autogen-goodmem

GoodMem memory and tools for the AutoGen agent framework.

autogen-goodmem gives an AutoGen agent two things:

  1. GoodMemContextProvider — an autogen_core.memory.Memory implementation backed by a GoodMem space, so context retrieval is automatic on every turn.
  2. create_goodmem_tools(client) — 11 FunctionTools the agent can call directly to manage spaces and memories.

Install

pip install autogen-goodmem

Quickstart

As an AutoGen Memory

import asyncio
from autogen_core.memory import MemoryContent, MemoryMimeType
from autogen_goodmem import GoodMemContextProvider, GoodMemMemoryConfig


async def main() -> None:
    provider = GoodMemContextProvider(
        config=GoodMemMemoryConfig(
            base_url="https://localhost:8080",
            api_key="gm_...",
            space_name="my-kb",
            embedder_id="<embedder-uuid>",
            verify_ssl=False,
        )
    )
    await provider.add(MemoryContent(content="The capital of France is Paris.", mime_type=MemoryMimeType.TEXT))
    results = await provider.query("What is the capital of France?")
    for r in results.results:
        print(r.content)
    await provider.close()


asyncio.run(main())

As tools on an agent

from autogen_goodmem import GoodMemClient, create_goodmem_tools

client = GoodMemClient(base_url="https://localhost:8080", api_key="gm_...", verify_ssl=False)
tools = create_goodmem_tools(client)  # 11 FunctionTools
# pass `tools=tools` to your AssistantAgent

Tool surface

create_goodmem_tools(client) returns these 11 tools in order:

Tool Purpose
goodmem_list_embedders List embedder models available on the server.
goodmem_list_spaces List all spaces visible to the API key.
goodmem_get_space Fetch one space by ID.
goodmem_create_space Create a space (idempotent by name).
goodmem_update_space Update name / publicRead / labels / chunking.
goodmem_delete_space Delete a space and everything in it.
goodmem_create_memory Add a memory from text or a local file.
goodmem_list_memories Paginated listing of a space's memories.
goodmem_retrieve_memories Semantic retrieval, optional reranker + LLM.
goodmem_get_memory Fetch a memory's metadata and original content.
goodmem_delete_memory Delete a memory and its embeddings.

goodmem_retrieve_memories (and GoodMemClient.retrieve_memories) accept the optional post-processor params: reranker_id, llm_id, relevance_threshold (0-1), llm_temperature (0-2), max_results, chronological_resort.

Integration tests

The tests in tests/test_goodmem_integration.py exercise every public method against a live GoodMem server. They are opt-in via the integration marker.

pip install -e ".[dev]"

export GOODMEM_API_KEY=gm_...
export GOODMEM_BASE_URL=https://localhost:8080
export GOODMEM_EMBEDDER_ID=<uuid>
export GOODMEM_RERANKER_ID=<uuid>
export GOODMEM_LLM_ID=<uuid>
export GOODMEM_PDF_PATH=/path/to/sample.pdf   # optional

python -m pytest tests/test_goodmem_integration.py -v -s -m integration

License

MIT

Project links

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: PAIR Systems

License

MIT License

Requires

Python >=3.10

Provides Extra

dev

Tags

autogen goodmem memory rag agents llm

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

autogen_goodmem-0.1.0.tar.gz (11.8 kB view details)

Uploaded Source

Built Distribution

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

autogen_goodmem-0.1.0-py3-none-any.whl (13.5 kB view details)

Uploaded Python 3

File details

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

File metadata

  • Download URL: autogen_goodmem-0.1.0.tar.gz
  • Upload date:
  • Size: 11.8 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.12

File hashes

Hashes for autogen_goodmem-0.1.0.tar.gz
Algorithm Hash digest
SHA256 109675b277cc3cfd625adf2710cb731fb543ca6b462623679497256f1b749290
MD5 b35abfe88f0be00a3851771c6d0cf391
BLAKE2b-256 19d41590a53f481df98bef99be80bb2af6e2452e98717f7c5d4e10969b934874

See more details on using hashes here.

Provenance

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

Publisher: release.yml on PAIR-Systems-Inc/goodmem-autogen

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

File details

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

File metadata

  • Download URL: autogen_goodmem-0.1.0-py3-none-any.whl
  • Upload date:
  • Size: 13.5 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.12

File hashes

Hashes for autogen_goodmem-0.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 ef681b0dfc9073eb9234c1a06bb5acdc791e549f3173dc02e0020fe5fd973ce7
MD5 b46ca0a6730e8ee29fca70b6447fc3ac
BLAKE2b-256 7094d9a63a89f285daf384efdbcb1b696e12cc3241bdf7cfac5407ae4de6b0d5

See more details on using hashes here.

Provenance

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

Publisher: release.yml on PAIR-Systems-Inc/goodmem-autogen

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