feat: Hermes Agent memory provider plugin#107
Merged
Conversation
Two integration paths: 1. MCP server (zero code) - add to ~/.hermes/config.yaml 2. Memory provider plugin (deeper) - hooks into Hermes agent loop Plugin implements the full MemoryProvider ABC: - prefetch() injects relevant memories before each LLM call - sync_turn() captures conversation turns in background (non-blocking) - on_session_end() marks sessions for summarization - on_pre_compress() re-injects context before compaction - on_memory_write() mirrors MEMORY.md writes - system_prompt_block() injects project profile - 3 tools: memory_recall, memory_save, memory_search Uses only stdlib (urllib, json, threading). No new dependencies.
|
Caution Review failedThe pull request is closed. ℹ️ Recent review info⚙️ Run configurationConfiguration used: defaults Review profile: CHILL Plan: Pro Run ID: 📒 Files selected for processing (1)
📝 WalkthroughWalkthroughAdds a Hermes Agent integration for agentmemory: documentation and plugin manifest plus a new Changes
Sequence Diagram(s)mermaid Estimated code review effort🎯 3 (Moderate) | ⏱️ ~20 minutes Possibly related PRs
Poem
🚥 Pre-merge checks | ✅ 2 | ❌ 1❌ Failed checks (1 warning)
✅ Passed checks (2 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. ✨ Finishing Touches📝 Generate docstrings
🧪 Generate unit tests (beta)
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 2
🧹 Nitpick comments (1)
integrations/hermes/__init__.py (1)
90-100:_secretinstance variable is stored but unused.
self._secretis assigned on line 94 but the_apifunction readsAGENTMEMORY_SECRETdirectly from the environment on each call. Consider either removing the unused instance variable or passing it to_apifor consistency.♻️ Option: Remove unused variable
def initialize(self, session_id: str, **kwargs: Any) -> None: self._base = os.environ.get("AGENTMEMORY_URL", DEFAULT_BASE_URL) self._session_id = session_id self._project = kwargs.get("cwd", os.getcwd()) - self._secret = os.environ.get("AGENTMEMORY_SECRET", "") _api(self._base, "session/start", {🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed. In `@integrations/hermes/__init__.py` around lines 90 - 100, The instance variable self._secret is assigned in initialize but never used because _api reads AGENTMEMORY_SECRET from env; update initialize to pass the stored secret into _api (e.g., include it in the payload or as an explicit parameter) so the _secret field is actually used, or remove the assignment if you prefer the env-only approach; locate the initialize method and the _api(...) call and either pass self._secret to that call or delete the self._secret assignment to eliminate the unused variable.
🤖 Prompt for all review comments with AI agents
Verify each finding against the current code and only fix it if needed.
Inline comments:
In `@integrations/hermes/__init__.py`:
- Around line 261-267: The on_pre_compress method currently calls
_api(self._base, "context", {...}) and ignores the returned context; either
re-inject the fetched context into the messages or document the no-op intent.
Fix by using the returned result.get("context") to modify messages (e.g.,
prepend/merge into the messages list or update message metadata) inside
on_pre_compress, or if the call is only meant to warm a cache, add a clear
comment explaining that behavior and leave it as a no-op; locate this change in
the on_pre_compress function and reference the _api call that fetches "context"
so reviewers can see where to apply the injection or add the explanatory
comment.
- Around line 54-67: The _api function (and is_available) must validate the
AGENTMEMORY_URL scheme before calling urlopen to prevent SSRF: parse the base
URL using urllib.parse.urlparse, ensure parsed.scheme is exactly "http" or
"https" (otherwise return None or raise a ValueError), and only then build the
full URL and call urlopen (preserve existing headers/timeout/TIMEOUT logic);
update the is_available function to perform the same scheme check on
AGENTMEMORY_URL before attempting any network call.
---
Nitpick comments:
In `@integrations/hermes/__init__.py`:
- Around line 90-100: The instance variable self._secret is assigned in
initialize but never used because _api reads AGENTMEMORY_SECRET from env; update
initialize to pass the stored secret into _api (e.g., include it in the payload
or as an explicit parameter) so the _secret field is actually used, or remove
the assignment if you prefer the env-only approach; locate the initialize method
and the _api(...) call and either pass self._secret to that call or delete the
self._secret assignment to eliminate the unused variable.
🪄 Autofix (Beta)
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
ℹ️ Review info
⚙️ Run configuration
Configuration used: defaults
Review profile: CHILL
Plan: Pro
Run ID: 226d7ee6-7500-4f5a-9343-99762dbec8e3
📒 Files selected for processing (4)
README.mdintegrations/hermes/README.mdintegrations/hermes/__init__.pyintegrations/hermes/plugin.yaml
- SSRF prevention: validate URL scheme (http/https only) before urlopen - on_pre_compress: inject fetched context into messages list (was no-op) - Remove unused self._secret; _api reads from env directly
This was referenced Apr 12, 2026
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
Adds first-class integration with Hermes Agent (33K stars, Nous Research). Two paths:
Path 1: MCP server (zero code)
Path 2: Memory provider plugin (deeper integration)
cp -r integrations/hermes ~/.hermes/plugins/memory/agentmemoryThe plugin implements the full Hermes
MemoryProviderABC:prefetch()injects relevant memories before each LLM callsync_turn()captures conversation turns (non-blocking, daemon thread)on_session_end()marks sessions for summarizationon_pre_compress()re-injects context before compactionon_memory_write()mirrors MEMORY.md writes to agentmemorysystem_prompt_block()injects project profile at session startmemory_recall,memory_save,memory_searchPure stdlib Python (urllib, json, threading). Zero dependencies beyond Hermes itself.
Files added
integrations/hermes/__init__.py- MemoryProvider implementation (~250 lines)integrations/hermes/plugin.yaml- Plugin metadataintegrations/hermes/README.md- Setup guide with both pathsREADME.md- Added Hermes to the agent setup tableTest plan
Summary by CodeRabbit
New Features
Documentation