# ShaprAI

An open-source agent lifecycle management platform that turns a raw language model into a self-governing agent maintaining a consistent persona, with lifecycle commands for creating, training and evaluating agents.

ShaprAI is an agent lifecycle management platform that takes a raw language model and produces what the project calls an Elyan-class agent, one intended to keep identity coherence and resist sycophancy while operating within a configured ethical framework.

Its core install is lightweight, covering the CLI, lifecycle management and base integrations, with heavier machine-learning training stacks available as optional extras, and it supports Python 3.10 through 3.14. It exposes MCP tool schemas for created agents, including an OpenAI function-calling format, and a community-posting feature is disabled by default behind several explicit opt-in flags, with posted text checked against a spam floor rather than for correctness, and engagement rate-limited per agent.

Evaluation and synthesis commands send API keys only to the specific service they are meant for, and it installs from PyPI or from source with pip.

Website: https://github.com/Scottcjn/shaprai