humanus.cpp

Humanus (meaning "human" in Latin) is a lightweight framework inspired by OpenManus and mem0, integrated with the Model Context Protocol (MCP). humanus.cpp enables more flexible tool choices, and provides a foundation for building powerful local LLM agents.

Let's embrace local LLM agents w/ humanus.cpp!

Project Demo

How to Build

git submodule update --init

cmake -B build
cmake --build build --config Release

How to Run

Configuration

To set up your custom configuration, follow these steps:

1. Copy all files from config/example to config.
2. Replace base_url, api_key, .etc in config/config_llm.toml and other configurations in config/config*.toml according to your need.

   Note: llama-server in llama.cpp also support embedding models.

3. Fill in args after "@modelcontextprotocol/server-filesystem" for filesystem to control the access to files. For example:

[filesystem]
type = "stdio"
command = "npx"
args = ["-y",
        "@modelcontextprotocol/server-filesystem",
        "/Users/{Username}/Desktop",
        "other/path/to/your/files]

4. Ensure all requirements for the MCP servers are installed. For example, run npx playwright install first for playwright.

mcp_server

(for tools, only python_execute as an example now)

Start a MCP server with tool python_execute on port 8895 (or pass the port as an argument):

./build/bin/mcp_server <port> # Unix/MacOS

.\build\bin\Release\mcp_server.exe  <port> # Windows

humanus_cli

Run with tools python_execute, filesystem and playwright (for browser use):

./build/bin/humanus_cli # Unix/MacOS

.\build\bin\Release\humanus_cli.exe # Windows

humanus_cli_plan (WIP)

Run planning flow (only agent humanus as executor):

./build/bin/humanus_cli_plan # Unix/MacOS

.\build\bin\Release\humanus_cli_plan.exe # Windows

humanus_server (WIP)

Run agents in MCP the server (default running on port 8896):

• humanus_initialze: Pass JSON configuration (like in config/config.toml) to initialize an agent for a session. (Only one agent will be maintained for each session/client)
• humanus_run: Pass prompt to tell the agent what to do. (Only one task at a time)
• humanus_terminate: Stop the current task.
• humanus_status: Get the current states and other information about the agent and the task. Returns:
  • state: Agent state.
  • current_step: Current step index of the agent.
  • max_steps: Maximum steps executing without interaction with the user.
  • prompt_tokens: Prompt (input) tokens consumption.
  • completion_tokens: Completion (output) tokens consumption.
  • log_buffer: Logs in the buffer, like humanus_cli. Will be cleared after fetched.
  • result: Explaining what the agent did. Not empty if the task is finished.

./build/bin/humanus_server <port> # Unix/MacOS

.\build\bin\Release\humanus_cli_plan.exe <port> # Windows

Configure it in Cursor:

{
  "mcpServers": {
    "humanus": {
      "url": "http://localhost:8896/sse"
    }
  }
}

What if add humanus to mcp_servers? It might be interesting.

Acknowledgement

Cite

@misc{humanus_cpp,
  author = {Zihong Zhang and Zuchao Li},
  title = {humanus.cpp: A Lightweight C++ Framework for Local LLM Agents},
  year = {2025}
}