AgentForge
A Python framework for creating, testing, and deploying LLM-powered agents.
🛡️ AgentReady threat assessment
MAESTRO 7-layer threat model + OWASP AIVSS risk score for AgentForge, derived from its capabilities.
These scores are auto-generated from public information (the agent's own listing, docs, and repository) using the canonical OWASP AIVSS formula and the MAESTRO framework — an estimate for guidance, not a penetration test, audit, or certification. See the scoring methodology — every score is re-derived by the same automated method as an agent's public evidence changes.
Overview
AgentForge is a low-code framework tailored for the rapid development, testing, and iteration of AI-powered autonomous agents and Cognitive Architectures. Compatible with a range of LLM models — currently supporting OpenAI, Google's Gemini, Anthropic's Claude, and Ollama or LMStudio for local LLMs — it offers the flexibility to run different models for different agents based on your specific needs.
Key features and capabilities
- Customizable Agents, Custom Tools & Actions, Dynamic Prompt Templates, Knowledge Graph Functionality, LLM Agnostic Agents (Each Agent can call different LLMs if needed), On-The-Fly Prompt Editing, OpenAI, Google & Anthropic API Support, Open-Source Model Support
Use cases
- API Automation, Custom AI Agent Development, Task Automation, Multi-Agent Simulation, Production Deployment.