Search

More Filters

Show More
Add Listing
Go Back

AgentForge

0
New
Multi-Agent Platforms & Frameworks
Report

Report Abuse

Basic Information

AgentForge is a low-code framework for rapid development, testing, and iteration of AI-powered autonomous agents and cognitive architectures. It is built around three core concepts—Agents, declarative Cogs, and integrated Memory—so users can compose simple agents or sophisticated multi-agent workflows with minimal code. Configuration is primarily YAML-based for agents, personas, and Cogs, enabling prompt templates and branching logic to be defined declaratively. The project is model-agnostic and supports cloud LLMs and local models, and it documents storage and settings options for persistent memory. The repository includes guides, core concept documentation, and examples to help both newcomers and experienced developers build, run, and refine autonomous agents.

Links

Stars
684
App URL
https://github.com/DataBassGit/AgentForge
Github Repository
https://github.com/DataBassGit/AgentForge/blob/main/README.md

App Details

Features
Declarative Cogs let you orchestrate multi-agent workflows, branching logic, and memory using YAML configuration. Customizable agents are defined with YAML prompt templates and persona files to set identity and style. Integrated memory is available to agents and Cogs and uses a vector store implementation documented as ChromaDB. Dynamic prompt templates adapt to context and memory and can be edited on the fly without restarting the system. The framework is LLM-agnostic and lists support for major APIs as well as local runtimes. Documentation covers installation, usage, APIs, storage, and utilities. The README notes that legacy tools and actions are deprecated in favor of an upcoming MCP-based system.
Use Cases
AgentForge reduces the amount of code needed to build and iterate on autonomous agents and multi-agent systems by using declarative YAML and reusable components. It helps teams prototype cognitive architectures rapidly, test different models per agent, and manage contextual memory and personas to improve coherence across interactions. Model-agnostic design enables comparisons between cloud APIs and local models for privacy or cost reasons. Included documentation and guides lower the learning curve for new users while advanced configuration supports sophisticated orchestration. The project also invites community contributions and provides contact channels for collaboration. The codebase is released under GNU GPLv3, clarifying reuse and contribution terms.

Categories

Content Creation (5042)
Monetization & Business (2246)
Development Tools (1407)
Marketing & Social Media (1403)
Education & Career (1380)
Multi-Agent Platforms & Frameworks (1009)
Health & Life (957)
AI Resources (920)
Agents & Automation (778)
Data & Analytics (764)
Productivity Tools (679)
Writing & Editing (666)

Similar Listings

listing image

virtual lab

0 (0 review)
listing image

mnemo

0 (0 review)
listing image

EdgeChains

0 (0 review)
listing image

RAG Agents Accelerator

0 (0 review)
listing image

LLM Zero to Hundred

0 (0 review)

Featured Listings

Tags

Please fill the required fields*