Back to directory

PersonaForge

A framework for designing and running AI personas that post, reply, and converse inside a simulated social media feed, for social simulation, games, and narrative generation.

PersonaForge

PersonaForge is a framework for building AI personas that behave like accounts in a simulated social media feed. Each persona has a profile covering mood, writing style, knowledge domain, and conversational memory, and personas post updates, reply to threads, and take part in multi-party conversations without being scripted line by line.

A memory graph lets personas recall past interactions, hold grudges, develop running jokes, and change topics based on context, so their behavior shifts over time. The project supports multiple LLM backends behind the personas.

It is intended for studying how AI personalities diverge and adapt under social pressure, for generating dialogue for games and storytelling, and for prototyping user-facing AI characters without building a full backend.

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.