zlacker

Beads – A memory upgrade for your coding agent

submitted by latchk+(OP) on 2025-11-28 04:50:57 | 111 points 68 comments
[view article] [source] [go to bottom]

NOTE: showing posts with links only show all posts
9. iand67+jt[view] [source] 2025-11-28 10:43:49
>>latchk+(OP)
I've been trying `beads` out for some projects, in tandem with https://github.com/github/spec-kit with pretty good results.

I set up spec-kit first, then updated its templates to tell it to use beads to track features and all that instead of writing markdown files. If nothing else, this is a quality-of-life improvement for me, because recent LLMs seem to have an intense penchant to try to write one or more markdown files per large task. Ending up with loads of markdown poop feels like the new `.DS_Store`, but harder to `.gitignore` because they'll name files whatever floats their boat.

19. simonw+Tx[view] [source] 2025-11-28 11:32:16
>>latchk+(OP)
The Beads project uses Beads itself as an issue tracker, which means their issues data is available here as JSONL:

https://github.com/steveyegge/beads/blob/main/.beads/issues....

Here's that file opened in Datasette Lite which makes it easier to read and adds filters for things like issue type and status:

https://lite.datasette.io/?json=https://github.com/steveyegg...

22. mbaner+Ky[view] [source] 2025-11-28 11:43:22
>>latchk+(OP)
Makes me wonder whether you can just give agents [Taskwarrior](https://taskwarrior.org/).

Set the TASKDATA to `./.task/`. Then tell the agents to use the task CLI.

The benefit is most LLMs already understand Taskwarrior. They've never heard of Beads.

◧◩◪◨⬒⬓
30. wowami+4D[view] [source] [discussion] 2025-11-28 12:26:12
>>simonw+RA
You are right. I dug through the document some more. The setup, as mentioned for protected branches [1], should ideally work without much overhead. It does suggest merging back to main, but the FAQ also mentions that the frequency can be decided individually.

[1] https://github.com/steveyegge/beads/blob/main/docs/PROTECTED...

34. pradee+fI[view] [source] 2025-11-28 13:13:05
>>latchk+(OP)
Ha, I was working on the same problem and updating my article when this hit. My focus is on making the agent integration more seamless with the tool. Claude offers a fantastic way for this using "skills" and now a "marketplace"

[1] Demo with Claude - https://pradeeproark.github.io/pensieve/demos/

[2] Article about it - https://pradeeproark.com/posts/agentic-scratch-memory-using-...

[3] https://github.com/cittamaya/cittamaya - Claude Code Skills Marketplace for Pensieve

[4] https://claude.com/blog/skills

◧◩
42. vdm+0T[view] [source] [discussion] 2025-11-28 14:37:14
>>iddan+lk
https://steve-yegge.medium.com/beads-best-practices-2db636b9...
◧◩
43. hmokig+7T[view] [source] [discussion] 2025-11-28 14:38:51
>>iand67+jt
First I hear of spec-kit, that looks very promising, I’m interested in trying it. My approach is to combine beads with superpowers skills https://github.com/obra/superpowers I’m wondering how does it compare to this, gonna give it a try, thanks!
44. themgt+pT[view] [source] 2025-11-28 14:40:41
>>latchk+(OP)
It does theoretically look like a useful project. At the same time I'm starting to feel like we're slipping into the Matrix. I check a GitHub issue questioning the architecture.md doc:

> I appreciate that this is a very new project, but what’s missing is an architectural overview of the data model.

Response:

You're right to call me out on this. :)

Then I check the latest commit on architecture.md, which looks like a total rewrite in response to a beads.jsonl issue logged for this.

> JSONL for git: One entity per line means git diffs are readable and merges usually succeed automatically.

Hmm, ok. So readme says:

> .beads/beads.jsonl - Issue data in JSONL format (source of truth, synced via git)

But the beads.jsonl for that commit to fix architecture.md still has the issue to fix architecture.md in the beads.jsonl? So I wonder does that get line get removed now that it's fixed ... so I check master, but now beads.jsonl is gone?

But the readme still references beads.jsonl as source of truth? But there is no beads.jsonl in the dogfooded repo, and there's like ~hundreds of commits in the past few days, so I'm not clear how I'm supposed to understand what's going on with the repo. beads.jsonl is the spoon, but there is no spoon.

I'll check back later, or have my beads-superpowered agent check back for me. Agents report that they enjoy this.

https://github.com/steveyegge/beads/issues/376#issuecomment-...

https://github.com/steveyegge/beads/commit/c3e4172be7b97effa...

https://github.com/steveyegge/beads/tree/main/.beads

◧◩◪◨⬒
59. simonw+Ji1[view] [source] [discussion] 2025-11-28 17:18:47
>>UmGuys+741
Claude Code doesn't do anything with semantic search or embeddings out of the box. They use a simple grep tool instead.

Neither does OpenAI's Codex CLI - you can confirm that by looking at the source code https://github.com/openai/codex

Cursor and Windsurf both use semantic search via embeddings.

You can get semantic search in Claude Code using this unofficial plugin: https://github.com/zilliztech/claude-context - it's built by and uses a managed vector database called Zilliz Cloud.

63. jaunty+5m1[view] [source] 2025-11-28 17:40:40
>>latchk+(OP)
Somewhat aside but I love the data architrcture. Jsonl lines checked into git, and a sqlite local cache. Auto-sync to replicate changes between the canonical and cache. https://github.com/steveyegge/beads?tab=readme-ov-file#the-m...

I finally started digging in to OpenCode for real these past couple weeks. It has a planning mode, which nicely builds out a plan on text chat as usual, but also a right pain on the TUI builds out a Todo list, which has been really nice. I often give it the go-ahead to do the next item or two or three. I've wondered how this is implemented, how OpenCode sets up and picks up on this structuring.

Beads formalizing that a bit more is tempting. I also deeply deeply enjoy that Beads is checked in. With both Aider and OpenCode, there's a nice history. But it's typically not checked in. OpenCode 's history in particular isnt even kept in the project directory, and can be quite complex with multiple sessions and multiple agents all flying around. Beads, as a strategy to record the work & understand it better, is also very tempting.

Would love to see deeper OpenCode + Beads integration.

◧◩◪
65. simonw+l02[view] [source] [discussion] 2025-11-28 22:24:51
>>threec+gW
That's a project from a few years ago, it uses Pyodide to run Datasette in Python in WebAssembly: https://simonwillison.net/2022/May/4/datasette-lite/
[go to top]