Skip to main content

Official Memori Labs long-term memory provider for Hermes Agent

Project description

Memori for Hermes Agent

Official Memori Labs provider for Hermes Agent, enabling structured long-term memory from agent trace and execution.

Memori gives Hermes Agent structured, long-term memory from agent trace and execution. It captures completed agent activity — including user goals, assistant decisions, tool usage, workflow steps, outcomes, constraints, failures, and feedback — and structures that activity into durable memory primitives for future recall. This allows Hermes agents to learn from prior execution, preserve workflow context, avoid repeated mistakes, and become more efficient over time. The provider exposes explicit tools for memory recall, summaries, quota checks, signup, and feedback.

Requirements

  • Hermes Agent with memory provider plugins
  • A Memori API key
  • Python 3.10+

Install

From this repository:

pip install -e .
pip install -e integrations/hermes

Or install the published package when available:

pip install hermes-memori

Configure

Use Hermes' memory setup flow and select memori:

hermes memory setup

If memori is not listed yet, install hermes-memori in the same Python environment Hermes uses, then set the provider manually.

Manual configuration also works:

hermes config set memory.provider memori
HERMES_HOME="${HERMES_HOME:-$HOME/.hermes}"
mkdir -p "$HERMES_HOME"
echo "MEMORI_API_KEY=your-key" >> "$HERMES_HOME/.env"

Then add $HERMES_HOME/memori.json:

{
  "entityId": "your-user-or-workspace-id",
  "projectId": "hermes"
}

Environment variables override file config:

  • MEMORI_API_KEY
  • MEMORI_ENTITY_ID
  • MEMORI_PROJECT_ID
  • MEMORI_PROCESS_ID

MEMORI_PROJECT_ID is optional. When it is not configured, Hermes-provided project context such as the active workspace, agent identity, user ID, session title, or session ID is used as the Memori project scope.

Tools

  • memori_recall
  • memori_recall_summary
  • memori_quota
  • memori_signup
  • memori_feedback

Behavior

The provider is intentionally fail-soft. Memori network failures are logged but do not stop Hermes from answering the user.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

hermes_memori-0.1.1.tar.gz (9.2 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

hermes_memori-0.1.1-py3-none-any.whl (8.9 kB view details)

Uploaded Python 3

File details

Details for the file hermes_memori-0.1.1.tar.gz.

File metadata

  • Download URL: hermes_memori-0.1.1.tar.gz
  • Upload date:
  • Size: 9.2 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.13.12

File hashes

Hashes for hermes_memori-0.1.1.tar.gz
Algorithm Hash digest
SHA256 c5b7da87a8d2b4a36b9afb03fafdab04cc426a3bc12664272db0f53e18d3e35f
MD5 32fddf5f64a0f16afe433059db02be02
BLAKE2b-256 dc7adf77d66bca069aa9bbcf5d6cd0bdba7bb4808e81a51a00116ec4bd66cbe4

See more details on using hashes here.

File details

Details for the file hermes_memori-0.1.1-py3-none-any.whl.

File metadata

  • Download URL: hermes_memori-0.1.1-py3-none-any.whl
  • Upload date:
  • Size: 8.9 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.13.12

File hashes

Hashes for hermes_memori-0.1.1-py3-none-any.whl
Algorithm Hash digest
SHA256 cce9099704191edb0018ae3ac5785949dd1a12db0c66246ecfba9e5009c45a77
MD5 d9e87fe07fd0de9941554534821835bf
BLAKE2b-256 05753d0088d35df1160cc8572e46e801434a18f3482f6a0114cfab8cb69bb69a

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page