Skip to main content

Hermes Agent memory provider plugin for recall-memory (SAG-based retrieval)

Project description

recall-memory-hermes

Hermes Agent memory provider plugin for recall-memory (SAG-based retrieval).

Installation

# Install recall-memory first
pip install recall-memory

# Install the Hermes plugin
hermes plugins install recall-memory-hermes

# Configure as memory provider
hermes memory setup
# → Select "recall" as provider

Configuration

# ~/.hermes/config.yaml
memory:
  provider: recall
  recall:
    db_path: "/path/to/recall_p0.db"      # default: auto-detect
    embed_url: "http://127.0.0.1:1234"    # LM Studio embed endpoint
    fallback_honcho: true                  # query Honcho if recall < 3 results
    fallback_honcho_url: "http://localhost:8082"

Architecture

Hermes Agent → memory tool
                  ↓
        recall-memory-hermes (plugin)
                  ↓
        ┌─────────────────┬────────────────────┐
        ▼                 ▼                    ▼
    recall (SAG)    Honcho (fallback)    SQLite (cache)
    sqlite-vec       pgvector HNSW        FTS5
    1444 memories    1625 embeddings      local

Development

# Clone
git clone https://github.com/Jnocode/recall-memory-hermes.git
cd recall-memory-hermes

# Install in dev mode
pip install -e .

# Install as Hermes plugin
hermes plugins install .

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

recall_memory_hermes-0.1.0.tar.gz (3.6 kB view details)

Uploaded Source

Built Distribution

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

recall_memory_hermes-0.1.0-py3-none-any.whl (3.8 kB view details)

Uploaded Python 3

File details

Details for the file recall_memory_hermes-0.1.0.tar.gz.

File metadata

  • Download URL: recall_memory_hermes-0.1.0.tar.gz
  • Upload date:
  • Size: 3.6 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.11.15

File hashes

Hashes for recall_memory_hermes-0.1.0.tar.gz
Algorithm Hash digest
SHA256 59a29776e7cf38612de208b37d9e6517be87fd2639eb2105d6b1e2019ae42b9d
MD5 29b1997501fec0cdaa6bf3810b44b389
BLAKE2b-256 1972ead12454611db6b89d4bf338dfdcecdd0801e5fb132d108886d06567a414

See more details on using hashes here.

File details

Details for the file recall_memory_hermes-0.1.0-py3-none-any.whl.

File metadata

File hashes

Hashes for recall_memory_hermes-0.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 2eba7a476c99d47c3468852e6aec0e5c8f4bc34454e621d17eced47fdbaf6eb0
MD5 16c78788ffea3f91a0025ce55a01ec3e
BLAKE2b-256 0f4e1dfa57e5de78e5e47a49ecc863590f775e36536cbcd424d4eb8182c2a9c1

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