Integration

Long-term memory for BeeAI framework

BeeAI framework (from i-am-bee) ships agents like `ReActAgent` with pluggable `BaseMemory` implementations, but the built-ins all live in-process. `EngramMemory` is a `BaseMemory` subclass that writes every message to an Engram bucket and hydrates recent history on construction, so your agents pick up where they left off after a process restart.

Get an API key (free) All integrations →

Install

Three steps: sign up for an Engram API key, paste a BYOK LLM-provider key on /models, then drop the snippet below into BeeAI framework.

Three steps to memory in your agent

Sign up. Free, no card. You'll land on a Getting Started page that walks the next two steps.
Add your LLM key. Engram is BYOK. Paste an OpenAI / Anthropic / Groq / Together / Fireworks key and we'll route every extraction and query call through your provider. You pay your provider directly. We never see your inference.
Paste the snippet below into your agent and restart it. Use Authorization: Bearer <api-key>with the API key from your portal.

beeai-framework-engram: durable BaseMemory

EngramMemory is a BaseMemory subclass that hydrates from the bucket on construction. Drop into any BeeAI agent's memory= arg. Source: github.com/lumetra-io/engram-beeai.

Install (PyPI release pending; install from source for now):

Terminal

pip install git+https://github.com/lumetra-io/engram-beeai

Export your API key:

Terminal

export ENGRAM_API_KEY="<api-key>"

Pass EngramMemory to any BeeAI agent:

Python

from beeai_framework.agents.react import ReActAgent
from beeai_framework.backend.chat import ChatModel
from beeai_framework.tools.search.duckduckgo import DuckDuckGoSearchTool
from beeai_framework_engram import EngramMemory

llm = ChatModel.from_name("ollama:granite3.3:8b")
agent = ReActAgent(
    llm=llm,
    tools=[DuckDuckGoSearchTool()],
    memory=EngramMemory(bucket="my-react-agent"),
)
result = await agent.run("What did we talk about last time?")
print(result.result.text)

What you can do once memory's wired in

Swap into `ReActAgent(memory=EngramMemory(bucket='my-react-agent'))` with a single line
Hydrate-on-construct: instantiating `EngramMemory(bucket='x')` pulls the last `hydrate_limit` messages back into the agent automatically
Per-user buckets via `EngramMemory(bucket=f'user-{user_id}')`
Call `.query('...')` for hybrid retrieval across the whole bucket when the recent-history window isn't enough

FAQ

What does `hydrate=True` (default) do?

On construction, `EngramMemory` loads up to `hydrate_limit` (default 200) recent messages from the bucket into the agent's working memory, so the agent has context from past sessions without needing to call `.query()` for it.

Does `reset()` clear the Engram bucket?

Yes. `reset()` wipes the entire bucket, so use per-agent or per-user bucket names if you don't want a reset to take out shared memory by accident.

Is the package on PyPI?

Not yet, the PyPI release is pending. Install from source with `pip install git+https://github.com/lumetra-io/engram-beeai`. The full `BaseMemory` contract is implemented (`messages`, `add`, `delete`, `reset`, `add_many`, `delete_many`, `splice`, `is_empty`, `clone`, `as_read_only`), plus an extra `await memory.query('...')` for hybrid retrieval.

Related integrations

Ship durable memory in BeeAI framework today

Free tier: 10K memories and 50K retrievals per month. No credit card. Same Engram backend powers all 41 integrations, so memories you write from one client are immediately queryable from the rest.

Start free See pricing