Hermes

HydraDB memory provider for the Hermes Agent: relevant context is recalled before each turn and completed turns are saved.

HydraDB is a native Hermes Agent memory provider: relevant context is recalled before each turn and completed turns are persisted automatically. This is the proper, native way to make HydraDB Hermes’ long-term memory (alongside providers like supermemory, retaindb, and ham). It uses the HydraDB public API only (recall + knowledge ingest); no HydraDB SDK is required.

Quick Start

1. Install the provider

   Catalog (recommended)

   HydraDB is a first-party entry in the curated Hermes plugin catalog:

   hermes plugins install hydradb
   hermes memory setup hydradb
   

   Directory (drop-in)

   Clone the repo and copy the hydradb_hermes/ folder (it contains __init__.py and plugin.yaml) into your Hermes memory plugins directory:

   git clone https://github.com/hydra-db/hydradb-hermes-plugin.git
   mkdir -p ~/.hermes/plugins/memory/hydradb/
   cp -r hydradb-hermes-plugin/hydradb_hermes/. ~/.hermes/plugins/memory/hydradb/
   

   pip (from GitHub)

   pip install git+https://github.com/hydra-db/hydradb-hermes-plugin.git
   

   Registered via the hermes_agent.memory_providers entry point. The package is not on PyPI yet.

   Requires Python 3.10+ and a Hermes Agent install.

2. Get credentials

   • Create an API key from the HydraDB dashboard
   • Create or copy your database ID from the HydraDB dashboard
3. Set environment variables

   export HYDRADB_API_KEY="your-api-key"
   export HYDRADB_DATABASE="your-database"
   
4. Enable it in config.yaml

   Memory providers are single-select:

   memory:
     provider: hydradb
   

How it works

The integration implements Hermes’ MemoryProvider contract:

Method	Role	HydraDB
prefetch(query, *, session_id)	Auto-recall: context injected before the API call	Hybrid POST /query (prefers the server-built llm_prompt)
sync_turn(user, assistant, ...)	Persist the completed turn (non-blocking, off-thread)	POST /context/ingest
is_available()	Provider availability	bool(HYDRADB_API_KEY)
get_config_schema() / save_config()	Setup wizard (API key, database)
name	Provider name	"hydradb"

• Auto-recall: Before each turn, Hermes calls prefetch, which queries HydraDB and returns graph-enriched context to inject into the request.
• Auto-retain: After each turn, sync_turn persists the user/assistant exchange off-thread so the model is never blocked on a write.

MCP alternative

For pull-style recall (agent-invoked tools) instead of automatic memory, point Hermes at the HydraDB MCP server. The memory provider already gives automatic recall and retain, so MCP is optional.

Feedback and contributions

This plugin is open source. Feel free to raise an issue or contribute on GitHub.