AgentForge and mini-agi

One is a simple, general-purpose AI agent based on the OpenAI API, while the other is a broader, extensible AGI framework, suggesting the former could potentially be implemented within or extended by the latter, making them potential ecosystem siblings or a framework and a lightweight application built for it.

AgentForge
77
Verified
mini-agi
46
Emerging
Maintenance 10/25
Adoption 17/25
Maturity 25/25
Community 25/25
Maintenance 0/25
Adoption 10/25
Maturity 16/25
Community 20/25
Stars: 762
Forks: 151
Downloads: 782
Commits (30d): 0
Language: Python
License: GPL-3.0
Stars: 2,907
Forks: 310
Downloads:
Commits (30d): 0
Language: Python
License: MIT
No risk flags
Stale 6m No Package No Dependents

About AgentForge

DataBassGit/AgentForge

Extensible AGI Framework

Orchestrates agents and workflows through declarative YAML-based "Cogs" that handle multi-agent orchestration, branching logic, and integrated memory management. Supports multiple LLM providers (OpenAI, Anthropic, Google, Ollama, LMStudio) with model-agnostic agent definitions, dynamic prompt templates, and ChromaDB-backed contextual memory accessible across agents and workflows.

About mini-agi

muellerberndt/mini-agi

MiniAGI is a simple general-purpose AI agent based on the OpenAI API.

Implements autonomous task execution through chain-of-thought reasoning with built-in tools for Python code execution, shell commands, and web search. Features short-term memory with automatic summarization and optional self-criticism mode to refine outputs, all coordinated through GPT-3.5-Turbo or GPT-4 for complex multi-step objectives.

Related comparisons

Scores updated daily from GitHub, PyPI, and npm data. How scores work