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.
A generalized information-seeking agent system with Large Language Models (LLMs).
| Date | Stars |
|---|---|
| 2026-07-31 | 1203 |
| 2026-08-06 | 1203 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
<p align="left">
English ｜ <a href="README_ZH.md">中文</a> | <a href="README_JA.md">日本語</a>
</p>
<br><br>
<p align="center">
<img src="blob/logo.png" width="400"/>
<p>
<br>
<p align="center">
📚 <a href="https://huggingface.co/datasets/kwaikeg/KAgentInstruct">Dataset</a> | 📚 <a href="https://huggingface.co/datasets/kwaikeg/KAgentBench">Benchmark</a> | 🤗 <a href="https://huggingface.co/collections/kwaikeg/kagentlms-6551e685b5ec9f9a077d42ef">Models</a> | 📑 <a href="http://arxiv.org/abs/2312.04889">Paper</a>
<br>
KwaiAgents is a series of Agent-related works open-sourced by the [KwaiKEG](https://github.com/KwaiKEG) from [Kuaishou Technology](https://www.kuaishou.com/en). The open-sourced content includes:
1. **KAgentSys-Lite**: a lite version of the KAgentSys in the paper. While retaining some of the original system's functionality, KAgentSys-Lite has certain differences and limitations when compared to its full-featured counterpart, such as: (1) a more limited set of tools; (2) a lack of memory mechanisms; (3) slightly reduced performance capabilities; and (4) a different codebase, as it evolves from open-source projects like BabyAGI and Auto-GPT. Despite these modifications, KAgentSys-Lite still delivers comparable performance among numerous open-source Agent systems available.
2. **KAgentLMs**: a series of large language models with agent capabilities such as planning, reflection, and tool-use, acquired through the Meta-agent tuning proposed in the paper.
3. **KAgentInstruct**: over 200k Agent-related instructions finetuning data (partially human-edited) proposed in the paper.
4. **KAgentBench**: over 3,000 human-edited, automated evaluation data for testing Agent capabilities, with evaluation dimensions including planning, tool-use, reflection, concluding, and profiling.
<br>
<table align='center'>
<tr>
<td align='center'><b>Type</b></td>
<td align='center'><b>Models</b></td>
<td align='center'><b>Training Data</b></td>
<td align='center'><b>Benchmark Data</b></td>
</tr>
<tr>
<td>Qwen</td>
<td>
<a href="https://huggingface.co/kwaikeg/kagentlms_qwen_7b_mat">Qwen-7B-MAT</a> <br>
<a href="https://huggingface.co/kwaikeg/kagentlms_qwen_14b_mat">Qwen-14B-MAT</a> <br>
<a href="https://huggingface.co/kwaikeg/kagentlms_qwen_7b_mat_gguf">Qwen-7B-MAT-cpp</a> <br>
<a href="https://huggingface.co/kwaikeg/kagentlms_qwen1.5_14b_mat">Qwen1.5-14B-MAT</a>
</td>
<td align="center" rowspan="2"><a href="https://huggingface.co/datasets/kwaikeg/KAgentInstruct">KAgentInstruct</a></td>
<td align="center" rowspan="2"><a href="https://huggingface.co/datasets/kwaikeg/KAgentBench">KAgentBench</a></td>
</tr>
<tr>
<td>Baichuan</td>
<td><a href="https://huggingface.co/kwaikeg/kagentlms_baichuan2_13b_mat">Baichuan2-13B-MAT</a></td>
</tr>
</table>
<br>
<br>
<p align="center">
<img src="blob/example.gif"/>
<p>
<br>
<p align="center">
<img src="blob/overview.png"/>
<p>
## News
* 2024.4.19 - Qwen1.5-14B-MAT model [[link]](https://huggingface.co/kwaikeg/kagentlms_qwen1.5_14b_mat) released.
* 2024.4.9 - Benchmark results have been refreshed.
* 2024.1.29 - Qwen-14B-MAT model [[link]](https://huggingface.co/kwaikeg/kagentlms_qwen_14b_mat) released.
* 2023.1.5 - Training data [[link]](https://huggingface.co/datasets/kwaikeg/KAgentInstruct) released.
* 2023.12.27 - 🔥🔥🔥 KwaiAgents have been reported on many sites. [[机器之心]](https://mp.weixin.qq.com/s/QhZIFL1GHH90z98gnk194g) [[Medium]](https://medium.com/@myscarletpan/can-7b-models-now-master-ai-agents-a-look-at-kwais-recent-llm-open-source-release-8b9e84647412) [[InfoQ]](https://www.infoq.cn/article/xHGJwG3b8hXSdaP4m6r0), etc.
* 2023.12.13 - The benchmark and evaluation code [[link]](https://huggingface.co/datasets/kwaikeg/KAgentBench) released.
* 2023.12.08 - Technical report [[link]](https://arxiv.org/abs/2312.04889) releExcerpt of 12,667 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:57b23f00f4ccf226, topic:large-language-models, topic:gpt
matched fp:57b23f00f4ccf226, topic:autonomous-agents, topic:autogpt
matched fp:57b23f00f4ccf226, topic:chatgpt
