yoheinakajima/babyagi

BabyAGI is an experimental framework for building self-modifying autonomous agents through a function management system.

View on GitHub ↗Jump to charts ↓

Summary Information

Updated 47 minutes ago
Added to GitGenius on September 2nd, 2026
Created on April 3rd, 2023
Open Issues & Pull Requests: 29 (+0)
GitHub issues: Enabled
Number of forks: 2,855
Total Stargazers: 22,354 (+0)
Total Subscribers: 308 (+0)

Charts & Analytics

Fetching additional details & charts...

Issue Activity (beta)

Issue API getrepoissuespagesummary failed: 429 Rate limit exceeded. Please try again later.

Detailed Description

BabyAGI is an experimental framework for building self-modifying autonomous agents through a function management system.

The project addresses the challenge of creating general autonomous agents by implementing the simplest possible self-building architecture. At its core is functionz, a function framework that stores, manages, and executes functions from a database. The framework uses a graph-based structure to track imports, dependent functions, and authentication secrets, with automatic loading and comprehensive logging. It includes a dashboard interface for managing functions, running updates, and viewing execution logs.

Developers considering this tool should understand it is explicitly experimental and not intended for production use. The creator notes it was built outside a professional development context and is shared primarily to spark discussion and exploration. The framework suits developers interested in experimenting with autonomous agent architectures, particularly those exploring how agents might self-modify and extend their own capabilities. The approach of organizing functions into packs and managing dependencies through metadata enables modular composition of agent behaviors.

Development activity shows the project underwent significant restructuring, with the original BabyAGI from March 2023 archived and moved to a separate repository in September 2024. The current version represents a deliberate pivot toward a simpler self-building architecture rather than incremental expansion of earlier efforts. The project includes pre-loaded function packs and draft features, indicating ongoing experimentation with the framework's capabilities. The presence of a dashboard and comprehensive logging infrastructure suggests active development focused on making the experimental system usable for exploration and iteration.