Skip to main content
Archived

This project has been archived by its maintainers, and is no longer receiving any updates.

Mimir CrewAI Integration

Persistent memory for CrewAI agents via Mimir.

Install

Install from source (not yet published to PyPI):

pip install crewai
pip install -e integrations/crewai/

Quick Start

from crewai import Agent, Task, Crew
from mimir_crewai import MimirMemoryTool

# Create the memory tool
memory = MimirMemoryTool(
    db_path="~/.mimir/data/crew.db"
)

# Give it to your agents
researcher = Agent(
    role="Senior Researcher",
    goal="Find and analyze information",
    backstory="Expert at gathering and synthesizing data",
    tools=[memory],
    verbose=True,
)

# Agents use it naturally
task = Task(
    description=(
        "Research the competitor's pricing strategy. "
        "Use Mimir Memory to recall any previous findings on this topic, "
        "then remember your new conclusions."
    ),
    agent=researcher,
    expected_output="A report with pricing analysis",
)

crew = Crew(agents=[researcher], tasks=[task])
result = crew.kickoff()

Available Actions

Action Description Parameters
remember Store a fact or decision category, key, content, entity_type?
recall Search stored memories query, category?, limit?
journal Record a significant event event_type, description, context?
context Get session context summary (none)

How It Works

The MimirMemoryTool wraps Mimir's MCP tools as a CrewAI tool:

  • remember → mimir_remember
  • recall → mimir_recall
  • journal → mimir_journal
  • context → mimir_context

All memories persist across sessions and crews. Agents can build up a shared knowledge base over time.

Requirements

  • Mimir v1.0.0+ (curl -sSL https://raw.githubusercontent.com/Perseus-Computing-LLC/mimir/main/scripts/bootstrap.sh | bash)
  • CrewAI >= 0.30.0
  • Python 3.10+

Metadata

Release files for mimir-crewai 0.1.1

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for mimir-crewai 0.1.1
File Size Uploaded Provenance Actions
mimir_crewai-0.1.1.tar.gz 6.0 kB Without provenance Details for mimir_crewai-0.1.1.tar.gz

Built distribution (wheel)

Table of built distributions (wheels) for mimir-crewai 0.1.1
File Interpreter ABI Platform Actions
mimir_crewai-0.1.1-py3-none-any.whl Python 3 none any Details for mimir_crewai-0.1.1-py3-none-any.whl

Total release size: 11.0 kB

Release files / mimir_crewai-0.1.1.tar.gz

Download URL mimir_crewai-0.1.1.tar.gz
Size 6.0 kB
Tags Source
SHA-256 checksum
How to use checksums
27d363c6b977b4946998acc0c293b6ff514ffd21b02158b14645d1b58b99a95a
BLAKE2b-256 checksum
How to use checksums
3b63da5df568edc7b1739ff52b6822e855681aa94a3bcc1ef6236dd08263201a
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/6.2.0 CPython/3.12.13

Release files / mimir_crewai-0.1.1-py3-none-any.whl

Download URL mimir_crewai-0.1.1-py3-none-any.whl
Size 5.0 kB
Tags Python 3
SHA-256 checksum
How to use checksums
0f68bfa80829dedd9d93c73f149e3f96242018992a40932b7e2a8e82d77ec851
BLAKE2b-256 checksum
How to use checksums
807604c7f22c03a16a257cbc26cf48ca721917288165565c5239c898dd1e7591
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/6.2.0 CPython/3.12.13

Security for mimir-crewai 0.1.1

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

No provenance found

None of the files in this release were uploaded with provenance metadata.

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

To learn more about protecting yourself from malicious actors, visit our package security documentation.

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page