The Nextpy repository describes a self modifying framework from the project’s current summary.
Open source
24 alternativesAgentForge
AgentForge describes an extensible framework for artificial general intelligence projects.
About AgentForge
AgentForge is an open-source Python framework for building, testing and iterating on autonomous agents and multi-agent cognitive architectures with less hand-written code. Agents, workflows and personas are described in YAML, so orchestration logic can be edited and reused rather than coded from scratch.
The framework separates three core concepts: flexible Agents, declarative Cogs for workflow composition, and optional Memory for context-aware interactions. It is model-agnostic, supporting OpenAI, Google Gemini and Anthropic Claude APIs as well as local models through Ollama or LMStudio, and different agents can be pointed at different models. Prompt templates can be edited while the system runs. Getting started follows a published documentation path, beginning with an install, scaffolding of a .agentforge/ directory and a no-credential debug smoke test before a first real model run.
Key features
- Declarative YAML Cogs orchestrate multi-agent workflows with branching logic and memory
- Agents defined through YAML prompt templates and configuration files
- Optional memory nodes declared in Cogs and exposed to agents automatically
- Persona YAML files set agent identity, style and context
- Model-agnostic: different agents can use different LLM providers
- Prompts can be edited in real time without restarting the system
Best for: Developers and researchers who want a low-code, Python-based way to assemble and iterate on single- or multi-agent AI workflows across multiple LLM providers.
Good for
- Open source under the GNU General Public License v3.0
- Supports OpenAI, Google Gemini, Anthropic Claude and local models via Ollama or LMStudio
- Quickstart includes a no-credential debug smoke test before real model runs
Watch out for
- Real model runs depend on third-party provider APIs or a locally installed model runtime
- Workflows, agents and personas must be authored in YAML and a .agentforge/ directory scaffolded
- Distributed derivative works are subject to GPL-3.0 copyleft terms
AgentForge at a glance
- Category
- AI & Machine Learning › AI Agents & Automation
- Type
- Open-source project
- Pricing
- Not confirmed. Check the site
- Open source
- Yes · Source code
- Language
- English
- Last checked
- Oct 6, 2026 · Online when checked
- Listed
- Oct 5, 2026
AgentForge alternatives
Tools and sites you could use instead, ranked by how closely they match.
AIlice provides an autonomous, general-purpose AI agent through its open-source repository.
Open source
24 alternatives
AI Manus is a general-purpose AI agent system that runs tools and operations in a sandbox.
Open source
24 alternatives
Use L2MAC, an automatic computer framework built around large language models.
Open source
24 alternatives
Upsonic provides a Python framework for creating autonomous AI agents.
Open source
24 alternatives
This repository provides an open source framework for self evolving language agents.
Open source
24 alternativesPopular in AI Agents & Automation
Well-known listings from the same topic.
Simsim.aiMaya AI.smartmaya.aiMakeformsmakeforms.ioAgent Skillsagentskills.ioGenFuse AIgenfuseai.comBeambeam.ai
AgentForge FAQ
Which language models can AgentForge use?
It integrates with OpenAI, Google Gemini and Anthropic Claude APIs, and can use local models through Ollama or LMStudio. Different agents can run on different models.
Do I need API credentials to try it?
The quickstart covers installation, scaffolding of a .agentforge/ directory and a no-credential debug smoke test. A first real model run then uses the default Codex OAuth model path or another chosen provider.
What license does AgentForge use?
The project is licensed under the GNU General Public License v3.0, with details in the repository LICENSE file.
Is something wrong or out of date?
Tell us and an editor will check it.
Own this website?
Claim this listing
Claim the listing and suggest updates yourself. An editor checks every claim first.