Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Show HN: Paca – Lightweight Jira alternative for human-AI collaboration

github.com

Post reply on HN
Print view View original

61–70 of 81 posts

Re: Show HN: Paca – Lightweight Jira alternative for human-AI collaboration

#61

Post by hashmap »

mcbetz wrote: post #43
_pdp_ wrote: post #30

You can take it a step further and strip out the frontend. Honestly. Nobody needs it and if you need any UI stuff it in the MCP. This is what I did with this project https://github.com/crmkit/crmkit/ and to be honest the approach grows on me and fits well if you are a backend person.

I like the direction! But why stop with CRM functionality with very limited schema for tasks on the headless when OP has a lot more to offer there? Why stop at CRM plus Project Management then? Why not also schemas for ERP, HR, finance tools and all other business software? And we even bother with a custom made API when PostgreSQL and PostgREST could reduce the full thinking to the database schema?

you can, yes, and the db becomes model weights that you can just use lookups for retrieval and have attention live in vram.

Re: Show HN: Paca – Lightweight Jira alternative for human-AI collaboration

#65

Post by AmareshHebbar »

I really love the concept, but I have a few minor concerns:

1. Is it safe to put proprietary company info in here? Can the AI read everything?

2. How are you planning to keep the lights on and pay for hosting if it's 100% free?

3. What happens if the AI goes a bit rogue and messes up the sprint? Can humans easily override or fix it? Or like Undo button??

Re: Show HN: Paca – Lightweight Jira alternative for human-AI collaboration

#66

Post by mzhaase »

dagss wrote: post #23

What are people's workflows these days? As I use claude more and more I've started using git worktrees, one branch per worktree per PR, with possibly multiple agents working in each worktree at the same time on different aspects. And I manually instruct those agents. Like Emdash/Cursor/Zed. Sometimes I review code locally, sometimes agents push and I review in GitHub, no clear system yet. (jj seems promising, but Zed…

Have custom slash commands in forgejo that spawn an agent using deepwhale which creates a branch, then commits and opens a PR when done.

Re: Show HN: Paca – Lightweight Jira alternative for human-AI collaboration

#68

Post by jing-ny »

flo_r wrote: post #38
dagss wrote: post #23

What are people's workflows these days? As I use claude more and more I've started using git worktrees, one branch per worktree per PR, with possibly multiple agents working in each worktree at the same time on different aspects. And I manually instruct those agents. Like Emdash/Cursor/Zed. Sometimes I review code locally, sometimes agents push and I review in GitHub, no clear system yet. (jj seems promising, but Zed…

Gh issues works surprisingly well as an agent board. Labels for state, one issue per feature. The part i haven't figured out yet is how to know when the output is actually done vs just "looks done" to the agent.

Been thinking about this. "Done vs looks done" is partially who is accountable for calling it done, and the trap is the agent that did the work also often declaring it done.

Cheapest fix: a separate done-caller (another agent or you) against criteria written before the work. Reviewer is never the author. (Basically RACI, responsible != accountable)

Re: Show HN: Paca – Lightweight Jira alternative for human-AI collaboration

#69

Post by pikann22 »

eranation wrote: post #45

Thanks for having a security policy https://github.com/Paca-AI/paca/security However I'm getting a 404 https://github.com/Paca-AI/paca/security/advisories/new (You need to enable private security advisories: https://docs.github.com/en/code-security/how-tos/report-and-... , really not sure why GitHub made it opt-in only)

Thank you! I didn't realize it was opt-in. I've enabled it now, so the link should work properly

Re: Show HN: Paca – Lightweight Jira alternative for human-AI collaboration

#70

Post by pikann22 »

AmareshHebbar wrote: post #65

I really love the concept, but I have a few minor concerns: 1. Is it safe to put proprietary company info in here? Can the AI read everything? 2. How are you planning to keep the lights on and pay for hosting if it's 100% free? 3. What happens if the AI goes a bit rogue and messes up the sprint? Can humans easily override or fix it? Or like Undo button??

[flagged]
Post reply on HN