camel-goodmem

GoodMem integration for CAMEL.

GoodMem gives AI agents retrieval-augmented generation (RAG) memory. Store documents in a space and GoodMem chunks, embeds, and indexes them so your agent can pull back the most relevant passages on any question.

This package exposes the GoodMem API as a CAMEL BaseToolkit. Drop GoodMemToolkit into a ChatAgent and the agent can store, list, and retrieve memories alongside its other tools.

Installation

pip install camel-goodmem

For local development:

pip install -e ".[dev]"

Quickstart

import os

os.environ["GOODMEM_BASE_URL"] = "https://localhost:8080"
os.environ["GOODMEM_API_KEY"] = "gm_xxxxxxxxxxxxxxxxxxxxxxxx"
os.environ["GOODMEM_VERIFY_SSL"] = "false"  # self-signed local server

from camel.agents import ChatAgent
from camel.models import ModelFactory
from camel.types import ModelPlatformType, ModelType

from camel_goodmem import GoodMemToolkit

toolkit = GoodMemToolkit(verify_ssl=False)

embedder_id = toolkit.goodmem_list_embedders()[0]["embedderId"]
space_id = toolkit.goodmem_create_space(
    name="quickstart", embedder_id=embedder_id
)["spaceId"]

agent = ChatAgent(
    system_message=(
        f"You are an assistant whose long-term memory lives in GoodMem "
        f"space '{space_id}'. Store facts the user shares, and answer "
        "their questions from that space."
    ),
    model=ModelFactory.create(
        model_platform=ModelPlatformType.DEFAULT,
        model_type=ModelType.DEFAULT,
    ),
    tools=toolkit.get_tools(),
)

Each tool returns either a Python list or a dict with operation-specific fields. Errors raise the underlying requests exception so the agent can see and recover from them.

Available operations

Retrieval options

goodmem_retrieve_memories accepts the following parameters in addition to query, space_ids, and max_results:

Environment variables

When the env vars are set, the toolkit constructor can be called with no arguments.

Trusting the dev cert on localhost

GoodMem's local dev server ships with TLS on, using a self-signed certificate. Two ways to handle that during development:

1. Pass verify_ssl=False to GoodMemToolkit(...). The toolkit suppresses the matching urllib3 InsecureRequestWarning so your console stays clean.
2. Set GOODMEM_VERIFY_SSL=false in your environment.

For production, install the GoodMem CA certificate into your trust store and leave verify_ssl=True.

End-to-end example

examples/example_usage.py drives the toolkit through four ChatAgent scenarios: persistent project context across agent.reset(), a scribe-and-analyst team pipeline, metadata-driven retrieval with a server-side filter, and tool-call inspection of the analyst's response. The answering step uses OpenAI; install with pip install camel-goodmem[examples] and set OPENAI_API_KEY before running.

python examples/example_usage.py

License

Apache License 2.0. See LICENSE.