Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Chain together LLMs for reasoning & orchestrate multiple large models for accomplishing complex tasks
| Date | Stars |
|---|---|
| 2026-07-24 | 610 |
| 2026-07-25 | 610 |
| 2026-07-28 | 610 |
| 2026-07-30 | 610 |
| 2026-08-06 | 610 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
<p>
<img src="https://github.com/jina-ai/agentchain/blob/main/agentchain-logo.png?raw=true" alt="AgentChain logo" width="250px"></a>
</p>
AgentChain uses Large Language Models (LLMs) for planning and orchestrating multiple Agents or Large Models (LMs) for accomplishing sophisticated tasks. AgentChain is fully multimodal: it accepts text, image, audio, tabular data as input and output.
- **🧠 LLMs as the brain:** AgentChain leverages state-of-the-art Large Language Models to provide users with the ability to plan and make decisions based on natural language inputs. This feature makes AgentChain a versatile tool for a wide range of applications, such as task execution give natural language instructions, data understanding, and data generation.
- **🌟 Fully Multimodal IO:** AgentChain is fully multimodal, accepting input and output from various modalities, such as text, image, audio, or video (coming soon). This feature makes AgentChain a versatile tool for a wide range of applications, such as computer vision, speech recognition, and transitioning from one modality to another.
- **🤝 Orchestrate Versatile Agents:** AgentChain can orchestrate multiple agents to perform complex tasks. Using composability and hierarchical structuring of tools AgentChain can choose intelligently which tools to use and when for a certain task. This feature makes AgentChain a powerful tool for projects that require complex combination of tools.
- **🔧 Customizable for Ad-hoc Needs:** AgentChain can be customized to fit specific project requirements, making it a versatile tool for a wide range of applications. Specific requirements can be met by enhancing capabilities with new agents (and distributed architecture coming soon).
# Get started
1. Install requirements: `pip install -r requirements.txt`
2. Download model checkpoints: `bash download.sh`
3. Depending on the agents you need in-place, make sure to export environment variables
```shell
OPENAI_API_KEY={YOUR_OPENAI_API_KEY} # mandatory since the LLM is central in this application
SERPAPI_API_KEY={YOUR_SERPAPI_API_KEY} # make sure to include a serp API key in case you need the agent to be able to search the web
# These environment variables are needed in case you want the agent to be able to make phone calls
AWS_ACCESS_KEY_ID={YOUR_AWS_ACCESS_KEY_ID}
AWS_SECRET_ACCESS_KEY={YOUR_AWS_SECRET_ACCESS_KEY}
TWILIO_ACCOUNT_SID={YOUR_TWILIO_ACCOUNT_SID}
TWILIO_AUTH_TOKEN={YOUR_TWILIO_AUTH_TOKEN}
AWS_S3_BUCKET_NAME={YOUR_AWS_S3_BUCKET_NAME} # make sure to create an S3 bucket with public access
```
4. Install `ffmpeg` library (needed for whisper): `sudo apt update && sudo apt install ffmpeg` (Ubuntu command)
5. Run the main script: `python main.py`
## System requirements
As of [this commit](https://github.com/jina-ai/agentchain/commit/da588a728c390fb538fd361d4f41dd50aa193751), it is needed to have at least 29 GB of GPU memory to run the AgentChain.
However, make sure to assign GPU devices correctly in `main.py`.
You can comment out some tools and models to reduce the GPU memory footprint (but for less capabilities).
# Demo
AgentChain demo 1: transcribing audio and visualizing the result as an image. A video of the AgentChain interface shows an uploaded audio and the resulting generated image, which is a representation of the audio content.
https://user-images.githubusercontent.com/4182659/225347932-87298e6c-58d0-4a29-892f-1398b1406c15.mp4
---
AgentChain demo 2: asking questions about an image. A video of the AgentChain interface shows an image and a question being asked about it, with the resulting answer displayed below.
https://user-images.githubusercontent.com/4182659/225348027-ed30f9d5-d05b-405a-9651-c08f4976cf83.mp4
---
AgentChain demo 3: question-answering on tabular data and making a phone call to report the results. A video of the AgentChain interface shows a table of data with a question being asked and the resulting answer displayed, followed by a phone call being made using the `Excerpt of 12,887 characters
Read on GitHub
AlaeddineAbdessalem
52
Han Xiao · @elastic · United States
26
Aziz Belaweid · Aleph Alpha · Germany
10
4
3
2
Alex Cureton-Griffiths · @jina-ai · Germany
2
Zecheng Tang · Soochow University · China
2
Bojie Li · @19PINE-AI @ustclug
1
1
1
United States
1
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:95199133c5aa6db8, topic:whisper, readme:speech recognition
matched fp:95199133c5aa6db8, topic:llm
matched fp:95199133c5aa6db8, topic:stable-diffusion
matched fp:95199133c5aa6db8, topic:multimodal, readme:multimodal