{"categories":[{"label":"Artificial Intelligence","url":"https://skillfed.io/packages/category/scientific-engineering-artificial-intelligence/10"}],"enrichment":{"capability":"A gymnasium framework for defining custom reinforcement learning environments where language model agents interact via tool calls and messages to solve structured tasks.","skillfed_tags":["agent-training","rl-environments","llm-evaluation"],"use_cases":["Train language agents on math reasoning tasks by defining environments with calculator tools and evaluating agent trajectories","Build custom multi-step reasoning environments where agents call domain-specific tools to solve problems","Evaluate language model performance on knowledge retrieval by wrapping datasets as environments with tool-based interaction","Research agent behavior on scientific tasks like protein stability prediction or sequence analysis","Run Jupyter notebooks as interactive environments where agents execute code and observe outputs"],"what_it_does":"This package provides a gymnasium-style framework for building custom reinforcement learning environments where language model agents solve tasks by making tool calls and exchanging messages. It defines core abstractions\u2014Environment, Message, Tool, and ToolRequestMessage\u2014that handle agent-environment communication following OpenAI's message standard. The library ships with pre-built environments for math, general knowledge, biological sequences, scientific literature, and protein stability tasks, plus a Jupyter notebook environment.\n\nThe core workflow involves subclassing Environment to define custom tasks, implementing reset() to initialize state and tools, and step() to execute agent actions and return observations and rewards. Communication flows through a message formalism where agents emit ToolRequestMessage objects containing tool calls, and the environment responds with ToolResponseMessage objects or general observations. The framework is designed to integrate with a sister library for defining agents as Language Decision Processes, though it remains task-agnostic and works with any agent implementation.","worth_installing":"Yes, if you are building or evaluating language agent systems on structured tasks. The framework is actively maintained, has no known vulnerabilities, uses permissive licensing, and provides a clean abstraction for agent-environment interaction. Best suited for researchers and developers working with language model agents; less relevant if you only need a standard RL gym or don't plan to define custom environments."},"id":"fhaviary","links":{"html":"https://skillfed.io/packages/fhaviary","md":"https://skillfed.io/packages/fhaviary.md","pypi":"https://pypi.org/project/fhaviary/"},"maintenance":{"status":"active"},"meta":{"latest_release":"2026-04-16","license_spdx":null,"license_treatment":"permissive","name":"fhaviary","python_support":"supports_current","summary":"Gymnasium framework for training language model agents on constructive tasks"},"popularity":{"monthly_downloads":106011,"position":12673,"tier":"top_15000"},"security":{"n_vulnerabilities":0},"version":"0.35.0"}