MIDREAL

Blowing up

updated 63 minutes ago

Category: All Coding agents MCP AI video Local AI Developer tools Self-hosted Models Skills

Sort: Velocity Stars gained, 7d Stars gained, 24h HN points

More filters

Language: All C C++ Cuda Go JavaScript Kotlin Python Rust Swift TypeScript

Topic: All ai ai-agents apple-silicon consumer-gpu deepseek gguf linux llama-cpp llm llm-inference local-ai local-first local-llm machine-learning macos mcp mlx ollama open-source openai openai-api python pytorch quantization qwen self-hosted speculative-decoding speech-to-text vllm windows

# Project Verdict Hype Reality Gap Stars gained, 7d Stars gainedStars gained over the window named in the column header. 24h is the change since our reading from at least 24 hours ago, 7d the change since our reading from at least 7 days ago. Blowing up and Hot on Hacker News show 7d, New to our radar shows 24h. More on the methodology page and pace Velocity (Nx usual pace)This week's star gain divided by the project's usual weekly gain. The usual gain is the average weekly gain over the 4 weeks before (days 8 to 35 ago), counted as at least 10 stars. 2.0x means twice the usual pace. Without a reading from 35 days ago, the ranking assumes 2% of the stars the project had 7 days ago as its usual weekly gain. More on the methodology page Signal SignalOne label per project that states a measured fact. It is not a verdict. The first rule that matches wins, and a missing number never triggers a rule. Archived: The repo is archived by its owner. Gone quiet: No commits in more than 90 days. Surging: At least 1,000 stars gained in 7 days, or at least 300 in 24 hours. Accelerating: This week's star gain is at least 3x the project's usual weekly gain (average of the 4 weeks before), and at least 50 stars. Slipping: The star count fell over 7 days, or gained nothing in a week when it usually gains. Cooling off: Usual weekly gain is at least 50 stars and this week's is under 40% of it. More talk than stars: At least 150 Hacker News points in 7 days and fewer than 200 stars gained in 7 days. Quiet climber: At least 300 stars gained in 7 days and no Hacker News points. Being talked about: At least 50 Hacker News points in 7 days. Watching: None of the above. Nothing stands out yet. More on the methodology page
1 linger

Linger is An Open-Source Personal Agent That Runs Fully on Your PC. We aim to break Big Te...

REAL 78 84 -6 +3,250 325.0x Surging

91% of its stars arrived in the last 7 days. No Hacker News posts in the last 7 days.

2 yogurt

Private AI meeting notes that stay on your computer. No meeting bot. Free and open source...

REAL 99 88 +11 +1,360 44.4x Surging

47% of its stars arrived in the last 7 days. No Hacker News posts in the last 7 days.

3 Haru

Haru: a low-latency, multilingual, full-duplex spoken dialogue model

TOO EARLY 73 30 +9 to +50 +367 36.7x Quiet climber

51% of its stars arrived in the last 7 days. No Hacker News posts in the last 7 days.

4 smolmaxxing

maxxing the ability to run different LLMs on the smallest devices possible

TOO EARLY 97 66 +17 to +54 +383 26.9x Quiet climber

35% of its stars arrived in the last 7 days. No Hacker News posts in the last 7 days.

5 ANR

Apex Neural Rendering (ANR) by Apex Compute

OVERHYPED 96 56 +40 +951 25.0x Quiet climber

33% of its stars arrived in the last 7 days. No Hacker News posts in the last 7 days.

6 LittleBit

Official implementation of LittleBit (NeurIPS 2025) and its follow-up LittleBit-2 (ICML 20...

TOO EARLY 75 4 +28 to +67 +385 20.0x Accelerating

52% of its stars arrived in the last 7 days. Gaining 20.0x its usual weekly pace. No Hacker News posts in the last 7 days.

7 WindowsiOS

Native Windows 11 ARM64 on iOS (iPhone Duo) with direct ARM64 JIT, 4KB ASID MMU, UEFI/ACPI...

TOO EARLY 69 17 +13 to +54 +179 17.9x Watching

38% of its stars arrived in the last 7 days. No Hacker News posts in the last 7 days.

8 Claude-Cage

Cage:为 Claude 特化的轻量化虚拟机,彻底杜绝网络泄露。多平台适配,支持多账号管理、远程部署、移动端操控。

REAL 77 92 -15 +1,896 17.1x Surging

25% of its stars arrived in the last 7 days. No Hacker News posts in the last 7 days.

9 AgentFlux

Agentic AI platform for visual workflows and autonomous agents. Run it with Docker on your...

TOO EARLY 67 14 +14 to +54 +129 12.9x Watching

41% of its stars arrived in the last 7 days. No Hacker News posts in the last 7 days.

10 deepseek-v3-jax

DeepSeek V3 (MLA, DeepSeekMoE, aux-loss-free balancing, MTP) in ~200 lines of pure JAX, tr...

TOO EARLY 94 36 +25 to +67 +106 10.6x Watching

41% of its stars arrived in the last 7 days. No Hacker News posts in the last 7 days.

11 WowType

像微信输入法一样顺手的Linux输入法:长句一次打完、按错键也能认出来、纯离线语音输入、实时翻译,越用越懂你。

REAL 70 95 -25 +187 10.2x Watching

17% of its stars arrived in the last 7 days. No Hacker News posts in the last 7 days.

12 MACaQ

SOTA model-agnostic quantization for GGUF, local inference and beyond. Quantize and run te...

TOO EARLY 94 31 +29 to +70 +96 9.6x Watching

25% of its stars arrived in the last 7 days. No Hacker News posts in the last 7 days.

13 blender-ai-copilot-hub

A multi-provider AI copilot hub for Blender—bring OpenAI, Anthropic Claude, Google Gemini,...

OVERHYPED 64 15 +49 +80 8.0x Watching

16% of its stars arrived in the last 7 days. No Hacker News posts in the last 7 days.

14 gputaskman

A GPU task manager for Windows, Linux, and WSL: per-process VRAM, GPU activity, and LLM mo...

REAL 74 81 -8 +421 6.5x Quiet climber

11% of its stars arrived in the last 7 days. No Hacker News posts in the last 7 days.

15 llama-modchip

Zero-GPU CPU inference for 30B-284B MoE models (Qwen3.8 176.5B cold-cache certified in 28....

REAL 95 70 +25 +152 6.1x Watching

11% of its stars arrived in the last 7 days. No Hacker News posts in the last 7 days.

16 bla

🛡️ BLA (bla-agents / Blind LLM Agents) — Open-source Blue Defense MCP server & CLI protect...

REAL 95 92 +4 +673 5.9x Quiet climber

11% of its stars arrived in the last 7 days. No Hacker News posts in the last 7 days.

17 Mika

An on-device AI agent for Android that operates apps and the web to get things done for yo...

REAL 76 97 -21 +874 5.1x Quiet climber

9% of its stars arrived in the last 7 days. No Hacker News posts in the last 7 days.

18 kapitsa

Blazing fast Apple Silicon inference engine optimized for Qwen & Nemotron. OpenAI + Anthro...

REAL 88 93 -6 +52 3.3x Watching

6% of its stars arrived in the last 7 days. No Hacker News posts in the last 7 days.

19 gpu-unlock

Your GeForce runs AI at half speed. This fixes it for 20/30/40 series cards. Up to 2× FP16...

OVERHYPED 100 54 +46 +1,095 2.8x Surging

5% of its stars arrived in the last 7 days. No Hacker News posts in the last 7 days.

20 survival-llm

A free AI assistant and survival library that runs on your own computer, with no internet...

MID 62 51 +11 +67 2.0x Watching

4% of its stars arrived in the last 7 days. No Hacker News posts in the last 7 days.

21 magnitude

Open source inference engine that tunes its kernels on your hardware to find the fastest w...

REAL 78 96 -18 +309 1.7x Quiet climber

4% of its stars arrived in the last 7 days. Gaining 1.7x its usual weekly pace. No Hacker News posts in the last 7 days.

22 neuron-explorer

Steering-first neuron explorer for Qwen3.5-4B: push every MLP neuron, keep every rollout,...

TOO EARLY 93 52 +19 to +59 +61 1.5x Watching

3% of its stars arrived in the last 7 days. No Hacker News posts in the last 7 days.

23 dynamo

A Datacenter Scale Distributed Inference Serving Framework

REAL 67 93 -26 +55 1.3x Watching

1% of its stars arrived in the last 7 days. Gaining 1.3x its usual weekly pace. No Hacker News posts in the last 7 days.

24 HyperQwen

Serve large Qwen models fast on the GPUs you actually own. Qwen3.8-27B on a single 24 GB c...

REAL 70 74 -4 +69 1.3x Watching

2% of its stars arrived in the last 7 days. No Hacker News posts in the last 7 days.

25 ggml

Tensor library for machine learning

OVERHYPED 97 62 +35 +354 1.1x Quiet climber

2% of its stars arrived in the last 7 days. No Hacker News posts in the last 7 days.

26 awesome-free-llm-apis

List of Permanent Free LLM API (API Keys)

REAL 85 89 -4 +680 1.0x Quiet climber

5% of its stars arrived in the last 7 days. Gaining 1.0x its usual weekly pace. No Hacker News posts in the last 7 days.

27 ollama

Get up and running with Kimi, GLM, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other model...

REAL 87 91 -4 +814 1.0x Quiet climber

0% of its stars arrived in the last 7 days. Gaining 1.0x its usual weekly pace. No Hacker News posts in the last 7 days.

28 ODS

ODS V3 Pre-Release: Public testing and refinement ahead of the official V3 launch. Turn yo...

REAL 62 78 -16 +65 1.0x Watching

1% of its stars arrived in the last 7 days. Gaining 1.0x its usual weekly pace. No Hacker News posts in the last 7 days.

29 freellmapi

10.1 billion tokens per month. 87 free LLM providers. 1,313 free model endpoints. All behi...

REAL 91 93 -3 +3,827 1.0x Surging

7% of its stars arrived in the last 7 days. Gaining 1.0x its usual weekly pace. No Hacker News posts in the last 7 days.

30 llmfit

Hundreds of models & providers. One command to find what runs on your hardware.

REAL 77 87 -9 +223 0.9x Watching

1% of its stars arrived in the last 7 days. Gaining 0.9x its usual weekly pace. No Hacker News posts in the last 7 days.

31 omlx

LLM inference server with continuous batching & SSD caching for Apple Silicon — managed fr...

REAL 92 98 -5 +175 0.9x Watching

1% of its stars arrived in the last 7 days. Gaining 0.9x its usual weekly pace. No Hacker News posts in the last 7 days.

32 starnet

A living pixel-art station where real AI agents do real work. Local-first desktop agent ha...

REAL 68 82 -14 +71 0.9x Watching

4% of its stars arrived in the last 7 days. Gaining 0.9x its usual weekly pace. No Hacker News posts in the last 7 days.

33 openwhispr

Voice-to-text dictation app with local (Nvidia Parakeet/Whisper) and cloud models (BYOK)....

REAL 83 85 -2 +419 0.8x Quiet climber

3% of its stars arrived in the last 7 days. Gaining 0.8x its usual weekly pace. No Hacker News posts in the last 7 days.

34 modly

Desktop app to generate 3D models from images or prompt using local AI — runs entirely on...

REAL 69 78 -9 +84 0.8x Watching

1% of its stars arrived in the last 7 days. Gaining 0.8x its usual weekly pace. No Hacker News posts in the last 7 days.

35 OpenMAIC

Open Multi-Agent Interactive Classroom — Get an immersive, multi-agent learning experience...

REAL 84 96 -12 +512 0.8x Quiet climber

1% of its stars arrived in the last 7 days. Gaining 0.8x its usual weekly pace. No Hacker News posts in the last 7 days.

36 cactus

Sub-50mb agentic, voice and vision intelligence for consumer devices.

REAL 74 68 +6 +125 0.7x Watching

1% of its stars arrived in the last 7 days. Gaining 0.7x its usual weekly pace. No Hacker News posts in the last 7 days.

37 WeKnora

Open-source LLM knowledge platform: turn raw documents into a queryable RAG, an autonomous...

REAL 86 80 +6 +531 0.7x Quiet climber

1% of its stars arrived in the last 7 days. Gaining 0.7x its usual weekly pace. No Hacker News posts in the last 7 days.

38 HAST-SEC

武汉光影流明科技有限公司 | 本地中文交互与连续角色运动 | 非商业早期研究版 | 寻求技术合作与融资

OVERHYPED 58 28 +30 +52 0.7x Watching

8% of its stars arrived in the last 7 days. Gaining 0.7x its usual weekly pace. No Hacker News posts in the last 7 days.

39 Handy

A free, open source, and extensible speech-to-text application that works completely offli...

REAL 87 82 +4 +783 0.7x Quiet climber

2% of its stars arrived in the last 7 days. Gaining 0.7x its usual weekly pace. No Hacker News posts in the last 7 days.

40 FluidVoice

Fastest and only macOS Dictation app with on-device STT and custom trained AI enhancement...

REAL 77 86 -9 +130 0.7x Watching

1% of its stars arrived in the last 7 days. Gaining 0.7x its usual weekly pace. No Hacker News posts in the last 7 days.

41 llm_wiki

LLM Wiki is a cross-platform desktop application that turns your documents into an organiz...

OVERHYPED 78 18 +60 +142 0.6x Watching

1% of its stars arrived in the last 7 days. Gaining 0.6x its usual weekly pace. No Hacker News posts in the last 7 days.

42 project-maya

Run GLM-5.3 (744B), DeepSeek-V4.1-Flash (748B), MiniMax-M3.1-Flash (428B), GLM-5.3-Flash (...

REAL 94 93 +0 +268 0.6x Watching

8% of its stars arrived in the last 7 days. Gaining 0.6x its usual weekly pace. No Hacker News posts in the last 7 days.

43 Soup

Fine-tune LLMs from one YAML. Layer streaming trains an 8B model on a 4 GB laptop GPU.

REAL 80 88 -8 +166 0.5x Watching

2% of its stars arrived in the last 7 days. Gaining 0.5x its usual weekly pace. No Hacker News posts in the last 7 days.

44 ComfyUI

The most powerful and modular diffusion model GUI, api and backend with a graph/nodes inte...

REAL 88 84 +4 +1,127 0.5x Surging

1% of its stars arrived in the last 7 days. Gaining 0.5x its usual weekly pace. No Hacker News posts in the last 7 days.

45 DeepInfer

DeepInfer: High-performance, large-scale inference framework for DeepSeek models

OVERHYPED 86 51 +36 +256 0.5x Watching

1% of its stars arrived in the last 7 days. No Hacker News posts in the last 7 days.

46 indra

1M param OCR model - runs on CPU, 15x faster than tesseract, close to 1B+ param models in...

REAL 76 63 +13 +89 0.3x Cooling off

5% of its stars arrived in the last 7 days. Gaining 0.3x its usual weekly pace. No Hacker News posts in the last 7 days.

47 DigUp

Search your computer by what's in your files: photos, PDFs, documents, recordings, videos...

MID 75 52 +23 +66 0.1x Cooling off

1% of its stars arrived in the last 7 days. Gaining 0.1x its usual weekly pace. No Hacker News posts in the last 7 days.