A simple framework for managing tasks using AI
autonomous AI agent projects
Autonomous agent projects, many of them open-source experiments in the style of AutoGPT and BabyAGI, let a model pursue a goal by planning and carrying out steps on its own.
The leading autonomous AI agent projects on botshub include BabyAGI, BabyCommandAGI and dimos. botshub lists 31 reviewed autonomous AI agent projects from companies around the world.
Top 10 at a glance
- 1.BabyAGI
A simple framework for managing tasks using AI
- 2.BabyCommandAGI
BabyCommandAGI is designed to test what happens when you combine CLI and LLM, which are older computer interfaces than GUI. Based on BabyAGI, and using Latest LLM API. Imagine LLM and CLI having a ...
- 3.dimos
Dimensional is the agentic operating system for physical space. Command humanoids, quadrupeds, drones, and other hardware platforms in natural language and build multi-agent systems that work seaml...
- 4.GenericAgent
Self-evolving agent: grows skill tree from 3.3K-line seed, achieving full system control with 6x less token consumption
- 5.JARVIS by Microsoft
JARVIS, a system to connect LLMs with ML community. Paper: https://arxiv.org/pdf/2303.17580.pdf
- 6.Lemon Agent
Plan-Validate-Solve (PVS) Agent for accurate, reliable and reproducable workflow automation
- 7.Mini AGI
MiniAGI is a simple general-purpose AI agent based on the OpenAI API.
- 8.Multi GPT
An experimental open-source attempt to make GPT-4 fully autonomous.
- 9.OpenAgents
[COLM 2024] OpenAgents: An Open Platform for Language Agents in the Wild
- 10.Suspicion Agent
The implementation of "Suspicion-Agent: Playing Imperfect Information Games with Theory of Mind Aware GPT-4"
Compare the top 10
| # | Name | Maker | Based in | Type | Open source |
|---|---|---|---|---|---|
| 1 | BabyAGI | BabyAGI | โ | โ | Yes |
| 2 | BabyCommandAGI | BabyCommandAGI | โ | โ | Yes |
| 3 | dimos | dimos | โ | โ | Yes |
| 4 | GenericAgent | GenericAgent | โ | โ | Yes |
| 5 | JARVIS | Microsoft | United States | โ | Yes |
| 6 | Lemon Agent | Lemon Agent | โ | โ | Yes |
| 7 | Mini AGI | Mini AGI | โ | โ | Yes |
| 8 | Multi GPT | Multi GPT | โ | โ | Yes |
| 9 | OpenAgents | OpenAgents | โ | โ | Yes |
| 10 | Suspicion Agent | Suspicion Agent | Australia | โ | Yes |
Browse by country
BabyCommandAGI is designed to test what happens when you combine CLI and LLM, which are older computer interfaces than GUI. Based on BabyAGI, and using Latest LLM API. Imagine LLM and CLI having a ...
Dimensional is the agentic operating system for physical space. Command humanoids, quadrupeds, drones, and other hardware platforms in natural language and build multi-agent systems that work seaml...
Self-evolving agent: grows skill tree from 3.3K-line seed, achieving full system control with 6x less token consumption
JARVIS, a system to connect LLMs with ML community. Paper: https://arxiv.org/pdf/2303.17580.pdf
Plan-Validate-Solve (PVS) Agent for accurate, reliable and reproducable workflow automation
MiniAGI is a simple general-purpose AI agent based on the OpenAI API.
An experimental open-source attempt to make GPT-4 fully autonomous.
[COLM 2024] OpenAgents: An Open Platform for Language Agents in the Wild
Suspicion Agent
Australia
The implementation of "Suspicion-Agent: Playing Imperfect Information Games with Theory of Mind Aware GPT-4"
BabyAGI-inspired agent, can recall infinite memory
AgentGPT
United States
Assemble, configure, and deploy autonomous AI Agents in your browser.
An LLM-powered autonomous agent platform Similar in spirit to AutoGPT and Baby AGI, but written in TypeScript. AI Legion is a framework for autonomous a...
AutoGPT
United Kingdom
Build your team of AI Experts for content, sales, research, and recurring work. Share the context, connect your tools, and let Otto coordinate.
BabyCatAGI
United States
BabyCatAGI is a mod of BabyBeeAGI, which is a mod of OG BabyAGI. BabyCatAGI is at 300 lines of code. This was built as a continued iteration on the original BabyAGI code in a lightweight way. Differences to BabyAGI include the following: - Task Creation Agent runs once - Execution Agent loops through tasks - Task dependencies for pulling relevant results - Two tools: search_tool and text_compleโฆ
Build autonomous AI agents! ๐
An Autonomous AI Agent that works
Towards a More Autonomous Agent System
OpenAGI: When LLM Meets Domain Experts
UFOยณ: Weaving the Digital Agent Galaxy
A GPT agent framework for invoking APIs
BabyDeerAGI
United States
Do, a deer, a female deer ๐ถ Introducing BabyDeerAGI ๐ถ๐ฆ๐ค Newest mod of OG @babyagi_ at ~350 lines of code. Added: ๐คน๐ปโโ๏ธParallel tasks (faster!) ๐ 3.5-turbo only (GPT-4 not required) ๐ฌUser input tool โ๏ธQuery rewrite in web search tool ๐ฅSaves results Repo URL below ๐
BabyElfAGI
United States
Meet BabyElfAGI! Biggest update to the OG @babyAGI_, finally broke out into multiple files: ๐ ๏ธ Skills Class allows for easy skill creation ๐ Dynamic Task List example w vector search ๐ Beta Reflection Agent ๐๏ธ Can read and write own code (yes it can write new skills and task list examples)
GPTSwarm
Saudi Arabia
๐ The First Self-Improving agents with RL / Prompting Optimization
LLM-powered lifelong learning agent in Minecraft
Frequently asked questions
- What are the best autonomous AI agent projects?
- The leading autonomous AI agent projects on botshub include BabyAGI, BabyCommandAGI and dimos. botshub lists 31 reviewed autonomous AI agent projects from companies around the world.
- What are autonomous AI agent projects?
- Autonomous agent projects, many of them open-source experiments in the style of AutoGPT and BabyAGI, let a model pursue a goal by planning and carrying out steps on its own.
- How many autonomous AI agent projects are listed?
- botshub currently lists 31 autonomous AI agent projects. The most listings are from United States (8) and India (1).
- Are there open-source autonomous AI agent projects?
- Yes. 30 of the 31 listings are tagged open source, including BabyAGI, BabyCommandAGI and dimos. Check each project's licence on its own page.
- How are these listings ranked?
- Listings are ordered by a quality score based on how complete and well documented each entry is. Every entry is reviewed before it is published.
Other categories
- AI coding agents (192)
- AI agent frameworks and SDKs (43)
- no-code AI agent and chatbot builders (20)
- AI agent observability and evaluation tools (10)
- AI agent infrastructure and tools (34)
- AI agent orchestration platforms and harnesses (29)
- AI assistants (123)
- AI workplace and productivity tools (62)
- AI customer support chatbots and agents (152)
- AI voice agents (31)
- AI sales and marketing agents (133)