5 Agent Frameworks tools (all free)
5 Agent Frameworks resources, picked out of 5 liked tweets, from creators like @mervenoyann, @virattt, @dabit3. 5 of them are free, freemium or open source.
smolagents is Hugging Face's lightweight agent framework that lets AI agents write and execute code actions rather than relying solely on JSON tool-calling. With added support for Vision-Language Models (VLMs), developers can create autonomous web-browsing agents that view screenshots, dismiss popups, and interact with live web pages dynamically.
ai-hedge-fund is an open-source terminal application that uses multiple AI agents to simulate investment decisions inspired by famous investor methodologies like Warren Buffett. It gathers market fundamentals, technicals, and earnings data, synthesizes them through risk and portfolio management modules, and outputs actionable signals. Designed for education and research, it features paper trading and backtesting modes without executing live trades.
Eliza is an open-source agent framework developed by ai16z for creating conversational and autonomous AI agents across platforms like Discord, Twitter, and Telegram. It provides modular support for diverse LLMs, character definition files, voice synthesis, RAG memory, and crypto wallet integrations for on-chain actions.
memary is a Python library that equips LLM agents with long-term, human-like memory using knowledge graphs. It tracks user interactions through a Memory Stream and an Entity Knowledge Store, ranking concepts by frequency and recency. By recursively querying and updating graph stores like Neo4j or FalkorDB, it lets agents retain context across sessions.
This technique has an AI browser agent automatically generate a structured skill.md file after successfully completing a complex task. On future runs, the agent reads the saved document to bypass exploratory actions, dramatically cutting down step count, execution time, and token cost. It serves as an accessible design pattern for building self-optimizing agent pipelines.