AgentForge
What it is
AgentForge is a lightweight, self-hosted platform for building and deploying AI agents using a FastAPI backend and React frontend. It supports three execution modes (Simple, Pipeline, and Custom Handler) and integrates hybrid RAG with pgvector and pg_bigm for semantic and keyword retrieval.
The problem it solves
Existing agent frameworks are often too heavy, complex, or tightly coupled, making it difficult to build lightweight, self-hosted, and customizable AI agent platforms.
What you could use it for
- Building internal chatbots with custom Python logic
- Creating multi-step AI workflows with conditional branching
- Deploying RAG-enabled agents over private document repositories
- Self-hosting a multi-tenant AI agent management system
Read the source ↗Back to the library →
Summary written by an AI model from the source; check the source before you rely on it.