Back to directory

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

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.

More in Agent frameworks

See all 902
  • Recurse

    recurse.run

    A serverless harness that lets a coding agent design, test, and deploy its own specialist sub-agents as tools, MCP servers, or bots, defined by a schema-validated manifest.

  • ProofForge

    shulgin.is-a.dev

    An AI-agent pipeline that decomposes a mathematics problem, proves each piece, and formalizes the result in Lean 4 and Mathlib until the Lean kernel accepts it, with six of its proofs already merged into Google DeepMind's formal-conjectures repository.

  • local-coder

    github.com

    Builds a local coding-agent team on top of Ollama and OpenCode by detecting the machine's hardware, recommending models for seven specialist roles, and testing whether each assigned model can actually use tools, edit a repository and pass verification.