chemcrow-public vs llm_agents
chemcrow-public is an open-source agent for ai models and llm tooling. llm_agents is an open-source agent framework for ai models and llm tooling.
- chemcrow-public is best for answering molecular property questions such as molecular weight of a named compound.
- llm_agents is best for learning how tool-using llm agents work internally.
- What it is
- chemcrow-public is an open-source agent for ai models and llm tooling.llm_agents is an open-source agent framework for ai models and llm tooling.
- Best for
- Answering molecular property questions such as molecular weight of a named compoundLearning how tool-using LLM agents work internally
- Kind
- AgentAgent
- Pricing
- Open sourceOpen source
- Platforms
- API, self-hosted, LinuxAPI, self-hosted
- Agent type
- Open-source agentAgent framework
- GitHub stars
- 9711.1K
- Last commit
- Dec 2024Jun 2025
- License
- MITMIT
- Open source
- Good for
- Answering molecular property questions such as molecular weight of a named compound; Predicting the products of a described chemical reaction; Planning retrosynthetic routes for a target moleculeLearning how tool-using LLM agents work internally; Prototyping a simple agent that searches the web and runs Python code; Building a custom agent with your own tool classes
What chemcrow-public does
Chemistry tool integration
Combines an LLM agent with RDKit, paper-qa and PubChem-style database lookups for chemistry questions.
Retrosynthesis and reaction prediction
Uses the RXN4Chem API by default for retrosynthetic planning and reaction product prediction.
Self-hosted chemistry services
Provides Docker images so the reaction prediction and retrosynthesis services can run on your own GPU.
LangChain-based agent
Built on LangChain, so the agent chooses among tools based on the user's request.
Pip-installable Python package
Installs with pip install chemcrow and is driven from a short Python session.
What llm_agents does
Thought-action-observation loop
The agent alternates model reasoning, tool calls and tool observations until it produces a final answer.
Pluggable tool classes
Each tool is a small Python class with a name, a description and a use method that the agent can call.
Built-in search and code tools
Ships with tools for Python REPL execution, Google search via SerpAPI and Hacker News search.
OpenAI chat model support
The language model component uses the OpenAI API, configured through an environment variable key.
Minimal codebase
Kept to a few files so the full agent logic can be read and understood without heavy abstraction layers.
chemcrow-public vs llm_agents: questions
Is chemcrow-public or llm_agents cheaper?
Both are open source. Compare current plans on each official site.
What is the difference between chemcrow-public and llm_agents?
chemcrow-public is an open-source agent for ai models and llm tooling. llm_agents is an open-source agent framework for ai models and llm tooling.

