Awesome AI AgentsAI Assistants

ur-whitelab/chemcrow-public

⭐ 955 Python added to this list on 2025-04-19 repository created 2023-06-04

ChemCrow is an open-source software package designed to address complex, reasoning-intensive tasks in chemistry by integrating large language models with specialized chemical tools and databases. It leverages Langchain to orchestrate a suite of chemistry-related functionalities, including molecular property calculations, retrosynthetic planning, reaction product prediction, and literature question answering. The package incorporates well-known chemical informatics tools such as RDKit for molecular manipulation and analysis, and accesses chemical databases like PubChem and Chem-space to enrich its knowledge base. ChemCrow also integrates paper-qa for querying scientific literature, enhancing its ability to provide accurate and contextually relevant chemical information. The project supports interaction with advanced language models like GPT-4, enabling users to pose complex chemical questions and receive detailed, informed responses. It offers flexibility in deployment, allowing users to either rely on external APIs such as RXN4Chem for retrosynthesis and reaction prediction or self-host these services using provided Docker images, which can improve performance and reduce dependency on external API keys. ChemCrow is accessible via Python, with straightforward installation through pip and simple API key configuration for OpenAI and optional Serp API usage. The project is actively maintained and tested, with continuous integration workflows ensuring reliability. It is also available as a demo on HuggingFace Spaces, allowing users to try its capabilities interactively. The package is grounded in academic research, with a published paper detailing its design and capabilities, and encourages citation for scholarly use. While the current public version does not include all tools described in the original paper due to API restrictions, it remains a powerful resource for chemists and researchers seeking to augment large language models with domain-specific chemical knowledge and tools.

https://github.com/ur-whitelab/chemcrow-public

apichem-spacechemcrowchemical-databaseschemical-informaticschemical-toolschemistrydockergpt-4huggingfacelangchainlarge-language-modelsmolecular-weightopen-sourcepaper-qapubchempythonrdkitreaction-predictionretrosynthesisrxn4chemscientific-literature

Also in AI Assistants

DietrichGebert/ponytail

Ponytail enables AI agents to generate more concise, efficient, and cost-effective code by enforcing a "lazy senior dev" methodology, prioritizing existing solutions and minimal implementation.

HKUDS/DeepTutor

DeepTutor is an AI-powered personalized learning assistant that offers interactive knowledge Q&A, visualization, practice generation, and deep research capabilities to enhance education through a comprehensive and adaptive platform.

agentscope-ai/QwenPaw

QwenPaw is a personal AI assistant framework that provides local or cloud deployment, multi-channel connectivity, skill extensibility, and multi-agent collaboration for enhanced productivity and cr...

mukul975/Anthropic-Cybersecurity-Skills

A comprehensive, open-source library of 754 structured cybersecurity skills for AI agents, mapped across five prominent industry frameworks.

googleworkspace/cli

gws is a command-line tool that dynamically interfaces with Google Workspace APIs (Drive, Gmail, Calendar, Sheets, Docs, Chat, Admin) and includes AI agent skills for automation.

nanocoai/nanoclaw

NanoClaw is a lightweight, secure AI assistant platform that runs agents in isolated containers, providing a customizable alternative to OpenClaw with native Anthropic Claude Code integration and m...

assafelovic/gpt-researcher

GPT Researcher is an autonomous AI agent that conducts deep web and local research to generate detailed, unbiased research reports with citations.

screenpipe/screenpipe

Screenpipe transforms your computer into a personal, local, and private AI that records, searches, and automates based on all your digital activities.