mirror of
https://github.com/e2b-dev/awesome-ai-agents.git
synced 2026-02-23 03:45:13 +00:00
329 lines
7.9 KiB
Markdown
329 lines
7.9 KiB
Markdown
# 🔮 AI Agents
|
|
|
|
*Welcome to our list of AI autonomous agents. Your favorite one is missing? Add them via pull request. Discussion and feedback appreciated :heart:*
|
|
|
|
[](https://discord.gg/5GmKg5Uz)
|
|
<a href="https://github.com/tizkovatereza/AI/pulls"> <img src="https://img.shields.io/badge/PRs-welcome-brightgreen.svg?longCache=true" alt="Pull Requests">
|
|
</a> <a href="https://twitter.com/e2b_dev" target="_blank">
|
|
<img src="https://img.shields.io/twitter/follow/e2b.svg?logo=twitter"> </a>
|
|
|
|
## [AgentGPT](https://agentgpt.reworkd.ai/)
|
|
A browser-based implementation of AutoGPT, accessible via a no-code platform
|
|
<details>
|
|
|
|
### How it works
|
|
- A no-code platform
|
|
- Assigning a goal to the agent, witnessing its thinking process, and formulation of an execution plan and taking actions accordingly
|
|
|
|
### Features
|
|
- Uses OpenAI **functions**
|
|
- Supports gpt-3.5-16k, pinecone and pg_vector databases
|
|
|
|
### Links
|
|
- [Website](https://agentgpt.reworkd.ai/)
|
|
- [GitHub](https://github.com/reworkd/AgentGPT)
|
|
|
|
### Stack
|
|
- Frontend: NextJS + Typescript
|
|
- Backend: FastAPI + Python
|
|
- DB: MySQL through docker with the option of running SQLite locally
|
|
|
|
### Links
|
|
- [Documentation](https://docs.reworkd.ai/)
|
|
- [GitHub](https://github.com/reworkd/AgentGPT)
|
|
</details>
|
|
|
|
|
|
|
|
## [AI Legion](https://gpt3demo.com/apps/ai-legion)
|
|
Similar in spirit to AutoGPT and Baby AGI, but written in TypeScript
|
|
<details>
|
|
|
|
- Author: eumemic
|
|
- [Website](https://gpt3demo.com/apps/ai-legion)
|
|
- [GitHub](https://github.com/eumemic/ai-legion)
|
|
- [Twitter](https://twitter.com/dysmemic)
|
|
</details>
|
|
|
|
## [AIrplane](https://www.airplane.dev/)
|
|
Developer infrastructure for internal tools
|
|
|
|
<details>
|
|
</details>
|
|
|
|
## [Aomni](Aomni.com)
|
|
<details>
|
|
</details>
|
|
|
|
|
|
|
|
## [AutoGPT](https://autogpt.net/)
|
|
|
|
<details>
|
|
|
|
- A lot like BabyAGI combined with LangChain tools.
|
|
- Can execute many commands such as Google Search, browse websites, write to files, and execute Python files
|
|
- [GitHub](https://github.com/Significant-Gravitas/Auto-GPT)
|
|
</details>
|
|
|
|
## [BabyAGI](https://github.com/yoheinakajima/babyagi)
|
|
<details>
|
|
|
|
- Default model is OpenAI GPT3-turbo
|
|
- Paper: [Task-driven Autonomous Agent Utilizing GPT-4, Pinecone, and LangChain for Diverse Applications](https://yoheinakajima.com/task-driven-autonomous-agent-utilizing-gpt-4-pinecone-and-langchain-for-diverse-applications/)
|
|
- The main idea behind this system is that it creates tasks based on the result of previous tasks and a predefined objective.
|
|
- The script then uses OpenAI's NLP capabilities to create new tasks based on the objective
|
|
|
|
</details>
|
|
|
|
|
|
## [BabyCatAGI](https://replit.com/@YoheiNakajima/BabyCatAGI)
|
|
BabyCatAGI is a mod of BabyBeeAGI, which is a mod of OG BabyAGI. BabyCatAGI is at 300 lines of code.
|
|
<details>
|
|
|
|
</details>
|
|
|
|
## [BitBuilder](BitBuilder)
|
|
|
|
<details>
|
|
</details>
|
|
|
|
## [Bloop](https://bloop.ai/)
|
|
|
|
<details>
|
|
</details>
|
|
|
|
## [Butternut AI](Butternut.ai)
|
|
|
|
<details>
|
|
</details>
|
|
|
|
|
|
## [Camel](https://github.com/camel-ai/camel)
|
|
CAMEL: Communicative Agents for “Mind” Exploration of Large Scale Language Model Society
|
|
|
|
<details>
|
|
</details>
|
|
|
|
|
|
## [Cognosys](https://cognosys.ai)
|
|
Web based version of AutoGPT/babyAGI
|
|
|
|
<details>
|
|
|
|
- Friendly UI for building AI agents
|
|
- Author: Sully Omarr
|
|
- Twitter: https://twitter.com/SullyOmarr
|
|
|
|
</details>
|
|
|
|
|
|
## [Databerry](https://www.databerry.ai/)
|
|
|
|
|
|
<details>
|
|
</details>
|
|
|
|
|
|
|
|
## [Factory](https://www.factory.ai/)
|
|
|
|
<details>
|
|
</details>
|
|
|
|
## [Fixie](https://www.fixie.ai/)
|
|
|
|
<details>
|
|
</details>
|
|
|
|
|
|
## [GitWit](https://www.gitwit.dev/)
|
|
|
|
<details>
|
|
</details>
|
|
|
|
|
|
## [Grit](https://www.grit.io/)
|
|
|
|
<details>
|
|
</details>
|
|
|
|
|
|
## [HayStack Agent](https://docs.haystack.deepset.ai/docs/agent)
|
|
|
|
<details>
|
|
</details>
|
|
|
|
|
|
## [Hex Magic](https://hex.tech/product/magic-ai/)
|
|
|
|
<details>
|
|
</details>
|
|
|
|
|
|
## [Heymoon.ai](https://heymoon.ai/)
|
|
Personal assistant for life: to keep you on top of your calendar, tasks and information. Was at Llama event demo
|
|
|
|
<details>
|
|
</details>
|
|
|
|
|
|
## [Hyperwrite](https://www.hyperwriteai.com/)
|
|
Your personal AI writing assistant
|
|
|
|
<details>
|
|
</details>
|
|
|
|
|
|
## [Jarvis]()
|
|
|
|
<details>
|
|
</details>
|
|
|
|
|
|
## [LangChain - Agents Round](https://blog.langchain.dev/agents-round/)
|
|
|
|
<details>
|
|
</details>
|
|
|
|
|
|
## [LastMile AI](https://lastmileai.dev/)
|
|
|
|
<details>
|
|
</details>
|
|
|
|
|
|
## [Loop GPT](https://github.com/farizrahman4u/loopgpt/tree/main)
|
|
|
|
<details>
|
|
- Languages: Python
|
|
- Default model: GPT-3.5-turbo (also possible with GPT-4)
|
|
- Modular Auto-GPT Framework
|
|
- Plug N Play" API - Extensible and modular "Pythonic" framework, not just a command line tool
|
|
- Easy to add new features, integrations and custom agent capabilities, all from python code, no nasty config files!
|
|
- Minimal prompt overhead - Every token counts. We are continuously working on getting the best results with the least possible number of tokens.
|
|
- Human in the Loop - Ability to "course correct" agents who go astray via human feedback.
|
|
- Full state serialization - can save the complete state of an agent, including memory and the states of its tools to a file or python object. No external databases or vector stores required (but they are still supported)!
|
|
</details>
|
|
|
|
## [Minion AI](https://minion.ai/)
|
|
|
|
<details>
|
|
</details>
|
|
|
|
|
|
## [MultiOn](https://multion.ai/)
|
|
|
|
<details>
|
|
</details>
|
|
|
|
|
|
## [Naut ai](https://www.naut.ai/)
|
|
|
|
<details>
|
|
</details>
|
|
|
|
|
|
## [Pezzo](https://www.pezzo.ai/)
|
|
|
|
<details>
|
|
</details>
|
|
|
|
|
|
## [Saga](https://saga.so/)
|
|
|
|
<details>
|
|
</details>
|
|
|
|
|
|
## [Second](https://www.second.dev/)
|
|
|
|
<details>
|
|
</details>
|
|
|
|
|
|
## [Smol developer](https://github.com/smol-ai/developer)
|
|
|
|
<details>
|
|
</details>
|
|
|
|
## [Superagent](https://www.superagent.sh/)</details>
|
|
|
|
<details>
|
|
</details>
|
|
|
|
|
|
## [Sweep](https://sweep.dev/)
|
|
|
|
<details>
|
|
</details>
|
|
|
|
## [“Westworld” simulation](https://theolvs.github.io/westworld/)
|
|
Westworld is a multi-agent simulation library, its goal to simulate and optimize systems and environments with multiple agents interacting.
|
|
<details>
|
|
|
|
- Researchers from Stanford and Google created an interactive sandbox env with 25 Gen AI agents can simulate human behavior
|
|
- They walk in the park, join for coffee at a cafe, and share news with colleagues. They demonstrated surprisingly good social
|
|
- Westworld's inspiration is drawn from Unity software and Unity ML Agents, adapted in Python
|
|
|
|
|
|
[Underlying paper - Generative Agents](https://arxiv.org/abs/2304.03442)
|
|
- A paper simulating interactions between tens of agents
|
|
- Presenting an architecture that extends a language model to store and synthesize the agent's experiences, enabling dynamic behavior planning in an interactive sandbox environment with generative agents
|
|
|
|
</details>
|
|
|
|
|
|
### Links
|
|
- [GitHub](https://github.com/TheoLvs/westworld)
|
|
- [Documentation](https://theolvs.github.io/westworld/ )
|
|
|
|
### Languages
|
|
- The library is available on PyPi via
|
|
pip install westworld
|
|
- [Javascript version (being developed)](https://github.com/TheoLvs/westworldjs)
|
|
|
|
### Current features
|
|
|
|
- Easy creation of Grid and non-grid environments
|
|
- Objects (Agents, Obstacles, Collectibles, Triggers)
|
|
- Subclassing of different objects to create custom objects
|
|
- Spawner to generate objects randomly in the environment
|
|
- Basic rigid body system for all objects
|
|
- Simple agent behaviors (pathfinding, wandering, random walk, fleeing, vision range)
|
|
- Automatic maze generation
|
|
- Layer integration to convert image to obstacle and snap it to a grid
|
|
- Sample simulations and sample agents for classic simulations
|
|
- Simulation visualization, replay and export (gif or video)
|
|
|
|
</details>
|
|
|
|
|
|
|
|
|
|
## [Yourgoal]()
|
|
|
|
Swift implementation of BabyAGI.
|
|
|
|
<details>
|
|
Author: PJ Gray
|
|
Twitter: https://twitter.com/pj4533
|
|
</details>
|
|
|
|
<br>
|
|
|
|
## :wave: Wanna discuss AI agents and more?
|
|
|
|
- [Hit us up on discord](https://discord.gg/5GmKg5Uz)
|
|
- [Pick a date for call in our calendar](https://calendly.com/tereza-tizkova/30min)
|
|
- Write us at hello@e2b.dev
|
|
|
|
<br>
|
|
|
|
# 💪 Contributors 💪
|
|
|
|
<a href="https://github.com/tizkovatereza/AI/graphs/contributors">
|
|
<img src="https://contrib.rocks/image?repo=tizkovatereza/AI" />
|
|
</a>
|
|
|
|
Made with [contrib.rocks](https://contrib.rocks). |