AI Agents
babyagi
Yohei Nakajima's autonomous task agent - now a self-building agent framework in Python
★ 22.4k starsMIT
View guide →// agents · yoheinakajima/babyagi_archive
babyagi_archive
babyagi_archive is an open-source ai agents project by yoheinakajima (yoheinakajima/babyagi_archive on GitHub). It has 110 GitHub stars and 27 forks, is released under the MIT license, and was last updated on GitHub on 30 September 2024.
A frozen snapshot of the original BabyAGI autonomous-agent experiment.
★ 110 stars⑂ 27 forksMITupdated 2024-09
▦ visual — this project's README ships no embeddable screenshot,
so here's a placeholder. The guide below is complete regardless.
so here's a placeholder. The guide below is complete regardless.
// project facts
Project facts
- Repository
- yoheinakajima/babyagi_archive
- GitHub stars
- 110
- Forks
- 27
- License
- MIT
- Last updated on GitHub
- 30 September 2024
- Category
- AI Agents
- Listing
- Full install guide
// how it works
How it works
- Define the job
Write down the task or workflow you want the agent to handle.
- Get the code
Clone the repository and read the README's prerequisites.
- Set up your environment
Install dependencies and configure keys or endpoints.
- Try the quickstart
Run the sample script and check the output against the docs.
// features
Why people love it
Historical snapshot
BabyAGI as of September 2024.
Task-list loop
The classic create-prioritize-execute cycle.
Viral origins
One of the first famous agent demos.
Readable Python
Simple enough to study in an afternoon.
MIT licensed
Free to learn from.
Preserved
Won't change - stable reference.
Advertisement
// run it
Run it yourself
- Step 1 - Clone the repo
Download the source and move into the project folder.
git clone https://github.com/yoheinakajima/babyagi_archive.git cd babyagi_archive - Step 2 - Install dependencies
Create a virtual environment and install the requirements.
python -m venv .venv && source .venv/bin/activate pip install -r requirements.txt - Step 3 - Run an example
Treat these as starting points - the README documents the exact commands.
python examples/quickstart.py
// use cases
What you can build
- Study the original autonomous agent loop.
- Teach agent history with primary sources.
- Compare 2024 agent design with today's.
- Reproduce a piece of AI history.
Advertisement
// faq
Questions, answered
Who maintains this project?
Nobody actively - it is a preserved snapshot of BabyAGI as of September 2024, kept for historical reference. For maintained code, look at the active frameworks in this collection.
Is babyagi_archive free to use?
Yes - it is MIT licensed, so you can use, modify, and distribute it freely, including in commercial projects.
Can I still run it?
In principle, but it is a frozen 2024 snapshot - expect outdated dependencies and legacy API requirements. It is best used for study, not deployment.
Should I build on this?
No - it is an archived snapshot, not a maintained framework. Learn from it, then build on an actively maintained project from this collection.
Where should I start?
The README and the official docs site are the fastest path: run the quickstart example first, then adapt it to your use case.
// keep exploring
Similar tools
AI Agents
agenticSeek
A fully local Manus-style autonomous agent: browses, codes and speaks — no APIs, no subscription
★ 27.5k starsGPL-3.0
View guide →Agents
CloddsBot
Autonomous AI trading agent spanning 1000+ markets, from Polymarket to Solana DEXs.
★ 2.9k starsMIT
View guide →AI Agents
SWE-agent
Give it a GitHub issue and it tries to fix the code for you - the original SWE-bench agent
★ 20.5k starsMIT
View guide →AI Agents
openfang
An open-source agent operating system in Rust - autonomous 'Hands' that do real work
★ 18.2k starsApache-2.0
View guide →Agents
jido
Autonomous agent framework for Elixir: distributed, event-driven, dynamic.
★ 1.9k starsApache-2.0
View guide →// alternatives
Alternatives in AI Agents
The most-starred other AI Agents projects in the LibreAI catalogue — the realistic shortlist if babyagi_archive is not the right fit.
- openclaw★ 391.6k
A personal AI that really does things — on any OS, with your data staying yours.
- superpowers★ 294.9k
An agentic skills framework & software development methodology that works.
- ECC★ 275.2k
Agent harness optimization system with skills, memory and security for Claude Code, Codex and more
- hermes-agent★ 252.0k
The agent that grows with you — a Python framework for adaptive AI agents.
- deepseek-harness★ 245.5k
DeepSeek's plugin-based agent harness where everything is a plugin.
// more in agents
More in AI Agents
Nearby AI Agents projects in the catalogue, closest in stars to babyagi_archive — keep exploring the shelf either side of it.
- OpenYabby★ 130
A voice-driven multi-agent assistant that orchestrates in realtime.
- ActPlane★ 104
eBPF-powered information-flow enforcement for safer AI agents.
- agent-memory-benchmark★ 144
A benchmark for comparing AI agent memory systems head-to-head.
- AgentArk★ 92
A personal AI assistant that puts security first.
- octomind★ 151
An MCP-native AI coding agent and runtime in a single binary.
- NarraNexus★ 88
A framework for agent nexuses where intelligence emerges from interaction.
Get babyagi_archive
Free and open — grab the source, star the repo, and start creating.