lagent vs Agentarium
Python frameworks for building and coordinating AI agents
lagent and Agentarium are Python frameworks for building AI agents and multi-agent workflows. lagent focuses on composing LLMs, tools, memory, and message handling, while Agentarium emphasizes interactive agent scenarios, custom actions, and checkpointed state.

lagent: Build LLM Agents with a PyTorch-Inspired Framework
InternLM’s Lagent is a lightweight Python framework for building LLM-based agents, using a PyTorch-inspired design for composing agents and message passing. It supports synchronous and asynchronous workflows, tools, memory, and multi-agent applications.

Agentarium: Orchestrate AI Agents in Interactive Simulations
Agentarium is a Python framework for creating and coordinating AI agents in interactive environments, with support for memory, custom actions, and checkpoints. It integrates AI providers through aisuite, making it useful for prototyping multi-agent workflows and simulations.
| lagent | Agentarium | |
|---|---|---|
| Language | Python | Python |
| License | Apache-2.0 | Apache-2.0 |
| Stars | 2.3k | 935 |
| Forks | 248 | 75 |
| Last analyzed | Oct 15, 2026 | Oct 15, 2026 |
Key differences
- lagent provides structured agent messages, customizable aggregators, and output parsers for tool calls; Agentarium focuses on agents choosing context-based actions and communicating directly.
- lagent supports synchronous and asynchronous variants across many components; Agentarium describes provider integration through aisuite.
- lagent examples include code execution, browsing, and iterative writing workflows; Agentarium targets interactive simulations and repeatable experiments with saved checkpoints.
- lagent lists topics including agent, gpt, llm, and transformers; Agentarium's listed topics are none.
- lagent has 2.3k stars and 245 forks, compared with Agentarium's 935 stars and 74 forks. Both use the Apache-2.0 license and are not archived.
Choose lagent if you…
- need structured LLM agent components for tools, memory, and message handling.
- want synchronous and asynchronous options or examples such as browsing and code execution.
- plan to build workflows that coordinate agents or use session IDs to isolate state.
Choose Agentarium if you…
- want to prototype interactive scenarios where agents act based on context and communicate.
- need custom actions defined with parameters and Python functions.
- want to save and restore agent states and interactions for repeatable experiments.
Compare the numbers side by side, or add more projects
This comparison is generated with AI from the OSRepos analyses of both projects. Always check each project's repository and documentation before choosing.