Alternatives
Products that do what Emmtrix ONNX-to-C Code Generator for Edge AI Deployment does
Hi HN, we wanted to share our open source ONNX-to-C code generator. It translates ONNX models into C code for deployment on embedded systems. We developed it for use with emmtrix Code Vectorizer (https://www.emmtrix.com/tools/emmtrix-code-vectorizer) which optimizes the generated code for various embedded architectures. The ONNX-to-C code generator can however also be used standalone to generate plain C code. In contrast to many other tools, it makes deployment trivial since the generated code is fully standalone and no additional runtime is required.
- 1N5
2020 · nn-512.com
- 2
Trace LLM requests + costs with OpenTelemetry monitoring
Oct 2025
- 3
- 4
- 5
- 6ZA
Hey HN, We’re excited to announce Zant v0.1, an open-source TinyML SDK built in Zig, designed to optimize and deploy neural networks on resource-constrained devices. Unlike existing solutions, Zant focuses on performance, portability, and ease of integration, making it a strong alternative for anyone working on Edge AI and embedded ML. Why Zant? Most TinyML frameworks are either too high-level (requiring bloated runtimes) or too low-level (requiring extensive manual optimization). Zant bridges the gap by offering: - A lightweight but powerful code generation system to translate ML models…
2025 · github.com
- 7WU
Hey HN, We’re Volodymyr and Volodymyr—two developers from Ukraine building WhiteLightning. It’s a tool that turns large LLMs (Claude 4, Grok 4, GPT-4o via OpenRouter) into tiny ONNX text classifiers that run anywhere—even on drones at the edge. Why we built this: Many developers want custom models (spam filters, sentiment analysis, PII detection, moderation tools), but don’t want to deal with constant API calls or deploy heavy models in production. How it works: WhiteLightning uses LLMs to generate training data and distills it into KB-sized ONNX models you can run on any device and in any…
2025 · whitelightning.ai
- 8SP
I was recently playing with Apple's CoreML and had several painful observations on tooling. It's not enough for a long read but should be for an HN post. In short, you can take a simple BERT-like encoder model in PyTorch, convert it into an f32 CoreML checkpoint, and run it on CPU or GPU, but not NPU. Let's unpack this. Having a simple and extensible format to exchange common ANN architectures is a big issue for anyone who uses more than one framework or programming language to run the same model. ONNX is the closest we have to that standard, but it's hard to call anything Protobuf-related…
2024 · github.com
- 9IM
Hey guys, I made a VS Code extension, within which you can use the Mixtral 8x7B AI model for free. Mixtral 8x7B is a new AI model from the Mistral family, which outperforms GPT-3 in many benchmarks, a fact that I have personally confirmed in daily coding tasks, where Mistral 8x7B was the clear winner. You can use all the AI features, such as AI Lens with custom instructions and similar. I'm pretty sure some of features will be useful to you. I'd appreciate both, positive and negative feedback!
2023 · marketplace.visualstudio.com
- 10EY
Jun 2026 · github.com
- 11SG
Hi HN, I built NOMA (Neural-Oriented Machine Architecture), a systems language where reverse-mode autodiff is a compiler pass (lowered to LLVM IR). My goal is to treat model parameters as explicit, growable memory buffers. Since NOMA compiles to standalone native binaries (no Python runtime), it allows using realloc on weights mid-training. This makes "self-growing" architectures a system primitive rather than a complex framework hack. I just pushed a reproducible benchmark (Self-Growing XOR) to validate the methodology: it compares NOMA against PyTorch and C++, specifically testing how…
Dec 2025 · github.com
- 12IB
For the last 6 months, I've been building ORUS Builder, an open-source AI code generator. My goal was to fix the biggest issue I have with tools like v0, Lovable, etc. – they generate broken, non-compiling code that needs hours of debugging. ORUS Builder is different. It uses a "Compiler-Integrity Generation" (CIG) protocol, a set of cognitive validation steps that run before the code is generated. The result is a 99.9% first-time compilation success rate in my tests. The workflow is simple: 1.Describe an app in a single prompt. 2.It generates a full-stack application…
Nov 2025
- 13LR
I just noticed it takes literally ~5 minutes to train millions parameters on slow CPU...but before you call Yudkowsky that "it's over", an important note: the main bottleneck is the corpus size, params are just 'cleverness' but given limited info it's powerless. Anyway, here is the project: https://github.com/bggb7781-collab/lrnnsmdds/tree/main couple of notes: 1. single C file, no dependencies. Below are literally all the "dependencies", not even custom header (copy paste from the top of the single c file): #define _POSIX_C_SOURCE 200809L #include #include…
Apr 2026 · raw.githubusercontent.com
- 14IB
Claw-Coder is an AI agent that runs locally on your laptop and has access to powerful tools instead of configuring claude or codex to use a local model just use claw-coder. Why was claw-coder created? Answer: To solve the problem of privacy and security. When you use an agent that is configured with a cloud model like codex, cursor, Claude etc. You are not just getting the agent but you are giving up your codebase to train an llm which is a bit concerning and this reduces trust in the technology called AI but now another problem comes in performance when you switch to a local model that is…
May 2026
- 15IC
I spent the past week implementing a 1 Layer Neural Net and training it on MNIST within the visual scripting language provided by scratch.mit.edu. It was tedious, but ultimately not too difficult. The code runs incredibly slowly, so much so that 64 samples of MNIST takes 5+ hours to train on my machine. There were a lot of little mini challenges that were fun to overcome (implementing softmax was very tricky). If you're interested, I encourage you to try and improve on it! More details in the linked blog post.
2024 · bell-boy.github.io
- 16BC
We are a small group of undergrads interested in building human in the loop coding agents. We dream of a world where building complex agent workflows feels as simple and creative as playing with legos. When we were building stuff we needed a tool that made it easy to try out different code embedding models so that we could see which ones worked best in different scenarios and understand their strengths and weaknesses. So to speed that process up we made PurpleSearch an 'instant' search engine for your local codebases. This tool lets you quickly deploy any open source embedding model on…
2025
- 17OS
I’ve been working on Code2Docs, an open-source CLI tool that helps developers automatically generate inline documentation (docstrings + comments) for Python code using AI. It’s built to solve a common problem I’ve faced (and seen often in teams): We code by "vibe" — fast iterations, minimal docs, and then forget what the logic was months later. Code2Docs helps bridge that gap by documenting as you go — without breaking your flow. Right now it supports function-level documentation. Planned features include: - README.md generation for projects - API endpoint docs - Database schema…
2025 · code2docs-open-source.netlify.app
- 18AH
hey guys, i wanted to show one of my side projects. The idea is a coding harness (independent of models) natively designed for C/C++ developer workflows. I'm a C++ dev and do not find claude code work well with C++ toolchain like gdb and perf. The current version has integrations for gdb, clang-tidy, cppcheck, sanitizers, perf, benchmarking, compile DB navigation, Godbolt, symbolization, binary inspection, and decompilation. It supports Anthropic, OpenAI, Gemini, and self-hosted models. There are editor workflows for VS Code, CLion, emacs, neovim, and cursor.
Jul 2026 · byteask.ai
- 19DG
Hi, I’m Chris and my partners and I are building Devplan, an AI product development tool that helps teams go from idea to working code faster. What Devplan does: - Creates deep contextual understanding from Github and the web with our open source context engine: https://github.com/devplaninc/contextify - Generates right-sized PRDs, user stories, and tech design based on company context - Gives a ballpark effort and complexity estimate for every user story - Breaks down requirements into structured coding prompts for tools like Claude Code, Cursor, Windsurf, or JetBrains…
2025 · devplan.com
- 20CO
So I've been building ClawMem, an open-source context engine that gives AI coding agents persistent memory across sessions. It works with Claude Code (hooks + MCP) and OpenClaw (ContextEngine plugin + REST API), and both can share the same SQLite vault, so your CLI agent and your voice/chat agent build on the same memory without syncing anything. The retrieval architecture is a Frankenstein, which is pretty much always my process. I pulled the best parts from recent projects and research and stitched them together: [QMD](https://github.com/tobi/qmd) for the…
Mar 2026 · github.com
- 21CT
2015 · github.com
- 22IB
Claw-Coder is an AI agent that runs locally on your laptop and has access to powerful tools instead of configuring claude or codex to use a local model just use claw-coder. Why was claw-coder created? Answer: To solve the problem of privacy and security. When you use an agent that is configured with a cloud model like codex, cursor, Claude etc. You are not just getting the agent but you are giving up your codebase to train an llm which is a bit concerning and this reduces trust in the technology called AI but now another problem comes in performance when you switch to a local model that is…
May 2026
- 23SA
2025 · usestrix.com
- 24PR
Hi HN, While building RAG agents, I noticed a lot of token budget was wasted on formatting overhead (HTML tags, JSON structure, whitespace). Existing solutions felt too heavy (often requiring torch/transformers), so I wrote this lightweight, zero-dependency library to solve it. It includes strategies for context packing, PII redaction, and tool output compression. Benchmarks show it can save ~15% of tokens with negligible latency overhead (<0.5ms). Happy to answer any questions!
Dec 2025 · github.com
Ranked by how close each launch is in meaning, then by votes. Refine with a description →