Awesome AI Agents › AI Agent Ecosystems

vortezwohl/Autono

⭐ 212 Python added to this list on 2025-05-02 repository created 2024-10-25

Autono is a highly robust autonomous agent framework based on the ReAct paradigm, designed to solve complex tasks through adaptive decision-making and multi-agent collaboration. Unlike traditional frameworks that rely on fixed workflows generated by LLM-based planners, Autono dynamically generates next actions during agent execution based on prior trajectories, enhancing robustness and flexibility. It introduces a timely abandonment strategy with a probabilistic penalty mechanism to address potential termination issues caused by adaptive execution paths. This strategy allows developers to balance conservative and exploratory tendencies in agent execution by tuning hyperparameters, significantly improving adaptability and task execution efficiency in complex environments. The framework supports multi-agent collaboration through a memory transfer mechanism that enables shared and dynamically updated memory among agents. This explicit division of labor allows agents to focus on specific task components, improving execution efficiency and quality. Autono is modular and compatible with the Model Context Protocol (MCP), enabling flexible action space expansion through external tool integration. Experimental results demonstrate that Autono significantly outperforms other frameworks like Autogen and Langchain in handling tasks of varying complexity, especially multi-step tasks with possible failures. It achieves high success rates in one-step tasks, multi-step tasks, and multi-step tasks with possible failures using models such as gpt-4o-mini, qwen-plus, and deepseek-v3. The framework is easy to install via PyPI or GitHub and provides a quick start guide for building custom agents. Users can define abilities as functions, instantiate agents with customizable personalities (e.g., prudent or inquisitive), and assign tasks for autonomous execution. Autono's design emphasizes robustness, adaptability, and collaboration, making it suitable for complex autonomous agent applications requiring dynamic decision-making and multi-agent coordination.

https://github.com/vortezwohl/Autono

abilitiesadaptive-decision-makingagentagent-personalitiesagiaiaiagentautogenautonomous-agentautonomous-agentsdynamic-action-generationexternal-tool-integrationframeworklangchainllm-frameworkmcpmcp-agentmcp-agent-frameworkmcp-clientmemory-transfer-mechanismmodel-context-protocolmodular-designmulti-agent-collaborationmulti-step-tasksmultiagentnlpopenaiprobabilistic-penaltypythonreactrobust-frameworktask-execution-efficiencytimely-abandonment-strategytool-learningtool-oriented-learningtransformer