Cairn
NousResearch/hermes-agent

RL Training docs missing links to related tools

Cluster 7724. Data as of

Nothing open on GitHub. Fix merged in #14506 on 23 Apr 2026. Check it covers your case.

The short answer

0open issues
0open PRs
4items grouped
Known?
Yes. 4 related items grouped here, 1 issue already closed.
Fix event
A fix was merged to main in PR #14506. Check it covers your case. No release data is tracked.
Tracker
The maintainers' tracker marks this unresolved. That is separate from the fix event.
Still open
Nothing open on GitHub.

These issues and PRs address missing hyperlinks to Atropos, Tinker, and Weights & Biases (wandb) in the User Guide's RL Training page. Multiple fix attempts were made to add the absent references.

Open issues0

No open issues.

Open PRs0

No open pull requests.

Fixes on record

Merged to main. A stamp counts the issues a fix is linked to.

  • #14506 docs(rl-training): link Atropos, Tinker, and wandb (salvage #7727)

    merged to main

    files: scripts/release.py, website/docs/user-guide/features/rl-training.md

    Show the diff
    • scripts/release.py
      @@ -402,6 +402,7 @@
     "[redacted:email]": "TaroballzChen",
     "[email protected]": "Lind3ey",
     "[redacted:email]": "phpoh",
+    "[redacted:email]": "vivganes",
 }
    • website/docs/user-guide/features/rl-training.md
      @@ -12,8 +12,8 @@ Hermes Agent includes an integrated RL (Reinforcement Learning) training pipelin
 
 The RL training system consists of three components:
 
-1. **Atropos** — A trajectory API server that coordinates environment interactions, manages rollout groups, and computes advantages
-2. **Tinker** — A training service that handles model weights, LoRA training, sampling/inference, and optimizer steps
+1. **[Atropos](https://github.com/NousResearch/atropos)** — A trajectory API server that coordinates environment interactions, manages rollout groups, and computes advantages
+2. **[Tinker](https://thinkingmachines.ai/tinker/)** — A training service that handles model weights, LoRA training, sampling/inference, and optimizer steps
 3. **Environments** — Python classes that define tasks, scoring, and reward functions (e.g., GSM8K math problems)
 
 The agent can discover environments, configure training parameters, launch training runs, and monitor metrics — all through a set of `rl_*` tools.
@@ -24,7 +24,7 @@ RL training requires:
 
 - **Python >= 3.11** (Tinker package requirement)
 - **TINKER_API_KEY** — API key for the Tinker training service
-- **WANDB_API_KEY** — API key for Weights & Biases metrics tracking
+- **WANDB_API_KEY** — API key for [Weights & Biases](https://wandb.ai/) metrics tracking
 - The `tinker-atropos` submodule (at `tinker-atropos/` relative to the Hermes root)
 
 ```bash

2 PRs closed without merging

From the close comments: superseded by another PR 1 · won't fix / by design 1

  • #7727 Fix: User guide missing links to Atropos and wandb · superseded by another PR → #14506
  • #11749 docs(rl-training): link Atropos, Tinker, and Weights & Biases · won't fix / by design
Closed issues · 1
  • Closed#7724[Bug]: No links for related tools in User guide - RL Training page
How this cluster was grouped
  • Link evidence (structural links throughout): every member is connected by structural evidence: shared changed files, or a closing/superseded reference.
  • Pairwise link density 0.50: the share of item pairs that carry a link, counting a structural link in full and a relevance-only link at 0.36. 1.00 means every pair is linked.

Pick up a Lab task

Check whether a fix covers the open issues here, with your own agent. Bring back evidence for maintainers.

Open the Lab

At a glance

Merged PRs
#14506
Closed issues
1
Attempts
2 PRs closed without merging
Fix link checked
23 Apr 2026. This confirmation is old and may be out of date (a revert or reopen would not have invalidated it here); re-verify.

For your agent

The same facts, typed.

cluster/7724.json
cluster/7724.md