docs(harness-hermes): 0.18.x memory/skill-loop verdict + Engram boundary (OPS-480)#17
Merged
Merged
Conversation
Source-verify the landscape survey's memory/skill-loop claims against hermes_cli/config.py on NousResearch/hermes-agent@main: the built-in memory provider is two flat Markdown files, not three tiers, and the skill-writing loop is on by default with unrestricted writes (no auto_create gate as a secondary source claimed). Turn hermes's own memory tier off so Engram stays the sole cross-harness memory of record, and gate agent-authored skill writes behind review. OPS-480
…-480) Append dated correction notes to the headline finding and the Hermes Agent entry rather than rewriting them, so the record shows both the original claim and the source-verified correction from the harness-hermes README Verdict section.
7ca10ce to
1524439
Compare
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
hermes_cli/config.pyonNousResearch/hermes-agent@main(not docs/blogs, several of which are wrong — see README verdict). Actual: two flat Markdown memory files (MEMORY.md/USER.md), no tier granularity; skill-writing loop (/learn,skill_manage) present and on by default with unrestricted writes.providers.<key>.api+ list-models:preset schema is correct against current runtime (theproviders:dict was write-only per a closed 2026-04 upstream bug — now fixed, bothcustom_providers:andproviders:merge at runtime).memory.memory_enabled: false) so Engram stays the sole cross-harness/cross-session memory of record; keep the skill-writing loop on but gate agent-authored skill writes behind review (skills.write_approval: true).packages/harness-hermes/README.md.Test plan
uv run pytest -qinpackages/harness-hermes— 4 passed (tests/test_presets.py,tests/test_pin_drift.py)