Skip to main content

Mantisdk - AI Agent Training and Evaluation Platform

Project description

Mantisdk

PyPI version License

AI Agent Training and Evaluation Platform

Mantisdk is a comprehensive toolkit for training and evaluating AI agents using reinforcement learning, automatic prompt optimization, and supervised fine-tuning.

Core Features

  • Turn your agent into an optimizable beast with minimal code changes
  • Build with any agent framework (LangChain, OpenAI Agent SDK, AutoGen, CrewAI, and more)
  • Selectively optimize one or more agents in a multi-agent system
  • Embraces algorithms like Reinforcement Learning, Automatic Prompt Optimization, Supervised Fine-tuning and more

Installation

pip install mantisdk

For optional dependencies:

# For LLMProxy feature (note: has strict dependency pins for boto3, grpcio, uvicorn)
pip install 'mantisdk[proxy]'

# For APO (Automatic Prompt Optimization)
pip install 'mantisdk[apo]'

# For VERL integration
pip install 'mantisdk[verl]'

# For Weave integration
pip install 'mantisdk[weave]'

# For MongoDB store
pip install 'mantisdk[mongo]'

Quick Start

import mantisdk as msk

# Initialize the client
client = msk.MantisdkClient()

# Your agent code here...

CLI Usage

# Start the Mantisdk server
msk store serve

# Run with vLLM
msk vllm start

Documentation

For full documentation, visit https://withmetis.github.io/mantis/mantisdk/

License

MIT License - see LICENSE for details.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

mantisdk-0.1.5.tar.gz (1.7 MB view details)

Uploaded Source

Built Distribution

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

mantisdk-0.1.5-py3-none-any.whl (948.2 kB view details)

Uploaded Python 3

File details

Details for the file mantisdk-0.1.5.tar.gz.

File metadata

  • Download URL: mantisdk-0.1.5.tar.gz
  • Upload date:
  • Size: 1.7 MB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.7

File hashes

Hashes for mantisdk-0.1.5.tar.gz
Algorithm Hash digest
SHA256 e7b9822dd8b0c8a9ce8757dc55e71385cf7ea5f8c6a7bb0868644e856337332d
MD5 2f9f9cf241f154d28e1ea81224d84425
BLAKE2b-256 7efecf5c2f579c11247e0338344ec3b7ee762d9ad8ea9c73910122afd18e2a04

See more details on using hashes here.

Provenance

The following attestation bundles were made for mantisdk-0.1.5.tar.gz:

Publisher: mantisdk-pypi-release.yml on metis-mantis/mantis

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

File details

Details for the file mantisdk-0.1.5-py3-none-any.whl.

File metadata

  • Download URL: mantisdk-0.1.5-py3-none-any.whl
  • Upload date:
  • Size: 948.2 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.7

File hashes

Hashes for mantisdk-0.1.5-py3-none-any.whl
Algorithm Hash digest
SHA256 62edea6d8d2a6d767a8302f33a32cd118868d725aea6934cc315496783dff47a
MD5 8fccd4ec47df1cf063005211b1ea7a00
BLAKE2b-256 2b3989ab45e27c713b38cdf91dd7b9f58cde72f361beba018de0076d910cb6b7

See more details on using hashes here.

Provenance

The following attestation bundles were made for mantisdk-0.1.5-py3-none-any.whl:

Publisher: mantisdk-pypi-release.yml on metis-mantis/mantis

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

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page