GitHub PR Review Agent with Hermes
Spend follows pull requests opened, not pushes and not the size of the codebase: forty opened in a week is forty runs, and a five line change costs a fraction of a nine hundred line one because the bill tracks the diff you feed the model. Hermes runs on the open Hermes models, so the per token half of that arithmetic is yours to choose when you fork it.
Watch it work before it's live
Run a staged conversation — no account needed. The agent handles it for real while a simulated world answers its tool calls; nothing touches real accounts, and nothing is actually sent.
Stream tile responses instead of buffering the whole body
Openopened by @marijke-devos
Replaces the buffered writer in the tile handler with a streaming encoder, so a 40MB vector tile stops sitting in memory before the first byte goes out. Nine files, 214 lines added, 118 removed, all under internal/tiles. Adds a benchmark showing peak memory falling from 96MB to 11MB on the Jakarta extract, plus table tests for the partial write path. The description links issue 402 and states the wire format is unchanged.
Set up in minutes
Using this template drops you into a guided setup. It asks exactly this, nothing else:
Connect GitHub
One sign-in. The agent acts through your account, scoped to what this template uses.
Connect Slack
One sign-in. The agent acts through your account, scoped to what this template uses.
Review checklist
What a pull request has to satisfy in this repository, put the way you would explain it to somebody reviewing here for the first time: which items are hard blockers, which paths you treat as sensitive, and what you want asked when the diff alone cannot settle one.
Runs on Hermes
Preselected for this page — connect your Hermes account during setup, or switch to NoClick's built-in models with one click.
Watch it handle a test run
A staged conversation against a simulated world — then it’s live.
Why Hermes for this agent
Only the opening event bills
Six pushes after the review lands add nothing to the invoice, because later pushes never wake it. The count you are budgeting for is one your repository already reports.
Different repositories, different models
Each fork carries its own model choice, so the flagship repository can have depth while the archive of quiet side projects runs on something cheap and still gets a first read.
Before you fork
How do we see a comment before a contributor does?
Fork the template and open a Test Run. It replays a staged pull request, including the fork one that quietly edits a release workflow, and shows the comment it would post without anything reaching GitHub. Read three of those and you will know whether the bar you wrote is specific enough to produce verdicts rather than shrugs.
Run it with a different agent
Put GitHub PR Review Agent to work on Hermes
Free to start. Guided setup, a test run against staged conversations, and it's live.