lightweight and on-device AI runtimes
Recent window: last 5.2 months
(2026-04-24 → 2026-09-28), compared with the prior
5.2 months.
horizontal · 264 members ·
Data as of 2026-09-30
These products provide compact models, distillation techniques, and optimized runtime engines designed to run AI locally on consumer hardware and edge devices. They are built for developers, hardware hackers, and embedded systems engineers seeking private, low-latency machine learning execution without expensive cloud GPUs. Unlike general cloud-hosted LLM APIs, this cluster focuses strictly on extreme memory efficiency and resource-constrained local inference.
Metrics
- Stage
- crowded
- Recent count
- 134
- Prior count
- 111
- Total count
- 264
- Momentum
- 20.72
- Attention
- 0.54
- Crowding
- 0.70
- Concentration
- 0.83
- Opportunity
- 0.33
Opportunity components
- Attention
- 0.54
- Low crowding
- 0.30
- Momentum (normalized)
- 0.30
- Low concentration
- 0.17
Source split
- github
- 10 (0.07)
- hn
- 91 (0.68)
- ph
- 33 (0.25)
- yc
- 0 (0.00)
Dominant source: hn · Divergence: 0.68
Members
|
Name
|
Source
|
Upvotes ▲
|
Launched
|
| go-binsync |
HN |
5 |
2026-08-27 |
| I built a local Elixir/Python pipeline to curate 14,000 RAW photos |
HN |
5 |
2026-04-20 |
| Micron: a high performance C++23 (re)implementation of Libc and the STL |
HN |
6 |
2026-06-05 |
| I generated a "stress test" of 200 rare defects from 7 real photos |
HN |
6 |
2026-02-12 |
| OpenEntropy |
HN |
6 |
2026-02-17 |
| Shoehorn, a library to quantize an LLM to fit your Mac's VRAM |
HN |
6 |
2026-08-14 |
| Build apps with 500 models locally. No tracking, no cloud, just code |
HN |
6 |
2025-12-21 |
| Trunchbull, run real models against any benchmark in your browser |
HN |
6 |
2026-08-12 |
| ChunkBack |
HN |
6 |
2025-11-19 |
| Codex builds a working NES Emulator in one hour |
HN |
6 |
2026-02-26 |
| OS Megakernel that match M5 Max Tok/w at 2x the Throughput on RTX 3090 |
HN |
6 |
2026-04-08 |
| Alcatraz |
HN |
6 |
2026-08-04 |
| Flint |
HN |
6 |
2026-04-16 |
| Witchcraft and Pickbrain |
HN |
6 |
2026-04-16 |
| ChonkLM |
HN |
6 |
2026-05-09 |
| Microterm runs Linux VM in any browser tab via WASM, RISCV64 emulation |
HN |
6 |
2026-02-22 |
| CodeDiff |
HN |
6 |
2026-09-29 |
| FASHN VTON v1.5 |
HN |
6 |
2026-01-28 |
| PrivateClaw |
HN |
6 |
2026-04-24 |
| Semantic Overlays |
HN |
6 |
2026-09-01 |
| Go-CoreML |
HN |
6 |
2026-01-14 |
| Breathe-Memory |
HN |
6 |
2026-03-26 |
| Vicinae |
HN |
6 |
2026-07-08 |
| Project AELLA |
HN |
6 |
2025-11-11 |
| Llmpm |
HN |
6 |
2026-03-09 |
| A beautiful and local-first PDF reader for studying dense things |
HN |
6 |
2026-06-06 |
| Model-agnostic cognitive architecture for LLMs |
HN |
6 |
2025-11-18 |
| Llama 3.2 3B and Keiro Research achieves 85% on SimpleQA |
HN |
6 |
2026-03-07 |
| Numax |
HN |
6 |
2026-06-16 |
| LLM Memory Storage that scales, easily integrates, and is smart |
HN |
6 |
2026-03-16 |
| Blink-Edit |
HN |
6 |
2026-01-27 |
| Omni |
HN |
6 |
2026-06-05 |
| Samosa Chat |
HN |
6 |
2026-07-15 |
| NanoEuler |
HN |
6 |
2026-06-19 |
| Inference API that adapts to your SLA and quality constraints |
HN |
6 |
2026-01-02 |
| Zroar |
HN |
6 |
2026-08-21 |
| Multi-agent autoresearch for ANE inference beats Apple's CoreML by 6× |
HN |
6 |
2026-03-31 |
| Makes local LLMs faster and more reliable by optimizing for your device |
HN |
6 |
2026-06-30 |
| Running BitNet b1.58 inside DRAM by breaking DDR4 timing rules |
HN |
6 |
2026-05-23 |
| Python running on the Super Nintendo (in-browser demo) |
HN |
7 |
2026-07-06 |
| Dbzero |
HN |
7 |
2025-12-20 |
| Docker Model Runner Integrates vLLM for High-Throughput Inference |
HN |
7 |
2025-11-20 |
| I made a Gemma 4 Mac app that names screenshots with local AI |
HN |
7 |
2026-05-31 |
| Selora |
HN |
7 |
2026-06-17 |
| Linear RNN/Reservoir hybrid generative model, one C file (no deps.) |
HN |
7 |
2026-04-09 |
| Micro-RLE ≤264-byte compression for UART/MCU logs, zero RAM growth |
HN |
7 |
2025-11-01 |
| CJIT, a single-binary C compiler that can self host |
HN |
7 |
2026-04-13 |
| Tsplat |
HN |
7 |
2026-04-14 |
| A Wasm to Go Translator |
HN |
7 |
2026-02-26 |
| I embedded 685M public texts in 32 minutes (on 8x A100, Rust, TensorRT) |
HN |
7 |
2026-06-04 |