Pricing

Open-source under GNU GPL v3.0 on GitHub; no commercial hosted pricing stated in the README.

Overview

AgentForge is an extensible open-source framework for building autonomous agents and multi-agent cognitive architectures. Developers define agents with YAML prompt templates and compose them into Cogs—declarative multi-agent workflows with branching, memory, and personas. It is LLM-agnostic, with support for OpenAI, Google, Anthropic, and local models via Ollama or LM Studio, plus on-the-fly prompt editing without restarts.

Key features

Declarative YAML Cogs for multi-agent workflows
Customizable agents via YAML prompt templates
Integrated memory nodes for context-aware runs
Persona files for identity and style
LLM-agnostic provider switching
OpenAI, Google, Anthropic, Ollama, and LM Studio support
Live prompt editing without system restart

Use cases

Show all 7Show fewer

Alternatives

AutoGenMicrosoft open-source framework for multi-agent chat apps and event-driven agent systems.ai agent frameworkFree
IXOpen-source platform for building, debugging, and deploying collaborative GPT agents and workflows.ai agent frameworkFree
OpenAI Agents SDKOpen-source SDK for building agents with tools, handoffs, guardrails, and tracing.ai agent framework
AgentOpsDeveloper observability platform to trace, debug, and cost-track ai agents.AI toolFreemium
AgnoSelf-hosted Python agent platform with AgentOS runtime and browser control plane.ai agent frameworkFreemium
ArizeObservability and evaluation platform for tracing, testing, and improving ai agents.AI toolFreemium