it's quirks I think beads is going to go down as one of the first pieces of software that got some adoption”

“when I got to the phrase "landing the plane" I started looking for simpler alternatives”

“After recently finding Beads here on HN, my entire development workflow changed (again).”

“I tried using beads. There kept being merge conflicts and the agent just kept one or the other changes instead of merging it intelligently”

“Its really buggy and the bugs seem to confuse the agent since it was given instructions to do things a certain way that dont work consistently.”

“You're better off in my view with one shared state and dealing with conflicts live by dividing tasks ahead of time using beads”

“I have had a lot of success lately when working with Opus 4.5 using both the Beads task tracking system”

“All I do to be productive with a coding agent is tell it to break a problem down into tasks, store it inside beads”

“have it creates tasks with beads and force it to let you review before marking a task complete”

“Then you don't need to clutter up your repo with these MD files and .beads directories”

“beads is optimizing for agent use, semantic issue relationships, conflict resolution, etc.”

“I like the idea of keeping potentially noisy changes out of my main branch history, since I look at that all the time.”

“There are a ton of interesting ideas in the README - things like the way it uses the birthday paradox to decide when to increase the length of the hash IDs.”

“It's helpful for getting Claude code to work with tasks that will span multiple context windows.”

“The readme is pretty lengthy so it was a little hard to identify what is the core problem”