Axiom
C++ tensor library with NumPy API and Metal GPU support
Details
- External ID
- 46859292
- Source
- HN
- Company
- —
- Product
- —
- Website domain
- —
- Launched
- Feb. 2, 2026
- Cohort
- —
- Upvotes
- 5
- Upvotes percentile
- 0.10512129380053908
- Tags
- —
- Fetched at
- Sept. 7, 2026, 9:26 p.m.
- Updated at
- Sept. 7, 2026, 9:26 p.m.
Description
I've been building a C++ tensor library that tries to bring the ergonomics of NumPy/PyTorch to native code. The main goals were: - Familiar API (operator overloading, method chaining, same function names) - Actual GPU acceleration via Metal (not just matmul, but all ops) - Cross-platform with SIMD on x86/ARM/RISC-V via xsimd - einops-style rearrange/reduce patternsIt started because I wanted NumPy's API but needed to deploy on edge devices without Python. Ended up going deeper than expected (28k LOC+) into BLAS backends, memory views, and GPU kernels.Some things I'm genuinely unsure about and would love feedback on: - Does Axiom actually seem useful? - What features might make you use it?GitHub: https://github.com/frikallo/axiomHappy to answer questions about the implementation.
Enrichment
- Theme
- lightweight and on-device AI runtimes
- Vertical
- Horizontal
- Function
- Model & infra
- Audience
- Developer
- AI stance
- Not AI
- Project type
- Hobby / open-source project
- Normalized one-liner
- c++ tensor library with gpu support
- Manually corrected
- False
Could you build this?
No Developing a custom C++ tensor library with Metal GPU acceleration requires deep native systems programming, memory management, and GPU shader kernel optimization.
What it would actually take: Requires modern C++ (C++20), Metal Shading Language (MSL), Objective-C++ bridges, and BLAS/LAPACK backends for CPU fallbacks. The hard parts include writing optimized GPU compute kernels for arbitrary tensor operations, handling strided memory layouts, broadcasting rules, autograd/computation graphs, and device-to-host memory synchronization. Demands specialized knowledge in high-performance computing, Apple Metal API, and numerical computation algorithms.
Discussion
No comments on this launch.
Competitors
Other products that read as similar to this one — 108 launches clear the similarity bar, closest 8 shown.
Attention rank: #102 of 109 (itself plus its competitors, highest first — normalized so YC and Product Hunt are compared fairly).
Launched 96 days after the earliest competitor.
- RunMat · hn · 2025-12-02 · 21 upvotes · similarity 0.53
- Axiom · hn · 2026-02-18 · 20 upvotes · similarity 0.50
- SymDerive · hn · 2026-02-01 · 26 upvotes · similarity 0.46
- SyNumpy · hn · 2026-04-02 · 22 upvotes · similarity 0.46
- Tensor Spy: inspect NumPy and PyTorch tensors in the browser, no upload · hn · 2026-03-02 · 22 upvotes · similarity 0.45
- Xpandas · hn · 2026-03-02 · 6 upvotes · similarity 0.43
- PyMOL-RS · hn · 2026-02-26 · 5 upvotes · similarity 0.42
- High speed graphics rendering research with tinygrad/tinyJIT · hn · 2026-01-22 · 31 upvotes · similarity 0.41
Other launches for this product
- No other launches for this product.
Same idea, different domain
Nobody's really built a model & infra tool for Fintech yet.