Skip to main content

A lightweight framework for building AI Agents using Google Gemini API.

Project description

ToolM 🛠️

ToolM is a powerful, lightweight Python framework designed to build AI Agents exclusively using Google's Gemini API. It abstracts the complexity of connection management and session history, providing a clean interface similar to LangChain but optimized for Gemini.

Features

  • 🚀 Easy Setup: Get an agent running in 3 lines of code.
  • 🧠 Built-in Memory: Automatically manages chat history context.
  • ⚙️ Configurable: Easy customization of temperature, top_k, and model selection.
  • 🛡️ Robust Error Handling: Clear exceptions for API keys and generation errors.

Installation

pip install toolm

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

toolm-0.1.1.tar.gz (4.3 kB view details)

Uploaded Source

Built Distribution

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

toolm-0.1.1-py3-none-any.whl (5.2 kB view details)

Uploaded Python 3

File details

Details for the file toolm-0.1.1.tar.gz.

File metadata

  • Download URL: toolm-0.1.1.tar.gz
  • Upload date:
  • Size: 4.3 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.11.0

File hashes

Hashes for toolm-0.1.1.tar.gz
Algorithm Hash digest
SHA256 594b1a41a557b0f7e527cdd67256ea8e05e79062bfc22e891006fff1a31975c3
MD5 bad951870ad951598a7601a2c06dacc2
BLAKE2b-256 1ac96710f0d9d279274ff17706cad2b09a3accd5d1cc203981aa5aef3fd26faa

See more details on using hashes here.

File details

Details for the file toolm-0.1.1-py3-none-any.whl.

File metadata

  • Download URL: toolm-0.1.1-py3-none-any.whl
  • Upload date:
  • Size: 5.2 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.11.0

File hashes

Hashes for toolm-0.1.1-py3-none-any.whl
Algorithm Hash digest
SHA256 f3607fffdf0931d883a4e32f9439c4d98c045c6c329a612e987acf1369859082
MD5 1be97760d9cd7b480ac97e97d2b10150
BLAKE2b-256 94ec2aed30c10d0d71d9cd91c1c5e1d748dd34dc1ca2c03d0964e9c86448bd98

See more details on using hashes here.

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