Source: https://seerepo.com/compare/NVIDIA/TensorRT-LLM/vs/Unity-Technologies/ml-agents
Markdown source: https://seerepo.com/compare/NVIDIA/TensorRT-LLM/vs/Unity-Technologies/ml-agents.md
Description: TensorRT-LLM and ml-agents share 3 technologies: h5py, torch, and pillow. Both are written in Python.

# TensorRT-LLM vs ml-agents

TensorRT-LLM and ml-agents share 3 technologies: h5py, torch, and pillow. Both are written in Python.

- [NVIDIA/TensorRT-LLM](https://seerepo.com/r/NVIDIA/TensorRT-LLM): TensorRT LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and supports state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorRT LLM also contains components to create Python and C++ runtimes that orchestrate the inference execution in a performant way.
- [Unity-Technologies/ml-agents](https://seerepo.com/r/Unity-Technologies/ml-agents): The Unity Machine Learning Agents Toolkit (ML-Agents) is an open-source project that enables games and simulations to serve as environments for training intelligent agents using deep reinforcement learning and imitation learning.

## What they share and what sets them apart

- In common: h5py, torch, pillow
- Only in TensorRT-LLM: FastAPI, blobfile, pyzmq, OpenAI, anyio, uvicorn, starlette, Rich, matplotlib, Plotly, accelerate, apache-tvm-ffi, cuda-python, flash-linear-attention, flashinfer-python, NVIDIA, nvidia-cudnn-frontend, openai-codex, openai-harmony, optimum, quack-kernels, rouge, rouge-score, sentencepiece, tiktoken, torch-c-dlpack-ext, torchao, triton, transformers, diffusers, einops, safetensors, torchvision, datasets, flash-attn, xgrammar, librosa, MCP, mistral-common, partial-json-parser, tritonclient, evaluate, llguidance, lm-eval, peft, jsonlines, jinja2, mako, Pydantic, msgspec, jsonschema, opentelemetry-api, opentelemetry-semantic-conventions-ai, psutil, prometheus-client, boto3, OpenTelemetry, opentelemetry-sdk, prometheus-fastapi-instrumentator
- Only in ml-agents: gymnasium

## Side by side

| | TensorRT-LLM | ml-agents |
|---|---|---|
| Size | 2,884,778 lines written, 3,120 code files | 81,989 lines written, 300 code files |
| Who writes it | 1.7% of its commits signed by AI. With Claude Code, CodeRabbit, GitHub Copilot, and Cursor | 0.1% of its commits signed by AI. With Claude Code |
| Activity | Last push November 8, 2026, 10,997 commits, 15,038 stars | Last push October 30, 2026, 3,177 commits, 19,822 stars |
| Tests | 2,703 test files. 58.6% of its code files have a test that imports them | 160 test files. 55.3% of its code files have a test that imports them |

- Size: Lines written by people and agents, without generated ones; code files, without tests.
- Who writes it: A commit counts as AI's when it carries its signature: a Co-Authored-By line, its author name or the merge of its branch.
- Activity: From GitHub and its history, on the day SeeRepo read it.
- Tests: The files that test the code, and the share of code files a test imports.

## Frequently asked questions

### Which is bigger, TensorRT-LLM or ml-agents?

TensorRT-LLM, with 2,884,778 lines written; ml-agents has 81,989.

The proof: [NVIDIA/TensorRT-LLM's code at commit b433473](https://github.com/NVIDIA/TensorRT-LLM/tree/b433473ba0d0d49764f4d2fb3d45c82716b946dc)

### Which has more GitHub stars, TensorRT-LLM or ml-agents?

ml-agents, with 19,822 stars; TensorRT-LLM has 15,038.

The proof: [Unity-Technologies/ml-agents on GitHub](https://github.com/Unity-Technologies/ml-agents)

### Which has more tests, TensorRT-LLM or ml-agents?

TensorRT-LLM, with 2,703 test files; ml-agents has 160.

The proof: [NVIDIA/TensorRT-LLM's code at commit b433473](https://github.com/NVIDIA/TensorRT-LLM/tree/b433473ba0d0d49764f4d2fb3d45c82716b946dc)

### Which was updated more recently, TensorRT-LLM or ml-agents?

TensorRT-LLM: its last push was on November 8, 2026, and ml-agents's on October 30, 2026.

The proof: [NVIDIA/TensorRT-LLM's commits on GitHub](https://github.com/NVIDIA/TensorRT-LLM/commits)

### Which has more commits signed by AI, TensorRT-LLM or ml-agents?

TensorRT-LLM: an AI signed 1.7% of its commits, with Claude Code, CodeRabbit, GitHub Copilot, and Cursor; in ml-agents, 0.1%.

The proof: [the commits each tool signed in NVIDIA/TensorRT-LLM](https://seerepo.com/r/NVIDIA/TensorRT-LLM/ai)

## Sources

- NVIDIA/TensorRT-LLM: Read on November 8, 2026, at commit b433473 (https://github.com/NVIDIA/TensorRT-LLM/tree/b433473ba0d0d49764f4d2fb3d45c82716b946dc)
- Unity-Technologies/ml-agents: Read on November 5, 2026, at commit 4649106 (https://github.com/Unity-Technologies/ml-agents/tree/4649106d09088a6135397e0f8ed7015ec600834a)

## What is your repo built with?

Any public repo, with no account: https://seerepo.com/r/owner/repo/built, with the owner and name it has on GitHub.