mini-a
Verified Safeby OpenAF
Overview
A goal-oriented autonomous agent for orchestrating LLMs, shell commands, and MCP servers to achieve user-defined objectives.
Installation
opack exec mini-aEnvironment 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
agentor
Build and deploy scalable AI agents that can interact with various tools and communicate via A2A and MCP protocols.
Polymcp
A comprehensive TypeScript framework for building and orchestrating Model Context Protocol (MCP) servers and AI agents, enabling LLMs to intelligently discover, select, and execute external tools.
AgentUp
A developer-first framework for building, deploying, and managing secure, scalable, and configurable AI agents, supporting various agent types (reactive, iterative) and the Model-Context Protocol (MCP) for seamless interactions.
ironmanus-mcp
Orchestrates AI workflows with an 8-phase control flow and specialized tools, serving as a Model Context Protocol (MCP) server.