Cairn

Hermes agent rule enforcement and pre-action hooks

NousResearch/hermes-agent · cluster 9534 · agent

Data as of

5 open items. No fix on record.

The short answer

5open issues
0open PRs
11items grouped
Known?
Yes. 11 related items grouped here, 6 issues already closed.
Fix event
No merged or attempted fix PR is on record for this cluster.
Tracker
The maintainers' tracker marks this unresolved. That is separate from the fix event.
Still open
5 issues and 0 PRs. Broad area: open items may be separate problems.

These issues and PRs concern the Hermes agent's unreliable adherence to system-prompt rules (especially under recency bias), and requests or attempts to add code-level enforcement mechanisms such as PreToolUse hooks and pre-response validation rather than relying solely on prompt instructions.

Open issues5

  • Issue#26742[Feature]: First-Class Claim Verification & Audit Mechanism for Hermes Agent
  • Issue#32682Skill triggering is purely prompt-driven with no code-level enforcement
  • Issue#40662[Feature] PreToolUse enforcement hook — LLM doesn't follow system-prompt/memory rules under recency bias during debugging
  • Issue#49764[Bug]: Hermes Agent fails to follow rules in memory and skills
  • Issue#68126Framework limitation: agent cannot internalize repeated corrections — needs forced pre-action guardrails, not just system prompt rules

Open PRs0

No open pull requests.

Closed issues · 6
  • Closed#9534Feature Request: Support for Pre-Action / Interceptor Hooks in Agent Lifecycle
  • Closed#22956Feature request: Pre-response validation hook for capability claims
  • Closed#47446title: "Feature Request: Agent-level pre-response hook for enforcing meta-workflow checks (e.g. skill pre-loading)" labels: ["enhancement", "agent-core"]
  • Closed#60429[Bug]: hermes agent keeps violating rules
  • Closed#63278Hermes is forgetful?!
  • Closed#63770[Feature] PreToolUse enforcement hook — prompt-level rules unreliable under recency bias
How this cluster was grouped
  • Link evidence (automated judgement only): no structural link between members; the grouping rests entirely on an automated relevance judgement over their text.
  • Read the members yourself before treating them as one problem.
  • Pairwise link density 0.09: 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

Subsystem
agent
Closed issues
6
Attempts
0 PRs closed without merging

For your agent

The same facts, typed.

cluster/9534.json
cluster/9534.md