GitHub
FreeLow-code framework for AI agents and cognitive architectures
FreeFree tier
About GitHub
AgentForge is a low-code framework for rapid development, testing, and iteration of AI-powered autonomous agents and cognitive architectures. It features declarative Cogs for orchestrating multi-agent workflows, customizable agents via YAML configuration, integrated memory for context-aware interactions, and support for multiple LLMs including OpenAI, Google Gemini, Anthropic Claude, and local models via Ollama or LMStudio. The framework enables both simple agent implementations and sophisticated multi-agent systems with minimal code, making it suitable for developers of all skill levels.
Key Features
Declarative Cogs for orchestrating multi-agent workflows with YAML
Customizable agents defined via YAML prompt templates and configuration
Integrated memory for context-aware interactions in agents and cogs
Persona configuration for agent identity, style, and context
Dynamic prompt templates that adapt to contexts and memory
LLM agnostic: supports OpenAI, Google Gemini, Anthropic Claude, Ollama, and LMStudio
On-the-fly prompt editing without restarting the system
OpenAI, Google, and Anthropic API support
Open-source model support through Ollama and LMStudio
Pros & Cons
Pros
- Low-code approach reduces development effort
- Flexible and model-agnostic: supports multiple LLM providers
- Declarative YAML configuration simplifies complex workflows
- Integrated memory enables coherent multi-turn interactions
- On-the-fly prompt editing allows real-time adjustments
- Open-source and free to use
Cons
- Actions and tools deprecated, replacement based on MCP standard pending
- Requires familiarity with YAML for configuration
- Documentation may be limited for advanced use cases
Best For
Building autonomous AI agents for various tasksDesigning multi-agent systems and cognitive architecturesRapid prototyping and testing of agent behaviorsCreating context-aware conversational agentsDeveloping workflows with branching logic and memory
FAQ
What is AgentForge?
AgentForge is a low-code framework for rapid development, testing, and iteration of AI-powered autonomous agents and cognitive architectures.
Which LLMs does AgentForge support?
AgentForge supports OpenAI, Google Gemini, Anthropic Claude, and local models via Ollama and LMStudio.
How do I install AgentForge?
Installation instructions are available in the Getting Started guide on the repository, with step-by-step instructions and prerequisites.
What are Cogs in AgentForge?
Cogs are declarative YAML configurations for orchestrating multi-agent workflows with branching logic and memory.
Is AgentForge free?
Yes, AgentForge is open-source and free to use under the license provided in the repository.