Back to directory

npcpy

A Python library of primitives for building multimodal LLM agents, including personas, tool-using agents and knowledge graphs, that works with local backends such as Ollama and llama.cpp as well as cloud providers.

npcpy

npcpy is a Python library for research and development with multimodal language models, agentic AI, and knowledge graphs. It provides an NPC class for defining a persona with a name, a primary directive and a chosen model and provider, a direct get_llm_response function for one-off calls, and an Agent class that ships with default tools such as shell, Python, file editing and web search.

Its Context-Agent-Tool data layer is meant to enforce compliance in software rather than relying on prompt instructions, and it supports building teams of multiple agents. It works with local providers, including Ollama, llama.cpp and LM Studio, and with cloud providers, and installs with pip install npcpy.

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.