Nous Research: twenty contributions landed in Hermes Agent, one review of Bot Screen

Context

Hermes Agent is Nous Research’s agent software. I use it for a fleet of agents built for owners who do not write software. The gaps I fix come from that use: the xAI provider, voice, image, reasoning effort, file delivery, context length.

Two of my pull requests were merged as opened, in October, into the plugin catalog. The others, maintainers take up again: cherry-pick, rebase, or salvage, with the author kept in the Git history. So the useful count is: the merged pull requests that contain my commits.

The survey of 28 October 2026 counts 20 of my pull requests landed: 2 merged directly, 18 taken up by maintainers, in 19 merged pull requests. On the main branch, 29 commits carry my name, 25 of them on the xAI/Grok integration. I had opened 81: 77 closed, 4 still open that day, which are not integrations.

I have worked with the Nous Research team: Teknium invited me to review Bot Screen, and twenty of my code contributions have landed in Hermes Agent, including the native xAI provider.

What was done

The nineteen merges, from the first to the last. The date is the merge date, in UTC. The title is shortened. Each link is public.

PR	Merged	Title
#5604	6 April	xAI prompt caching
#7093	10 April	Grok context lengths
#7372	10 April	Native xAI provider
#9923	14 April	xAI provider prefix
#14473	23 April	Grok transcription
#14765	23 April	xAI image generation
#22807	9 May	Reasoning effort to xAI
#29277	20 May	Retired models, migration
#29376	20 May	Voice pauses, opt-in
#30579	22 May	Grok Build context
#37089	2 June	Video model routing
#70510	24 July	x_search and xurl routing
#72170	26 July	File delivery
#85434	13 August	grok-4.6 context cache
#109295	12 September	Summary without a 400 error
#132885	5 October	fleet-policy plugin in the catalog (direct merge)
#133825	6 October	xAI transcription, pinned model
#138958	17 October	hermes-xai plugin in the catalog (direct merge)
#145718	27 October	Bot Chat delivery after a login

Merges by month

April 6, May 4, June 1, July 2, August 1, September 1, October 4. Source: GitHub API, survey of 28 October 2026. Merges by month

Category

Detail

Count

Code merged, authorship kept

29 commits, 19 merges

20 pull requests

Idea taken up, without my code

idea or approach

4

Review that led to fixes

Bot Screen

1

Credit in other PR closures

same fix (5), Bot Screen (1)

6

Pull requests I opened

77 closed, 4 open

81

GitHub API and main-branch history, read only, 28 October 2026.

Two integrations are partial, two others shared. Pull request 9923 does not keep two of the proposed changes. Pull request 14765 drops the image-edit path. Pull request 72170 brings six contributors together: one of my commits out of ten. Pull request 109295 counts me as the author of the fix, with a co-author, and tests by other people.

The bodies of these merges say so. “Cherry-picked from #5548 by @Julientalbot”. “Salvaged from #7050, contributor authorship preserved”. “Credit to @Julientalbot — authorship preserved via rebase-merge”. On pull request 70510, the maintainer writes that the routing doctrine “was right and most of it survived verbatim”.

Other pull requests take up an idea I had proposed, without my code. On 3 May, pull request 19132: “Your config.yaml integration approach was the foundation”. On 6 April, pull request 5595 applies a fix proposed in mine, without naming me. On 10 May, pull request 23291 takes the same intent by a simpler path. On 13 May, pull request 25126 lists me among the proposals it replaces. The video code comes from another author.

On 12 September, four competing pull requests for the same fix were closed naming me as first author: three with the wording “cherry-picked from #32777 by @Julientalbot, the first submitter”, the fourth with “credit goes there”. A fifth, which rebased mine, was closed the same day: “Julien Talbot stays the author”. The fix itself is the one in pull request 109295.

The review stands apart. Bot Screen shows the agent’s desktop inside Hermes Desktop, lets a person take control, then hand it back. Pull request 108914 was opened by Teknium on 12 September, and merged on 23 September. At his invitation, I reviewed the interaction between the person and the agent. The review is public the same day, at 19:14 UTC. Five cases, each with a regression probe. Three priority ones: the browser tools kept acting while the person held control; a capture crossed a full take-and-hand-back cycle; an abnormal disconnect handed control back to the agent mid-input. Two secondary ones: a stale image stayed displayed as live; one host’s control state was applied to another host, at the same profile path. Two design notes completed those five points. I wrote the limits of the review: no real trial of the remote desktop, no study with users.

What changed

Measured, on the repository. Teknium replied the same day, at 19:54 UTC: “Thanks @Julientalbot — every finding reproduced.” An online reply gives that second round a section, under my name, and names the browser probe as my test: “your probe, red on the previous head”. The five fixes and the note on an unreadable lease were in place at the merge. The note on the cue shown during human action was addressed, then the mechanism was removed on 13 September. Waiting for in-flight actions before confirming the takeover was declined, by a maintainer decision. I am a reviewer of Bot Screen, not its author. I am one reviewer among eighteen named in the body, the first on the list.

The nineteen merges are in the history. Whether they are still in today’s code, after later refactors, has not been audited.

Limits

A follow-up PR proposed on 22 September, pull request 118788, took up three of my commits on voice transcription. It landed on 6 October in pull request 133825, authorship kept: it is counted.

Pull requests still open are not counted. A closing line, “your contribution is what shipped”, on one of my closed pull requests, is contradicted by the attribution: the code that shipped comes from another author. I do not use it.

The work on these pull requests is assisted by agents. The figure of 81 pull requests opened is not a figure of 81 contributions. The figure that holds is 20 contributions landed, 29 commits, one review.

Sources

• Survey of 28 October 2026: all my pull requests, GitHub API, read only, and main-branch history (five author identities). The earlier surveys, of 27 and 28 September, counted 15 merges and 22 commits.
• Nineteen merges, links in the table above. Review: pull request 108914, review of 12 September, Teknium’s reply.
• Credits without code taken up: pull requests 19132, 5595, 23291, 25126. Closures with credit: 61777, 95796, 104377, 109207, 108747, 109446.