mentedb-crewai
MenteDB integration for CrewAI and AutoGen. Gives your multi agent teams persistent, cognitive memory that survives across sessions and tracks reasoning quality over time.
Installation
pip install mentedb-crewai
Components
MenteDBCrewMemory
A memory backend for CrewAI agents that stores and retrieves memories through MenteDB. Each agent can have its own memory space, or agents on the same team can share a common space for collaborative recall.
from crewai import Agent, Crew, Task
from mentedb_crewai import MenteDBCrewMemory
memory = MenteDBCrewMemory(
data_dir="./crew-memory",
space="research-team",
)
researcher = Agent(
role="Senior Researcher",
goal="Find comprehensive information on the topic",
memory=memory,
)
writer = Agent(
role="Technical Writer",
goal="Write clear documentation from research",
memory=MenteDBCrewMemory(
data_dir="./crew-memory",
space="research-team",
agent_name="writer",
),
)
task = Task(
description="Research and document the latest trends in vector databases",
agent=researcher,
)
crew = Crew(agents=[researcher, writer], tasks=[task])
crew.kickoff()
Memory is stored persistently, so the next time the crew runs it can recall findings from previous sessions.
MenteDBTool
A tool that lets agents query MenteDB directly using MQL (Mente Query Language). Attach it to any agent so the agent can search and retrieve from the team's knowledge base during task execution.
from crewai import Agent
from mentedb_crewai import MenteDBTool
memory_tool = MenteDBTool(data_dir="./crew-memory")
agent = Agent(
role="Analyst",
goal="Analyze data using historical context",
tools=[memory_tool],
)
The agent can then invoke the tool during its reasoning to recall past decisions, find related context, or check what the team already knows about a topic.
Usage with AutoGen
MenteDB works with AutoGen agents through the same memory and tool interfaces. Use MenteDBCrewMemory to give AutoGen agents persistent memory, or MenteDBTool to let them query the knowledge base.
from mentedb_crewai import MenteDBCrewMemory, MenteDBTool
memory = MenteDBCrewMemory(data_dir="./autogen-memory", space="dev-team")
tool = MenteDBTool(data_dir="./autogen-memory")
# Store context from agent work
memory.store("The team decided to use PostgreSQL for the main database.")
# Search for relevant memories
results = memory.search("database decision", k=5)
# Get assembled context within a token budget
context = memory.get_context("Plan the database migration", token_budget=2000)
Configuration
| Parameter | Default | Description |
|---|---|---|
data_dir |
./mentedb-data |
Path to the MenteDB data directory |
space |
default |
Memory space name for agent isolation or sharing |
agent_name |
None |
Optional agent name for per agent memory scoping |
License
Apache 2.0
1 maintainer
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file mentedb_crewai-0.12.3.tar.gz.
File metadata
- Download URL: mentedb_crewai-0.12.3.tar.gz
- Upload date:
- Size: 2.8 kB
- Tags: Source
- Uploaded using Trusted Publishing? Yes
- Uploaded via:
twine/6.1.0 CPython/3.13.12
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
4d865ae1e89ebd0b1658f29729fc55ab90d2479df5807be92c9b440fb4488416
|
|
| MD5 |
a4c43340c787e00ffba525cc2fa76e0c
|
|
| BLAKE2b-256 |
9a8bf88966927b640340a1c2d53a4ab5b698be47ab72820f13309490df9362f8
|
Provenance
The following attestation bundles were made for mentedb_crewai-0.12.3.tar.gz:
Publisher:
publish-sdks.yml on nambok/mentedb
-
Statement:
-
Statement type:
https://in-toto.io/Statement/v1 -
Predicate type:
https://docs.pypi.org/attestations/publish/v1 -
Subject name:
mentedb_crewai-0.12.3.tar.gz -
Subject digest:
4d865ae1e89ebd0b1658f29729fc55ab90d2479df5807be92c9b440fb4488416 - Sigstore transparency entry: 2171334739
- Sigstore integration time:
-
Permalink:
nambok/mentedb@108d55725f13135d68604da7a2c93252defa9c8f -
Branch / Tag:
refs/heads/main - Owner: https://github.com/nambok
-
Access:
public
-
Token Issuer:
https://token.actions.githubusercontent.com -
Runner Environment:
github-hosted -
Publication workflow:
publish-sdks.yml@108d55725f13135d68604da7a2c93252defa9c8f -
Trigger Event:
workflow_dispatch
-
Statement type:
File details
Details for the file mentedb_crewai-0.12.3-py3-none-any.whl.
File metadata
- Download URL: mentedb_crewai-0.12.3-py3-none-any.whl
- Upload date:
- Size: 4.1 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? Yes
- Uploaded via:
twine/6.1.0 CPython/3.13.12
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
20c90386c4a1b53a39824d68fd3a411f7eda8c5240cf623ab4e759cea74b5e37
|
|
| MD5 |
7dbc5acc7d58233928832a34631998b2
|
|
| BLAKE2b-256 |
4d8725290afed4a5e3f7ef6a6887beb2b8682f09a53d6085a354e40f3e6b4230
|
Provenance
The following attestation bundles were made for mentedb_crewai-0.12.3-py3-none-any.whl:
Publisher:
publish-sdks.yml on nambok/mentedb
-
Statement:
-
Statement type:
https://in-toto.io/Statement/v1 -
Predicate type:
https://docs.pypi.org/attestations/publish/v1 -
Subject name:
mentedb_crewai-0.12.3-py3-none-any.whl -
Subject digest:
20c90386c4a1b53a39824d68fd3a411f7eda8c5240cf623ab4e759cea74b5e37 - Sigstore transparency entry: 2171334796
- Sigstore integration time:
-
Permalink:
nambok/mentedb@108d55725f13135d68604da7a2c93252defa9c8f -
Branch / Tag:
refs/heads/main - Owner: https://github.com/nambok
-
Access:
public
-
Token Issuer:
https://token.actions.githubusercontent.com -
Runner Environment:
github-hosted -
Publication workflow:
publish-sdks.yml@108d55725f13135d68604da7a2c93252defa9c8f -
Trigger Event:
workflow_dispatch
-
Statement type:
