fabricatio
A LLM multi-agent framework.
What it is and what it does
Fabricatio is a framework for building applications where multiple LLM-powered agents coordinate work through an event-driven architecture. It combines Python's ease of use with Rust's performance for compute-intensive operations, using PyO3 to bind them together. The library provides an EventEmitter pattern for task management, async/await support for concurrent execution, and templating via Handlebars for dynamic prompt generation.
The package is designed for developers building complex LLM workflows that require orchestration across multiple agents, integration with language models, and extensibility through custom actions. It targets scenarios where event-driven coordination, asynchronous execution, and performance matter—such as multi-turn reasoning, parallel task dispatch, or high-throughput agent systems. The framework is actively maintained and supports modern Python versions (3.12–3.14).
Use it for:
- Build multi-agent systems where agents communicate and coordinate through event-driven task queues.
- Create LLM applications requiring dynamic prompt templating and real-time interaction with language model APIs.
- Develop asynchronous workflows that execute custom actions in parallel while maintaining agent state.
- Integrate with external services (ComfyUI, RAG backends, vector databases) via extensible action handlers.
- Prototype and iterate on agent-based reasoning systems with minimal boilerplate.
Worth the install?
AI-flagged interpretation of the facts on this page — verify before relying
Fabricatio is a Python library for building LLM-powered multi-agent applications using an event-driven architecture, with Rust-backed performance for core operations and PyO3 bindings.
Yes, if you are building multi-agent LLM applications and want an event-driven framework with Rust-backed performance and active maintenance. The permissive license, modern Python support, and zero known vulnerabilities make it low-risk. Medium install friction (compiled wheels) is typical for performance-critical libraries. Not recommended if you need a mature, heavily documented framework—the project is young (first release February 2025) and has an extensive TODO list indicating ongoing development.
Install
fabricatio on PyPI
pip
pip install fabricatiouv
uv add fabricatiopoetry
poetry add fabricatioInstalling fabricatio
Before you install
Medium install friction due to compiled wheels for multiple Python versions (3.12–3.14) and platforms. Active maintenance with recent commits and no known vulnerabilities. Depends on fabricatio-core, a single runtime dependency.
License in practice
Licensed under permissive terms (MIT), allowing use in commercial and proprietary projects without significant legal constraints.
Quickstart
pip install fabricatio
from fabricatio import EventEmitter
emitter = EventEmitter()
emitter.on('task_complete', lambda result: print(result))
Requires Python 3.12 or later (3.12, 3.13, or 3.14); compiled wheels are platform-specific.
Verify before relying
- Whether the TODO items (API support, MCP server, web UI completion) are actively being developed or represent aspirational roadmap items.
- Performance characteristics and scalability limits for multi-agent workflows compared to other frameworks.
- Maturity of the Rust integration and stability of the PyO3 bindings across different deployment environments.
Package facts
| License | not declared (permissive) |
| Python support | supports the current Python release (<3.15,>=3.12) |
| Install friction | medium — platform-specific wheel |
| Runtime dependencies | 1 — fabricatio-core |
| Maintenance | actively maintained — 51 days since the last release |
| Last repo commit | |
| First released | |
| Downloads | 677,179/month — #5,381 on PyPI (30-day window, as of 2026-08-14) |
| Known vulnerabilities | none known (OSV.dev, checked 2026-08-14) |
Evidence: fabricatio-0.32.3-cp312-cp312-macosx_11_0_arm64.whl; fabricatio-0.32.3-cp312-cp312-manylinux_2_34_x86_64.whl; fabricatio-0.32.3-cp312-cp312-win_amd64.whl; fabricatio-0.32.3-cp313-cp313-macosx_11_0_arm64.whl; fabricatio-0.32.3-cp313-cp313-manylinux_2_34_aarch64.whl; fabricatio-0.32.3-cp313-cp313-manylinux_2_34_x86_64.whl; fabricatio-0.32.3-cp313-cp313-win_amd64.whl; fabricatio-0.32.3-cp314-cp314-macosx_11_0_arm64.whl; fabricatio-0.32.3-cp314-cp314-manylinux_2_34_aarch64.whl; fabricatio-0.32.3-cp314-cp314-manylinux_2_34_x86_64.whl; fabricatio-0.32.3-cp314-cp314-win_amd64.whl
Keywords: ai, agents, multi-agent, llm, pyo3
Tags
More Application Frameworks packages
FastAPI is a Python web framework for building…
permissive · top 100 on PyPI
annotated-docProvides a way to document function parameters,…
permissive · top 100 on PyPI
textualTextual is a Python framework for building…
permissive · top 100 on PyPI
typerTyper builds command-line applications from…
permissive · top 1,000 on PyPI
mcpBuild and connect to Model Context Protocol…
permissive · top 1,000 on PyPI
WerkzeugWerkzeug is a WSGI utility library providing…
permissive · top 1,000 on PyPI
autogen-coreAutoGen Core provides a runtime and…
permissive · top 5,000 on PyPI
nemo-relaynemo-relay wraps a shared Rust runtime to give…
permissive · top 15,000 on PyPI
sglang-routerA high-performance Rust-based load balancer and…
permissive · top 15,000 on PyPI
rustworkxA high-performance graph library for Python,…
permissive · top 5,000 on PyPI
agent-framework-coreBuild, orchestrate, and deploy AI agents and…
permissive · top 5,000 on PyPI
litellm-enterpriseLiteLLM Enterprise provides a unified Python…
unclear · top 5,000 on PyPI
agentscopeAgentScope is a production-ready framework for…
permissive · top 15,000 on PyPI
PraisonAIPraisonAI is a framework for building and…
permissive · top 15,000 on PyPI
nvidia-nat-langchainIntegrates LangChain and LangGraph with…
permissive · top 15,000 on PyPI
langgraphLangGraph is a low-level orchestration…
permissive · top 1,000 on PyPI