Awesome/awesome-ai-agents
1
0
Fork 0
mirror of https://github.com/e2b-dev/awesome-ai-agents.git synced 2026-02-20 02:15:11 +00:00
Code Issues Packages Projects Releases Wiki Activity

commit

Browse Source
This commit is contained in:
tizkovatereza
2023-06-20 15:41:11 -07:00
parent f1d0b0bb02
commit 78f7bb37c4
1 changed files with 138 additions and 17 deletions
Download Patch File Download Diff File Expand all files Collapse all files

155
README.md
View File

@@ -99,29 +99,96 @@ An AI agent specifically designed for research
## [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.
### How it works
- 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
- Leverages OpenAI's GPT-4, pinecone vector search, and LangChainAI framework
- Default model is OpenAI GPT3-turbo
- The system maintains a task list for managing and prioritizing tasks
- It autonomously creates new tasks based on completed results and reprioritizes the task list accordingly, showcasing the adaptability of AI-powered language models
###Links
- 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/)
- [Founder's twitter](https://twitter.com/yoheinakajima)
- [Twitter thread describing the system](https://twitter.com/yoheinakajima/status/1640934493489070080)
</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.
BabyCatAGI is a mod of BabyBeeAGI, which is a mod of OG BabyAGI
<details>
### How it works
- Just 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_completion
- “Mini-agent” as tool
- Search tool combines search, scrape, chunking, and extraction.
- Results combined to create summary_report
### How to use
- Fork this into a private Repl
- Add your OpenAI API Key (required) and SerpAPI Key (optional)
- Update the OBJECTIVE variable
- Press "Run" at the top.
### Links
- [Twitter](http://twitter.com/babyAGI)
- [GitHub](https://github.com/yoheinakajima/babyagi)
- Author: @yoheinakajima (Twitter)
</details>
## [BabyDeer]
## [BitBuilder](https://github.com/marketplace/document-guardian)
Raises pull requests against your repository.
<details>
</details>
### How it works
- Working with BitBuilder is just like working with a remote colleague. Please see our full documentation for more information.
Create an Issue
Approve the Implementation Plan
Review the Pull Request
Virtual interns for developers.
Task them with writing code, reviewing changes, addressing comments, answering questions, and more.
You gotta check our
@bitbuilder_ai
, it raises pull requests against your repository. In fact the backend is built with
@tiangolo
’s FastAPI so I can personally attest to its ability to create routers, endpoints, and wire it all together.
We’ve made more than a pretty demo.
@bitbuilder_ai
will create Pull Requests from Issues. And review your code.
### BitBuilder Junior
- BitBuilder Junior is an intern-level code generation tool that lives in your GitHub repository. It follows instructions to implement unamibigous code changes by changing multiple files, writing tests for generated code, and matching the style, framework, and libraries you're already using.
### Statistics
- 990+
REPOSITORIES
use BitBuilder, including private and organization repos
### Links
- [Slack](https://bitbuilder-ai.slack.com/join/shared_invite/zt-1tlrds3n4-rpmgIGM6XrB5W97005IA1Q#/shared-invite/email)
## [BitBuilder](BitBuilder)
<details>
</details>
## [Bloop](https://bloop.ai/)
@@ -139,6 +206,19 @@ BabyCatAGI is a mod of BabyBeeAGI, which is a mod of OG BabyAGI. BabyCatAGI is a
Communicative Agents for “Mind” Exploration of Large Scale Language Model Society
<details>
1) AI user agent: give instructions to the AI assistant with the goal of completing the task.
2) AI assistant agent: follow AI user’s instructions and respond with solutions to the task
### Links
- [Paper - CAMEL: Communicative Agents for “Mind”
Exploration of Large Scale Language Model Society](https://ghli.org/camel.pdf)
- [Colab demo](https://colab.research.google.com/drive/1AzP33O8rnMW__7ocWJhVBXjKziJXPtim?usp=sharing)
- [GitHub](https://github.com/camel-ai/camel)
- [Hugging face datasets](https://huggingface.co/camel-ai)
- [Slack](https://camel-kwr1314.slack.com/join/shared_invite/zt-1vy8u9lbo-ZQmhIAyWSEfSwLCl2r2eKA#/shared-invite/email)
- Authors: Guohao Li∗ Hasan Abed Al Kader Hammoud* Hani Itani* Dmitrii Khizbullin, Bernard Ghanem
</details>
@@ -197,6 +277,30 @@ A developer assistant able to make whole nodejs project with unlimited prompts
<details>
</details>
## [GPT Engineer](https://github.com/AntonOsika/gpt-engineer)
Specify your project, and the AI agent constructs the entire code base.
GPT Engineer is made to be easy to adapt, extend, and make your agent learn how you want your code to look. It generates an entire codebase based on a prompt.
<details>
Model: GPT 4
Specify what you want it to build, the AI asks for clarification, and then builds it.
### Features
- You can specify the "identity" of the AI agent by editing the files in the identity folder.
Editing the identity, and evolving the main_prompt, is currently how you make the agent remember things between projects.
Each step in steps.py will have its communication history with GPT4 stored in the logs folder, and can be rerun with scripts/rerun_edited_message_logs.py.
### Links
- Author: [Anton Osika](https://twitter.com/antonosika)
- [Twitter review by @Attack](https://twitter.com/Attack/status/1671165869064609792)
</details>
## [Grit](https://www.grit.io/)
@@ -210,12 +314,6 @@ A developer assistant able to make whole nodejs project with unlimited prompts
</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
@@ -260,6 +358,26 @@ Your personal AI writing assistant
- 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>
## [LocalGPT](https://github.com/PromtEngineer/localGPT)
Inspired by privateGPT
<details>
### How it works
- Most of the description on readme is inspired by the original privateGPT
- Model: Vicuna-7B
- Using InstructorEmbeddings
- Both Embeddings as well as LLM will run on GPU. It also has CPU support if you do not have a GPU
- Built with Langchain
### Features
- Ask questions to your documents without an internet connection, using the power of LLMs. 100% private, no data leaves your execution environment at any point. You can ingest documents and ask questions without an internet connection!
### Links
- [YouTube - LocalGPT: OFFLINE CHAT FOR YOUR FILES [Installation & Code Walkthrough]](https://www.youtube.com/watch?v=MlyoObdIHyo&ab_channel=PromptEngineering)
</details>
## [Minion AI](https://minion.ai/)
@@ -315,7 +433,7 @@ Your personal AI writing assistant
## [Teenage AGI](https://github.com/seanpixel/Teenage-AGI/blob/main/README.md#experiments)
Can recall infinite memory, THINKS before it speaks, and doesn't lose memory after being shutting down
<details>
### How it works
@@ -333,6 +451,7 @@ Your personal AI writing assistant
- Based on the thought from Step 3 and relevant memories from Step 2, AI generates an output
- AI stores the current query and its answer in its Pinecone vector database memory
### Links
- Created by [@sean_pixel](https://twitter.com/sean_pixel)
!
@@ -352,8 +471,6 @@ Westworld is a multi-agent simulation library, its goal to simulate and optimize
- 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)
@@ -393,6 +510,10 @@ Twitter: https://twitter.com/pj4533
# Companies building agents
## [Hex Magic](https://hex.tech/product/magic-ai/)
<details>
</details>
<br>