HackerReposA FIELD GUIDE TO OPEN SOURCE
ProSponsor the shelf♧ 0
← Back to top all-time
github
gh-aw
Go2026–2026
github / gh-aw

gh-aw

GitHub Agentic Workflows

8Distinct people
8Mentions
0Explicit recommenders
5.6KGitHub stars
REPOSITORY AT A GLANCE

What to know before exploring

What it is

GitHub Agentic Workflows

GitHub

Where it is used

No documented product use has been verified yet.

What people are saying

No recommendation phrase was found in the indexed comments.

No classified warning is attached to this page. Read the discussions before treating silence as approval.

Also in these discussions

No other repository is repeatedly linked in the same discussions.

This week on Hacker News

Nov 7–Nov 14 UTC · Direct repository links and separately labeled related project stories. Indexed through 11/14/2026, 12:54:37 PM UTC.

No direct repository links were found in the indexed HN discussions over the past seven days. Older discussions are available below.

Mentions over time

HN mentions by 3-hour interval8 dated mentions

Observed mentions: 2026-02-08 15:12:27 UTC to 2026-02-11 05:54:56 UTC.

01232026-02-08 15:00:00 UTC to 2026-02-08 18:00:00 UTC (exclusive): 3 mentions; 0 submissions, 3 commentsFeb 8, 15:002026-02-08 18:00:00 UTC to 2026-02-08 21:00:00 UTC (exclusive): 2 mentions; 0 submissions, 2 comments2026-02-08 21:00:00 UTC to 2026-02-09 00:00:00 UTC (exclusive): 1 mentions; 0 submissions, 1 comments2026-02-09 00:00:00 UTC to 2026-02-09 03:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2026-02-09 03:00:00 UTC to 2026-02-09 06:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2026-02-09 06:00:00 UTC to 2026-02-09 09:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2026-02-09 09:00:00 UTC to 2026-02-09 12:00:00 UTC (exclusive): 1 mentions; 0 submissions, 1 comments2026-02-09 12:00:00 UTC to 2026-02-09 15:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2026-02-09 15:00:00 UTC to 2026-02-09 18:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2026-02-09 18:00:00 UTC to 2026-02-09 21:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2026-02-09 21:00:00 UTC to 2026-02-10 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 commentsFeb 9, 21:002026-02-10 00:00:00 UTC to 2026-02-10 03:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2026-02-10 03:00:00 UTC to 2026-02-10 06:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2026-02-10 06:00:00 UTC to 2026-02-10 09:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2026-02-10 09:00:00 UTC to 2026-02-10 12:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2026-02-10 12:00:00 UTC to 2026-02-10 15:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2026-02-10 15:00:00 UTC to 2026-02-10 18:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2026-02-10 18:00:00 UTC to 2026-02-10 21:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2026-02-10 21:00:00 UTC to 2026-02-11 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2026-02-11 00:00:00 UTC to 2026-02-11 03:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2026-02-11 03:00:00 UTC to 2026-02-11 06:00:00 UTC (exclusive): 1 mentions; 1 submissions, 0 commentsFeb 11, 03:00

Counts come from the repository’s dated source evidence. Index cutoff: 2026-11-02 08:16:59 UTC.

View mention counts and date ranges
UTC ranges include their start and exclude their end. Select a period to filter the source evidence.
PeriodStart (UTC)End (exclusive, UTC)MentionsSubmissionsComments
Feb 8, 15:002026-02-08 15:00:00 UTC2026-02-08 18:00:00 UTC303
Feb 8, 18:002026-02-08 18:00:00 UTC2026-02-08 21:00:00 UTC202
Feb 8, 21:002026-02-08 21:00:00 UTC2026-02-09 00:00:00 UTC101
Feb 9, 00:002026-02-09 00:00:00 UTC2026-02-09 03:00:00 UTC000
Feb 9, 03:002026-02-09 03:00:00 UTC2026-02-09 06:00:00 UTC000
Feb 9, 06:002026-02-09 06:00:00 UTC2026-02-09 09:00:00 UTC000
Feb 9, 09:002026-02-09 09:00:00 UTC2026-02-09 12:00:00 UTC101
Feb 9, 12:002026-02-09 12:00:00 UTC2026-02-09 15:00:00 UTC000
Feb 9, 15:002026-02-09 15:00:00 UTC2026-02-09 18:00:00 UTC000
Feb 9, 18:002026-02-09 18:00:00 UTC2026-02-09 21:00:00 UTC000
Feb 9, 21:002026-02-09 21:00:00 UTC2026-02-10 00:00:00 UTC000
Feb 10, 00:002026-02-10 00:00:00 UTC2026-02-10 03:00:00 UTC000
Feb 10, 03:002026-02-10 03:00:00 UTC2026-02-10 06:00:00 UTC000
Feb 10, 06:002026-02-10 06:00:00 UTC2026-02-10 09:00:00 UTC000
Feb 10, 09:002026-02-10 09:00:00 UTC2026-02-10 12:00:00 UTC000
Feb 10, 12:002026-02-10 12:00:00 UTC2026-02-10 15:00:00 UTC000
Feb 10, 15:002026-02-10 15:00:00 UTC2026-02-10 18:00:00 UTC000
Feb 10, 18:002026-02-10 18:00:00 UTC2026-02-10 21:00:00 UTC000
Feb 10, 21:002026-02-10 21:00:00 UTC2026-02-11 00:00:00 UTC000
Feb 11, 00:002026-02-11 00:00:00 UTC2026-02-11 03:00:00 UTC000
Feb 11, 03:002026-02-11 03:00:00 UTC2026-02-11 06:00:00 UTC110

What Hacker News says

8 sources
I thought that it was to allow non-tech people to start making their own workflows/CI in a no/low-code way and compete against successful companies on this market. But the implementation is comically awful. Sure, you can "just write natural language" instructions and hope for the best. But they couldn't fully get away from their old demons and you still have to pay the YAML tax to set the necessary guardrails. I can't help but laugh at their example: https://github.com/github/gh-aw?tab=readme-ov-file#how-it-wo... They wrote 16 words in Markdown and... 19 in YAML. Because you can't trust the agent, you still have to write tons on gibberish YAML. I'm trying to understand it, but first you give permissions, here they only provide read permissions. And then give output permissions, which are actually write permissions on a smaller scope than
Read the rest
the previous ones. Obviously they also absolve themselves from anything wrong that could happen by telling users to be careful. And they also suggest to setup an egress firewall to avoid the agents being too loose: https://github.com/github/gh-aw-firewall Why setting-up an actual workflow engine on an infra managed by IT with actual security tooling when you can just stick together a few bits of YAML and Markdown on Github, right?
In GitHub Agentic Workflows
I noticed this unusual line in go.mod and got curious why it is using replace for this (typically you would `go get github.com/Masterminds/semver/v3@v3.4.0` instead). replace github.com/Masterminds/semver/v3 => github.com/Masterminds/semver/v3 v3.4.0 I found this very questionable PR[0]. It appears to have been triggered by dependabot creating an issue for a version upgrade -- which is probably unnecessary to begin with. The copilot agent then implemented that by adding a replace statement, which is not how you are supposed to do this. It also included some seemingly-unrelated changes. The copilot reviewer called out the unrelated changes, but the human maintainer apparently didn't notice and merged anyway. There is just so much going wrong here. [0] https://github.com/github/gh-aw/pull/4469
In GitHub Agentic Workflows

MAKE YOURSELF AT HOME

A few shortcuts

/
Search the collection
?
Open this guide
Esc
Close dialogs and navigation

Your saved repositories and interests stay in this browser.