https://github.com/dreadnode/nerve

Create LLM agents without writing code.
https://github.com/dreadnode/nerve

agent-based-modeling agents ai groq llm ollama openai stateful-llm

Last synced: 4 days ago
JSON representation

Create LLM agents without writing code.

• Host: GitHub
• URL: https://github.com/dreadnode/nerve
• Owner: dreadnode
• License: other
• Created: 2024-06-07T09:58:13.000Z (8 months ago)
• Default Branch: main
• Last Pushed: 2025-01-30T16:56:01.000Z (12 days ago)
• Last Synced: 2025-01-30T17:31:46.357Z (12 days ago)
• Topics: agent-based-modeling, agents, ai, groq, llm, ollama, openai, stateful-llm
• Language: Rust
• Homepage:
• Size: 4.63 MB
• Stars: 767
• Watchers: 15
• Forks: 44
• Open Issues: 2
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

• awesome-ChatGPT-repositories - nerve - Create LLM agents without writing code. (NLP)

README

        


    





  Create LLM agents in a simple YAML based syntax.





  

  

  

  

  

  





    

        

            Documentation

        

    



- 🧑‍💻 **Agents Made Simple:** Agents are defined using YAML based files called [tasklets](https://github.com/dreadnode/nerve/blob/main/docs/tasklets.md). _The sky is the limit!_ You can define an agent for any task you desire — check out the [existing examples](https://github.com/dreadnode/nerve/tree/main/examples) for inspiration.

- 🧠 **Automated Problem Solving:** Nerve provides [a standard library of actions](https://github.com/dreadnode/nerve/blob/main/docs/namespaces.md) the agent uses autonomously to inform and enhance its performance. These include identifying specific goals required to complete the task, devising and revising a plan to achieve those goals, and creating and recalling memories comprised of pertinent information gleaned during previous actions.

- 🛠️ **Simple and Universal Tool Calling:** Nerve will automatically detect if the selected model natively supports function calling. If not, it will provide a compatibility layer that empowers the LLM to perform function calling anyway.

- 🤖 **Works with any LLM:** Nerve is an [LLM-agnostic tool](https://github.com/dreadnode/nerve/blob/main/docs/index.md#llm-support).

- 🤝 **Multi-Agent Workflows:** Nerve allows you to define a [multi-agent workflow](https://github.com/dreadnode/nerve/blob/main/docs/workflows.md), where each agent is responsible for a different part of the task.

- 💯 **Zero Code:** The project's main goal and core difference with other tools is to allow the user to instrument smart agents by writing simple YAML files.

## Usage

Please refer to the [documentation](https://github.com/dreadnode/nerve/blob/main/docs/index.md) for installation and usage instructions.

## License

Nerve is released under the GPL 3 license. To see the licenses of the project dependencies, install cargo license with `cargo install cargo-license` and then run `cargo license`.

[![Star History Chart](https://api.star-history.com/svg?repos=dreadnode/nerve&type=Date)](https://star-history.com/#dreadnode/nerve&Date)