Back to Home
OpenAF icon

mini-a

Verified Safe

by OpenAF

Overview

A goal-oriented autonomous agent for orchestrating LLMs, shell commands, and MCP servers to achieve user-defined objectives.

Installation

Run Command
opack exec mini-a

Environment Variables

  • OAF_MODEL
  • OAF_LC_MODEL
  • OAF_MINI_A_CON_HIST_SIZE
  • OAF_MINI_A_LIBS
  • OAF_MINI_A_NOJSONPROMPT
  • OAF_MINI_A_LCNOJSONPROMPT
  • OAF_MINI_A_MODE
  • AWS_ACCESS_KEY_ID
  • AWS_SECRET_ACCESS_KEY
  • AWS_SESSION_TOKEN

Security Notes

Mini-A is designed for powerful autonomous execution, including shell commands and filesystem modifications. It has robust built-in safety features: shell access and write operations are disabled by default (`useshell=false`, `readwrite=false`), dangerous commands are banned by default (e.g., `rm`, `sudo`, `curl`), and interactive confirmation (`checkall=true`) is available. Model API keys are stored encrypted. The system's power necessitates careful configuration, but defaults are secure. Client-side evaluation for charts includes basic pattern filtering.

Similar Servers

Stats

Interest Score0
Security Score8
Cost ClassLow
Avg Tokens10000
Stars0
Forks0
Last Update2026-01-17

Tags

autonomous-agentLLM-orchestratorMCP-integrationtask-planningshell-automation