Devpost
Participate in our public hackathons
Devpost for Teams
Access your company's private hackathons
Grow your developer ecosystem and promote your platform
Drive innovation, collaboration, and retention within your organization
By use case
Blog
Insights into hackathon planning and participation
Customer stories
Inspiration from peers and other industry leaders
Planning guides
Best practices for planning online and in-person hackathons
Webinars & events
Upcoming events and on-demand recordings
Help desk
Common questions and support documentation
One command quantizes MiniLM to INT8 and proves a 2.45x latency speedup on native Arm64—with reproducible CI and embedding-fidelity guardrails.
Capture moments from Reels, YouTube Shorts, or TikTok and turn them into interactive language lessons with on-device transcription, translation, subtitles, and tap-to-learn vocabulary.
A secure, fully local legal document parsing assistant optimized to run efficiently on Arm64 architecture, providing complete data privacy and zero cloud API costs for law firms.
Autonomous ReAct deep-research agent running on a $0 free Arm CPU server. Plans, searches, runs Python, & synthesizes cited reports via Arm KleidiAI microkernels with $0 GPU spend.
Generate less. Route locally. Audit everything.
Five AI models on one mid-range phone. Voice chat, vision, OCR translation, image generation - 100% on-device, zero cloud. Custom fine-tuned & self-quantized for Arm Cortex-A78.
An Arm-optimized TTS model, small and fast enough to run on DGX Spark and Apple Silicon Arm CPU - no GPU, no internet, no cloud API. 4.8x smaller, 8.6x faster than Kokoro. Demo narrated by it.
5.8x faster local retrieval on Apple M4 with 74.7% less corpus memory—and an automatic Recall@10 brake pedal.
Autonomous LLM tuning on AWS Graviton: a deterministic autotuner + a Claude analyst reading Arm Performix counters. 2.1x decode, quality-guarded, replayable from a saved recipe.
Evidence-driven local AI routing that uses a 1.5B fast path and a measured 7B quality fallback on Arm64.
A local RTL design agent on an 8GB ARM Mac was used to benchmark KleidiAI and quantization. Finding: Q4_0 beats the default Q4_K_M by 43% because KleidiAI has no kernel for Q4_K_M.
FTIR spectral agent retrieval kernel optimized for Arm64 — real cross-architecture benchmark, reproducible on GitHub Actions ARM runners.
A lightweight AI runtime for ARM Cortex-M that uses dynamic memory allocation and reusable memory pools to reduce SRAM usage and enable efficient on-device AI inference.
Efficient NLP engine for the Arm ecosystem transforming psychological text analysis through lightweight, explainable AI. Atlas Jiwa delivers privacy-focused insights with edge-friendly inference.
Fail-closed proof and rollback gates for Arm64 cloud inference performance claims.
Evidence-first AI agent with a 57.36% faster deterministic gate on Google Axion.
Armsmith finds why your AI repo is slow on Arm and drafts the fix PR — 7.4× measured on Neoverse-N2, and it deletes the fixes it can't prove.
Naive INT8 quantization is 100x SLOWER on Arm without the right kernel. We show the trap and the real fix, benchmarked live on a Raspberry Pi 5.
ReachGuard: An Arm - optimized AI vulnerability triage platform that prioritizes exploitable, reachable CVEs and drafts validated fixes - without your code leaving your infrastructure.
Fast and private AI that runs directly on your device.
ARMONIC-An autonomous agent that reads Arm64 silicon telemetry and rewrites your Python AI code for Neoverse — validated, git-isolated, zero human touch.
AI-powered edge safety system that detects workplace hazards, assesses risk, and triggers real-time emergency responses using computer vision and sensor fusion.
First TFLite-Micro + CMSIS-NN port to Infineon's PSOC Control C3 (Arm Cortex-M33): MCU bearing-fault detection optimized into a 2.2× faster, 3× smaller pipeline with control + inference on one chip.
100kb fullstack chatbot with multimodal, local storage for chat history, branches, web search mcp, cloudflare docs mcp, voice output, and local searches, with links.
193 – 216 of 333
