OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
Agent Frameworks

LLM Functions

LLM Functions is a command-line framework that turns Bash, JavaScript and Python functions into callable tools for language models and agents. It generates function declarations from code comments and supports agents composed of instructions, tools and documents.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

LLM Functions — OpenViST project profile in Agent Frameworks.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use it when you want a command-line workflow for defining custom function-calling tools and composing them into agents, particularly when working with AIChat.

Who it is for

  • Developers building LLM tools around their own Bash, JavaScript or Python functions.
  • AIChat users who want to make those tools and agents available through the CLI.

Documented uses

  • Expose custom code to a language model for system-command execution or data processing.
  • Connect a model to APIs through functions written by the developer.
  • Assemble an agent from instructions, tools and local or remote text documents.
  • Make LLM Functions tools and agents available through MCP, or connect external MCP tools through its bridge.
Before you choose

Requirements & limits

The project is available as a public GitHub repository and specifies the MIT license.

  • The README lists argc and jq as prerequisites.
  • The README names AIChat as the only CLI tool then supporting the framework.
  • Selected tools may require environment variables, Node or Python dependencies, or an MCP bridge server; argc check is documented for checking readiness.
  • MCP support is split between serving LLM Functions tools and agents through MCP and using external MCP tools through a bridge.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Prepare LLM Functions for use with AIChat

Build the tool and agent declarations and connect the repository to AIChat’s functions directory.

Before you start

  • argc and jq
  • AIChat, identified in the README as the supported CLI client
  • Any Node or Python dependencies required by selected functions

Steps

  1. Clone the LLM Functions repository and enter its directory.

  2. List tool filenames in tools.txt and agent names in agents.txt.

  3. Run argc build, then argc check to check the environment and dependencies.

  4. Link the repository to AIChat’s functions directory with argc link-to-aichat or set AICHAT_FUNCTIONS_DIR to the repository path.

Expected outcome

The generated tools and agents are placed where AIChat can use them.

Guide limitations

  • The README identifies AIChat as the only CLI tool supporting LLM Functions.
  • The steps prepare and connect the framework; they do not establish that any particular custom function or integration will work.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
15 October 2026
Original website title
sigoden/llm-functions · Official homepage title · retained in its source language
How we review sourcesSuggest a correction