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.
End-to-end Generative Optimization for AI Agents
| Date | Stars |
|---|---|
| 2026-07-31 | 750 |
| 2026-08-06 | 752 |
Today
+2 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/microsoft/Trace/blob/main/docs/images/Trace_Primary_C.png" alt="drawing" width="500"/>
</p>
# End-to-end Generative Optimization for AI Agents
[](https://arxiv.org/abs/2406.16218)
**[This repository accomponanies the [Trace paper](https://arxiv.org/abs/2406.16218). It is a fully functional implementation of the platform for generative optimization described in the paper, and contains code necessary to reproduce the experiments reported. This library was implemented and maintained by the authors while they were at Microsoft.]**
Trace is a new AutoDiff-like tool for training AI systems end-to-end with general feedback (like numerical rewards or
losses, natural language text, compiler errors, etc.). Trace generalizes the back-propagation algorithm by capturing and
propagating an AI system's execution trace. Trace is implemented as a PyTorch-like Python library. Users write Python
code directly and can use Trace primitives to optimize certain parts, just like training neural networks!
[Paper](https://arxiv.org/abs/2406.16218) | [Project website](https://microsoft.github.io/Trace/) | [Documentation](https://microsoft.github.io/Trace/intro.html) | [Blogpost](https://www.microsoft.com/en-us/research/blog/tracing-the-path-to-self-adapting-ai-agents/) | [Discord channel](https://discord.gg/9CcNqXAnPC) | [Mailing list](https://groups.google.com/g/trace-opt)
<p >
<img src="https://github.com/microsoft/Trace/blob/main/docs/images/platform2.png" alt="drawing" width="100%"/>
</p>
## Setup
Simply run
pip install trace-opt
Or for development, clone the repo and run the following.
pip install -e .
The library requires Python >= 3.9. By default (starting with v0.1.3.5), we use [LiteLLM](https://github.com/BerriAI/litellm) as the backend of LLMs. For backward compatibility, we provide backend-support with [AutoGen](https://github.com/microsoft/autogen); when installing, users can add `[autogen]` tag to install a compatible AutoGen version (e.g., `pip install trace-opt[autogen]`). You may require [Git Large File Storage](https://git-lfs.com/) if
git is unable to clone the repository.
**For questions or reporting bugs, please use Github Issues or post on our [Discord channel](https://discord.gg/9CcNqXAnPC). We actively check these channels.**
## Updates
- **2025.2.7** Trace was featured in the [G-Research NeurIPS highlight](https://www.gresearch.com/news/neurips-paper-reviews-2024-8/) by the Science Director Hugh Salimbeni.
- **2024.12.10** Trace was demoed in person at NeurIPS 2024 Expo.
- **2024.11.05** Ching-An Cheng gave a talk at UW Robotics Colloquium on Trace: [video](https://www.youtube.com/watch?v=T2g1Vo3u_9g).
- **2024.10.21** New [paper](https://arxiv.org/abs/2410.15625) by Nvidia, Stanford, Visa, & Intel applies Trace to
optimize for mapper code of parallel programming (for scientific computing and matrix multiplication). Trace (OptoPrime) learns code achieving 1.3X speed up under 10
minutes, compared to the code optimized by a system engineer expert.
- **2024.9.30** Ching-An Cheng gave a talk to the AutoGen community: [link](https://twitter.com/qingyun_wu/status/1840093778595721727).
- **2024.9.25** [Trace Paper](https://arxiv.org/abs/2406.16218) is accepted to NeurIPS 2024.
- **2024.9.14** TextGrad is available as an optimizer in Trace.
- **2024.8.18** Allen Nie gave a talk to [Pasteur Labs](https://pasteurlabs.ai/) & Institute for Simulation Intelligence.
## QuickStart
Trace has two primitives: `node` and `bundle`. `node` is a primitive to define a node in the computation graph. `bundle`
is a primitive to define a function that can bExcerpt of 22,493 characters
Read on GitHub
223
181
12
11
Microsoft Open Source · Microsoft · United States
5
@voxel51
3
2
Eduardo Salinas · Microsoft · United States
2
1
1
Sina Semnani · @Liquid4All @stanfordnlp @stanford-oval · United States
1
Jack Gerrits · United States
1
1
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:314744647453922a, topic:agents, topic:agentic-workflow, desc:ai agents
matched fp:314744647453922a, topic:large-language-models, topic:llm