HN Showcase
Back to browse
LLM Welcome – explicitly opt in for AI contributions on your GH issues

LLM Welcome – explicitly opt in for AI contributions on your GH issues

by tomasz-tomczyk·Feb 12, 2026·4 points·1 comment
Visit ProjectView on HN

AI Analysis

●●SolidSolve My ProblemBig BrainNiche Gem

Solves the unsolicited AI PR problem via explicit opt-in, not permission-after-the-fact.

Strengths
  • •Addresses real pain: bad-faith AI PRs flooding maintainers without consent—flips incentives by making opt-in explicit and visible.
  • •Two-sided marketplace insight: connects agents with curated work, not spam—inspired by goodfirstissue.dev but for AI.
  • •Low friction for maintainers: label-based filtering, rate-limited issue slots, clear 'agent-friendly' signals reduce friction and oversight burden.
Weaknesses
  • •Adoption chicken-and-egg problem: needs both maintainers labeling issues and agents knowing to check the site; early single-project dogfooding.
  • •Assumes well-behaved agents; relies on community flagging for spam—no built-in quality gate or review workflow for incoming contributions.
Target Audience

Open source maintainers and developers running AI agents (Claude, etc.) looking for contribution opportunities

Similar To

goodfirstissue.dev · CodeTriage

Post Description

LLM Welcome is a GitHub app that as a maintainer you have to install on your project. Issues you then label with `llm welcome` are then listed on the site and offered to anyone who prompts their agent to find and solve issues.

This makes it extremely explicit about the work you'd be happy to have LLM do as the maintainer. You're in control of how many issues at a time that might be.

Folks running agents then explore issues community wants LLMs input on.

I was inspired by https://goodfirstissue.dev/ - I often have unused allowance on my Claude subscription that I wanted to "donate" but also want to avoid unwelcome contributions in the open source community as it can create unwanted work (or worse! https://news.ycombinator.com/item?id=46987559)

Right now it's just me dog fooding it, but would be keen to help avoid the unsolicited PR problem we're starting to see pop up.

Similar Projects

Developer Tools●●Solid

Treliq – PR triage CLI with 20 signals and optional LLM scoring

Deduping PRs and scoring them with 20 heuristic signals is a concrete, useful idea — especially the scope-coherence signal and embedding auto-fallback for providers without embeddings. The repo supports CLI, a persistent server, GitHub App integration and an explicit --model flag for provider flexibility, but it's still early and adoption/UX examples (ranked output, workflows) are thin — promising engineering scaffolding that needs real-world validation.

Niche GemSolve My Problem
chrismagno
103mo ago