Overview Diffrax provides numerical solvers for ordinary, stochastic and controlled differential equations in JAX. All equation types go through one interface, `diffeqsolve`. It includes explicit solvers such as Tsit5, Dopri5 and Dopri8, plus symplectic and implicit solvers, and offers several adjoint methods for backpropagation.
Who it is for: Researchers and engineers solving differential equations in JAX
Strengths Single API covers ODEs, SDEs and CDEs, including neural differential equations Autodifferentiable and vmappable, with multiple adjoint methods for backpropagation Supports PyTrees as state and dense solutions Installs with pip; hosted documentation site Weaknesses Requires JAX and Python 3.10+; not usable from other array frameworks Aimed at scientific computing, not LLM or generative model workflows No benchmarks against other solver libraries in the README What it needs GPU optional Needs JAX, Python 3.10+ What changed From the release notes. No flag means the note does not say so, not that the upgrade is safe.
Also in ML frameworks and libraries Rank Project Score 1 transformers Model-definition library for pretrained text, vision, audio and multimodal models 169.3k stars Apache-2.094 out of 100 score 2 ultralytics Python library and CLI for training and running YOLO vision models 63.5k stars AGPL-3.094 out of 100 score 3 pytorch-image-models PyTorch library of image models, pretrained weights and training scripts 37.3k stars Apache-2.094 out of 100 score # 4pytorch Python tensor library with GPU support and tape-based autograd 105.8k stars custom license93 out of 100 score # 5supervision Python toolkit for loading, annotating and counting computer vision detections
Live demo ↗
(opens in a new tab) 51.7k stars MIT92 out of 100 score
How to choose Pick the framework your target models and papers already use. Check hardware support (CUDA, ROCm, Apple Silicon, TPU) for your machines. Look at release cadence; a framework that stalls strands your code. Health
Releases 2 in the last 12 monthsLast one 273 days ago
Top contributor 50% of commits10 of 20 in the last 12 months
Security advisories NoneOn GitHub, in the last 12 months
OpenSSF Scorecard Not checked Read from GitHub, deps.dev and OpenSSF on 18 Nov 2026. Bots and coding-agent accounts are left out of the commit counts. Not part of the score: how we check .
License in plain words Apache-2.0 Permissive
Use it at work Yes
Change it and rebrand it Yes
Sell it or host it for others Yes Your part: Keep the notices and mark the files you change. It also grants you the contributors’ patent rights.
A plain summary, not legal advice. Read the license on GitHub ↗ (opens in a new tab)
Where to run it Referral links: if you sign up through one, we get a commission. They never change a rank.
Ask your AI assistant The rankings as an MCP server for Claude, Cursor, ChatGPT and any MCP client. Free, no key, read-only.
Setup for other apps → Claude Code claude mcp add archestack -- npx -y @archestack/mcpCopy
Connector URL https://mcp.archestack.com/mcpCopy
Then ask: Compare diffrax with its top alternatives on Archestack
Share this rank #206 of 242 in ML frameworks and libraries on Archestack, as of 18 Nov 2026.
Show it in your README or on your site The badge below goes in a README; a card with the rank, score and signals goes on a site or blog. Both update twice a day.
Copy for README Copy for your site
Show code README (Markdown)
[](https://archestack.com/best-of-ai/projects/diffrax/)Site or blog (HTML)
<iframe src="https://archestack.com/embed/best-of-ai/diffrax/" title="diffrax on Archestack" width="400" height="270" style="border:0;max-width:100%" loading="lazy"></iframe>How badges work Preview the card
Best of Open-Source AI on GitHub Each review comes from the project's README and facts we check on GitHub. The fix form opens with diffrax filled in.