nerve

nerve

The Simple Agent Development Kit for LLM-based automation with native MCP support

1,278
Stars
109
Forks
1,278
Watchers
2
Issues
Nerve provides a platform for building, running, evaluating, and orchestrating large language model (LLM) agents using declarative YAML configurations. It supports both client and server roles for the Model Context Protocol (MCP), allowing seamless integration, team collaboration, and advanced agent orchestration. With extensible tool support, benchmarking, and LLM-agnostic handling via LiteLLM, it enables programmable and reproducible workflows for technical users.

Key Features

Declarative agent definition via YAML
Built-in and user-extensible tools
Native MCP support as both client and server
Structured agent benchmarking and evaluation
Workflow and pipeline composition
LLM-agnostic model switching using LiteLLM
CLI for creating, running, and managing agents
Programmable and auditable automation
Community and documentation support
Support for remote and local tool integration

Use Cases

Building custom LLM-based automations
Orchestrating multi-agent workflows with shared context
Evaluating agent performance with structured benchmarks
Integrating LLM agents into larger AI systems using MCP
Creating auditable and reproducible model pipelines
Defining interoperable agent teams for collaborative tasks
Switching easily between different LLM providers
Extending agents with custom shell or Python tools
Deploying MCP-compliant servers using YAML definitions
Automating technical or business workflows with LLM agents

README

nerve

The Simple Agent Development Kit

Documentation Release Package Docker CI License Human Coded

Join the project community on our server!

Nerve is a simple yet powerful Agent Development Kit (ADK) to build, run, evaluate, and orchestrate LLM-based agents using just YAML and a CLI. It’s designed for technical users who want programmable, auditable, and reproducible automation using large language models.

Key Features

📝 Declarative Agents

Define agents using a clean YAML format: system prompt, task, tools, and variables — all in one file.

🔧 Built-in Tools & Extensibility

Use shell commands, Python functions, or remote tools to power your agents. Tools are fully typed and annotated.

🌐 Native MCP Support (Client & Server)

Nerve is the first framework to let you define MCP servers in YAML — and act as both client and server, enabling agent teams and deep orchestration.

📊 Evaluation Mode

Benchmark your agents with YAML, Parquet, or folder-based test cases. Run reproducible tests, log structured outputs, and track regression or progress.

🔁 Workflows

Compose agents into simple, linear pipelines to create multi-step automations with shared context.

🧪 LLM-Agnostic

Built on LiteLLM, Nerve supports OpenAI, Anthropic, Ollama, and dozens more — switch models in one line.

Quick Start

bash
# 🖥️ install the project with:
pip install nerve-adk

# ⬇️ download and install an agent from a github repo with:
nerve install evilsocket/changelog

# 💡 or create an agent with a guided procedure:
nerve create new-agent

# 🚀 go!
nerve run new-agent

Read the documentation and the examples for more.

Contributing

We welcome contributions! Check out our contributing guidelines to get started and join our Discord community for help and discussion.

License

Nerve is released under the GPL 3 license.

Star History Chart

Star History

Star History Chart

Repository Owner

evilsocket
evilsocket

User

Repository Details

Language Python
Default Branch main
Size 5,580 KB
Contributors 13
License Other
MCP Verified Nov 12, 2025

Programming Languages

Python
98.81%
Jinja
0.92%
Dockerfile
0.27%

Tags

Topics

adk agent-based-modeling agent-development-kit agents ai llm mcp mcp-client model-context-protocol

Join Our Newsletter

Stay updated with the latest AI tools, news, and offers by subscribing to our weekly newsletter.

We respect your privacy. Unsubscribe at any time.

Related MCPs

Discover similar Model Context Protocol servers

  • Mastra

    Mastra

    A TypeScript framework for building scalable AI-powered agents and applications.

    Mastra is a modern TypeScript-based framework designed for developing AI-powered applications and autonomous agents. It offers model routing to integrate over 40 AI providers, a graph-based workflow engine, advanced context management, and production-ready tools for observability and evaluation. Mastra features built-in support for authoring Model Context Protocol (MCP) servers, enabling standardized exposure of agents, tools, and structured AI resources via the MCP interface.

    • 18,189
    • MCP
    • mastra-ai/mastra
  • VideoDB Agent Toolkit

    VideoDB Agent Toolkit

    AI Agent toolkit that exposes VideoDB context to LLMs with MCP support

    VideoDB Agent Toolkit provides tools for exposing VideoDB context to large language models (LLMs) and agents, enabling integration with AI-driven IDEs and chat agents. It automates context generation, metadata management, and discoverability by offering structured context files like llms.txt and llms-full.txt, and standardized access via the Model Context Protocol (MCP). The toolkit ensures synchronization of SDK versions, comprehensive documentation, and best practices for seamless AI-powered workflows.

    • 43
    • MCP
    • video-db/agent-toolkit
  • Taskade MCP

    Taskade MCP

    Tools and server for Model Context Protocol workflows and agent integration

    Taskade MCP provides an official server and tools to implement and interact with the Model Context Protocol (MCP), enabling seamless connectivity between Taskade’s API and MCP-compatible clients such as Claude or Cursor. It includes utilities for generating MCP tools from any OpenAPI schema and supports the deployment of autonomous agents, workflow automation, and real-time collaboration. The platform promotes extensibility by supporting integration via API, OpenAPI, and MCP, making it easier to build and connect agentic systems.

    • 90
    • MCP
    • taskade/mcp
  • FastMCP

    FastMCP

    The fast, Pythonic way to build MCP servers and clients.

    FastMCP is a production-ready framework for building Model Context Protocol (MCP) applications in Python. It streamlines the creation of MCP servers and clients, providing advanced features such as enterprise authentication, composable tools, OpenAPI/FastAPI generation, server proxying, deployment tools, and comprehensive client libraries. Designed for ease of use, it offers both standard protocol support and robust utilities for production deployments.

    • 20,201
    • MCP
    • jlowin/fastmcp
  • Vibe Check MCP

    Vibe Check MCP

    Plug & play agent oversight tool to keep LLMs aligned, reflective, and safe.

    Vibe Check MCP provides a mentor layer over large language model agents to prevent over-engineering and promote optimal, minimal pathways. Leveraging research-backed oversight, it integrates seamlessly as an MCP server with support for STDIO and streamable HTTP transport. The platform enhances agent reliability, improves task success rates, and significantly reduces harmful actions. Designed for easy plug-and-play with MCP-aware clients, it is trusted across multiple MCP platforms and registries.

    • 315
    • MCP
    • PV-Bhat/vibe-check-mcp-server
  • Agentic Long-Term Memory with Notion Integration

    Agentic Long-Term Memory with Notion Integration

    Production-ready agentic long-term memory and Notion integration with Model Context Protocol support.

    Agentic Long-Term Memory with Notion Integration enables AI agents to incorporate advanced long-term memory capabilities using both vector and graph databases. It offers comprehensive Notion workspace integration along with a production-ready Model Context Protocol (MCP) server supporting HTTP and stdio transports. The tool facilitates context management, tool discovery, and advanced function chaining for complex agentic workflows.

    • 4
    • MCP
    • ankitmalik84/Agentic_Longterm_Memory
  • Didn't find tool you were looking for?

    Be as detailed as possible for better results