goodmem-wandb

GoodMem client packaged for wandb agent integrations. GoodMem is a memory layer for AI agents with support for semantic storage, retrieval, and summarization. This package exposes the full GoodMem API surface as a clean Python client that can be used with any wandb agent (or any Python app).

Install

pip install goodmem-wandb

Quick start

from goodmem_wandb import GoodMemClient

client = GoodMemClient(
    base_url="http://localhost:8080",
    api_key="gm_your_key_here",
)

# 1. List available embedders
embedders = client.list_embedders()

# 2. Create a space
space = client.create_space(
    name="my-space",
    embedder_id=embedders[0]["embedderId"],
)

# 3. Store a text memory
memory = client.create_memory(
    space_id=space["spaceId"],
    text_content="Important information to remember.",
    source="manual",
    tags="test,demo",
)

# 4. Store a PDF memory
pdf_memory = client.create_memory(
    space_id=space["spaceId"],
    file_path="/path/to/document.pdf",
)

# 5. Retrieve memories by semantic search
results = client.retrieve_memories(
    query="important information",
    space_ids=[space["spaceId"]],
    reranker_id="<reranker-uuid>",     # optional
    llm_id="<llm-uuid>",               # optional, enables abstractReply
    relevance_threshold=0.5,           # optional
    llm_temperature=0.2,               # optional
    max_results=5,
    chronological_resort=False,
)

# 6. Inspect / delete
mem = client.get_memory(memory["memoryId"])
client.delete_memory(memory["memoryId"])

Available operations

Operation Method Purpose
List Embedders list_embedders() Discover available embedder models
List Spaces list_spaces() List all spaces
Get Space get_space(space_id) Fetch a single space
Create Space create_space(name, embedder_id, ...) Create or reuse a space
Update Space update_space(space_id, ...) Rename, relabel, or flip visibility
Delete Space delete_space(space_id) Delete a space and its memories
Create Memory create_memory(space_id, ...) Store text or a file as a memory
List Memories list_memories(space_id, ...) List memories in a space (paginated)
Retrieve Memories retrieve_memories(query, space_ids, ...) Semantic search across spaces
Get Memory get_memory(memory_id) Fetch one memory and its content
Delete Memory delete_memory(memory_id) Delete a memory

Retrieval options

retrieve_memories supports the full GoodMem post-processor configuration:

Argument Type Purpose
reranker_id str UUID of a reranker model to improve result ordering
llm_id str UUID of an LLM to generate contextual responses (abstractReply)
relevance_threshold float Minimum score (0–1) for including results
llm_temperature float Creativity setting for LLM generation (0–2)
max_results int Limit the number of returned memories
chronological_resort bool Reorder results by creation time

Authentication

The GoodMemClient requires:

  • base_url: The base URL of your GoodMem instance (e.g. http://localhost:8080, https://api.goodmem.ai).
  • api_key: Your GoodMem API key (X-API-Key, starts with gm_).

For self-signed certs (e.g. local dev with https://localhost:8080), pass verify_ssl=False.

License

MIT

Project links

Data verified by PyPI on May 21, 2026
Data provided by the project maintainers, verified at the time the release was uploaded to PyPI.

Key dates

PyPI data
Data sourced directly from PyPI's database.
  • Released:
Latest release

1 maintainer

PyPI data
Data sourced directly from PyPI's database.
Avatar for bashar-alrfooh from gravatar.com bashar-alrfooh

Credits

Author: PairSys

GitHub Statistics

Data verified by PyPI on May 21, 2026
The GitHub source repository was provided by the project maintainers and verified by PyPI at the time of upload. Stars, forks, and open issues/PRs are derived from that repository and have not been independently verified.

License

MIT License (MIT)

Requires

Python >=3.9

Provides Extra

dev

Tags

agents goodmem llm memory rag vector-search wandb

Classifiers

Report project as malware

Download files

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

Source Distribution

goodmem_wandb-0.1.0.tar.gz (10.2 kB view details)

Uploaded Source

Built Distribution

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

goodmem_wandb-0.1.0-py3-none-any.whl (11.3 kB view details)

Uploaded Python 3

File details

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

File metadata

  • Download URL: goodmem_wandb-0.1.0.tar.gz
  • Upload date:
  • Size: 10.2 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.12

File hashes

Hashes for goodmem_wandb-0.1.0.tar.gz
Algorithm Hash digest
SHA256 060927d1e18b45cd1a20492bd14156c25ac56c6a7aa6ab80c7a046130ebd4421
MD5 35e9ef91fe4e176ee173c8176f24c3a4
BLAKE2b-256 c2c7f0169c50e6569f9abed47bf7d2e04cdb5c51be238e6920ef42b0709c9942

See more details on using hashes here.

Provenance

The following attestation bundles were made for goodmem_wandb-0.1.0.tar.gz:

Publisher: publish.yml on PAIR-Systems-Inc/goodmem-wandb

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

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

File metadata

  • Download URL: goodmem_wandb-0.1.0-py3-none-any.whl
  • Upload date:
  • Size: 11.3 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.12

File hashes

Hashes for goodmem_wandb-0.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 56ec79893fe6c13554d5f6b075b029b32e01a0fb180e9f20f4594910dc96d031
MD5 5707a7fcc6f3f0a80d97ac5d9a5e188a
BLAKE2b-256 04067ad943bbcf1bd0d33552a9edc003d26e72986cbcc2082a345b8a8369bd3d

See more details on using hashes here.

Provenance

The following attestation bundles were made for goodmem_wandb-0.1.0-py3-none-any.whl:

Publisher: publish.yml on PAIR-Systems-Inc/goodmem-wandb

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Release history Release notifications | RSS feed

This release

0.1.0 This release

2 files

Supported by

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