MIDREAL

New to our radar

updated 62 minutes ago

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

Sort: Default order Stars gained, 7d Stars gained, 24h HN points

More filters

Language: All C++ HTML JavaScript Jupyter Notebook Python Swift TypeScript

Topic: All agent agent-skills ai audio claude-code comfyui cuda cursor deep-learning elevenlabs ffmpeg gemma image-generation jev large-language-models llm llm-agents macos open-source python pytorch qwen self-hosted speech-to-text stable-diffusion text-to-image text-to-speech transformer tts video-generation

# Project Verdict Hype Reality Gap Stars gained, 24h 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 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 skill-distill

Distill a good Claude Code / Codex session into a skill an open-weight model can follow to...

first seen 16h ago, repo created 21 Nov 2026

MID 42 29 +13 - Watching
2 dettato

KobiMusic's multi-instrument audio-to-MIDI transcriber: notes, instrument tracks and drums...

first seen 24h ago, repo created 16 Nov 2026

MID 42 57 -15 +55 Watching
3 Neural-State-OS

Calibrated internal-state modulation, readout, and neural observability for local dense la...

first seen 47h ago, repo created 14 Nov 2026

MID 42 24 +18 +47 Watching
4 pear

Training Reasoning Models in Simulation to Natively Use Real Robots

first seen 6d ago, repo created 13 Nov 2026

MID 42 53 -11 +12 Watching
5 pro-tools-desktop

Pro Tools 2026 desktop setup with multitrack editing, MIDI sequencing, VST hosting and a p...

first seen 6d ago, repo created 14 Nov 2026

MID 42 47 -5 0 Watching
6 tiny-voca

A 4.5M-parameter two-voice English text-to-speech model, trained from scratch

first seen 6d ago, repo created 14 Nov 2026

SLEEPER 42 83 -41 +33 Watching
7 MiniMax-H3-Image

MiniMax-H3-Image, an open-weight model for 16-megapixel image generation and editing.

first seen 9d ago, repo created 9 Nov 2026

TOO EARLY 63 27 +0 to +42 +6 Watching
8 PAN2

Training code for PAN2, a open foundation world model for physical intelligence

first seen 10d ago, repo created 5 Nov 2026

TOO EARLY 57 9 +7 to +47 +1 Watching
9 TimeNet

Download and explore time-series datasets through one standardized format.

first seen 10d ago, repo created 8 Jul 2026

REAL 91 80 +11 +1 Watching
10 SPECTRA

Compress any LLM in seconds, load it for inference and in one click you have an AI that co...

first seen 10d ago, repo created 8 Nov 2026

TOO EARLY 83 26 +20 to +62 0 Watching
11 deleting-weights

Public code release for the paper "The Surprising Effectiveness of Deleting Weights in LLM...

first seen 10d ago, repo created 10 Nov 2026

TOO EARLY 56 18 -1 to +41 +2 Watching
12 ttf-home

Ternary language models on a home computer: run, train, convert, fine-tune, export to GGUF

first seen 10d ago, repo created 9 Nov 2026

OVERHYPED 90 39 +51 0 Watching
13 ttf-conversion

Qwen3.5 / 3.8 to ternary with TTF-trainable ternary adapters

first seen 10d ago, repo created 24 Oct 2026

TOO EARLY 82 34 +14 to +56 0 Watching
14 ttf-ternary

Two-timescale threshold flips (TTF): training and converting ternary {-1,0,1} LLMs without...

first seen 10d ago, repo created 31 Aug 2026

MID 85 59 +25 +3 Watching
15 supermimic

Humanoid whole-body motion tracking with one differentiable world model.

first seen 11d ago, repo created 10 Nov 2026

TOO EARLY 74 43 +3 to +45 +14 Quiet climber
16 Naive-N0.5-Flash

Naive-N0.5-Flash is an open-weight 309B MoE model with 15.5B active parameters, built for...

first seen 11d ago, repo created 27 Sep 2026

TOO EARLY 62 0 +23 to +57 +13 Watching
17 Flide

🔥🔥 The extremely fast inference engine for decision model

first seen 12d ago, repo created 24 Oct 2026

REAL 93 78 +15 0 Watching
18 OpenAmika

OpenAmika: MekaHime's AI companion Amika, open source. Live2D avatar, real-time voice, lon...

first seen 16d ago, repo created 3 Nov 2026

REAL 59 74 -15 0 Watching
19 NextTransformer

:sunrise: A comprehensive, cutting-edge open-source framework for next-generation Transfor...

first seen 17d ago, repo created 31 Oct 2026

REAL 62 77 -15 +2 Watching
20 frontier-weight-edit

A frontier model edits another model's weights by hand (Gemma 4 12B, EN->IT tense). Plus a...

first seen 17d ago, repo created 3 Nov 2026

MID 22 25 -3 0 Watching
21 latent-sparse-attention

Code for Latent Sparse Attention: Towards Subquadratic Ultra-Long Context Attention

first seen 17d ago, repo created 27 Oct 2026

SLEEPER 30 68 -38 0 Watching
22 shisei

💃 Free CC0 mannequin pose reference library for AI image tools (Nano Banana, ChatGPT, Comf...

first seen 19d ago, repo created 29 Oct 2026

MID 59 41 +18 +4 Watching
23 Mol-1

Open Frontier Biomolecular Intelligence

first seen 22d ago, repo created 26 Oct 2026

MID 51 30 +21 0 Watching
24 nesformer

An NES CPU compiled into the weights of a stock Qwen3.5 model

first seen 22d ago, repo created 30 Oct 2026

TOO EARLY 87 8 0 Watching
25 SenseNova-6.8-Code2Video

The first open-source model for code-driven video creation.

first seen 22d ago, repo created 24 Oct 2026

TOO EARLY 65 14 +12 to +52 +8 Watching
26 Concept-Brittleness

Concept Brittleness

first seen 23d ago, repo created 28 Oct 2026

REAL 42 60 -18 0 Watching
27 ReMCTS

ReMCTS

first seen 23d ago, repo created 27 Oct 2026

REAL 42 66 -23 0 Watching
28 openjutsu

One-click character swap for videos: an open-source, local Higgsfield Genjutsu alternative...

first seen 24d ago, repo created 26 Oct 2026

TOO EARLY 70 32 +4 to +46 +21 Watching
29 bla

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

first seen 24d ago, repo created 25 Oct 2026

REAL 95 92 +4 +49 Quiet climber
30 detectorscope

Build AI text detectors whose decisions are mechanistically grounded and human-auditable (...

first seen 24d ago, repo created 24 Oct 2026

TOO EARLY 90 8 +1 Watching
31 MiniCPM-OCR

Fast, accurate OCR with correctness assessment.

first seen 24d ago, repo created 27 Oct 2026

REAL 62 73 -11 +3 Watching
32 Hy-Nomas

Hy-Nomas: Towards Free-form Interactive World Generation

first seen 26d ago, repo created 21 Oct 2026

REAL 53 61 -7 +1 Watching
33 hob

An easier way to use AI on your own computer. A free, open-source alternative to Claude an...

first seen 26d ago, repo created 14 Oct 2026

OVERHYPED 92 61 +30 +1 Watching
34 WeVisOne-VL

WeVisOne-VL is a powerful VLM by the WeChat Vision Team at Tencent, unifying object-level...

first seen 27d ago, repo created 22 Oct 2026

TOO EARLY 61 12 +10 to +50 +7 Watching
35 GVS5H

GVS5H: Five Qwen3.8-27B Models Match Claude Fable 5 on LiveCodeBench Hard | Fable 5 Level...

first seen 28d ago, repo created 26 Aug 2026

TOO EARLY 87 13 +1 Watching
36 Lampline

Build AI phone agents on your own computer and test every change with an AI caller. Open s...

first seen 28d ago, repo created 19 Oct 2026

SLEEPER 17 65 -48 0 Slipping
37 SuperMimic-Reproduced

Independent reproduction of SuperMimic (arXiv:2610.28480) on mjlab/MuJoCo Warp, written fr...

first seen 28d ago, repo created 21 Oct 2026

MID 29 34 -5 0 Watching
38 voxcpm2-turkce-ses-tasarimi

Turkish voice design with VoxCPM2 on a 4 GB GPU: describe a voice, pick a variant, read te...

first seen 28d ago, repo created 22 Oct 2026

REAL 62 69 -7 +9 Watching
39 PySR

Symbolic Learning in Python and Julia

first seen 28d ago, repo created 14 Sep 2020

REAL 54 72 -18 +5 Watching
40 Ming-3.0-tts

Ming-3.0-tts is an open-source TTS model family with 0.5B dense and 7.9B-A1.3B MoE variant...

first seen 29d ago, repo created 19 Oct 2026

TOO EARLY 57 23 -3 to +39 +4 Watching
41 supermimic_vibed

vibe coded supermimic within 1h, LAFAN passed within 1.5 gpuh training

first seen 30d ago, repo created 21 Oct 2026

MID 64 50 +14 0 Watching
42 ai-jailbreaks

AI jailbreaks: 35 paste-ready AI jailbreak prompts for 25+ frontier and open-weight models...

first seen 30d ago, repo created 21 Oct 2026

TOO EARLY 53 8 +4 to +44 +1 Watching
43 whatmodel

Find the best AI models you can run

first seen 31d ago, repo created 28 Sep 2026

SLEEPER 5 56 -51 0 Watching
44 bzo

Battlezone Online: a free 3D multiplayer tank game in the browser (desktop, phone or VR) t...

first seen 32d ago, repo created 6 Dec 2025

SLEEPER 1 80 -79 0 Watching
45 NPCTalk

Make any NPC in any game talk back with Fish Audio: skills, a self-hosted voice server and...

first seen 32d ago, repo created 15 Oct 2026

MID 13 38 -25 0 Watching
46 MOSS-Image

Official repository for MOSS-Image, a 5B-parameter base DiT model with high-quality text r...

first seen 36d ago, repo created 16 Oct 2026

TOO EARLY 79 27 +16 to +58 +11 Cooling off
47 claudemy

Claudemy: an open-source alternative to Udemy and Coursera. Give Claude a topic, it resear...

first seen 37d ago, repo created 14 Oct 2026

MID 59 39 +19 0 Cooling off
48 llm-legislativo

Corpus legislativo brasileiro em larga escala e modelo Transformer causal treinado do zero...

first seen 38d ago, repo created 13 Oct 2026

MID 16 5 +11 +2 Watching
49 indra

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

first seen 38d ago, repo created 13 Oct 2026

REAL 76 63 +13 +5 Cooling off
50 video-prediction-policy-2

Official implementation of Video Prediction Policy 2: Predict Better, Act Better

first seen 39d ago, repo created 8 Oct 2026

MID 25 24 +1 +1 Watching
51 EdgeRock

EdgeRock: Strong Reasoning at Constant Memory. Multimodal models with O(N) generation and...

first seen 40d ago, repo created 7 Oct 2026

TOO EARLY 72 15 +18 to +58 +48 Watching
52 vegaml

Typed decisions from a frozen language model and a small physics engine: calibrated probab...

first seen 40d ago, repo created 9 Oct 2026

SLEEPER 18 87 -70 +3 Watching
53 ai-promo-video-maker

一句话让 AI 帮你做产品宣传片!把产品名或网址告诉 Cursor、Claude Code、Codex 等 AI 编程工具,它会自己调研产品、画出多种风格样图让你挑选、截取 4K...

first seen 40d ago, repo created 9 Oct 2026

LEANS MID 31 1 -9 to +26 0 Watching
54 RSI-Anything

RSI-Anything: Unlocking Recursive Self-Improvement with World Models

first seen 40d ago, repo created 8 Oct 2026

TOO EARLY 64 7 +16 to +56 +2 Watching
55 scam-with-your-friends-web

Scam With Your Friends Web: unofficial open-source browser remake. Co-op AI call center ga...

first seen 42d ago, repo created 9 Oct 2026

MID 16 38 -21 0 Watching
56 ema-lightning

Tiny, fast and accurate Turkish text-to-speech. 8.6M parameters, 0.92% WER on Freya-TR-Eva...

first seen 44d ago, repo created 5 Oct 2026

MID 9 27 -17 0 Watching
57 LittleBit

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

first seen 44d ago, repo created 18 Nov 2025

TOO EARLY 75 4 +28 to +67 +107 Accelerating
58 Qwen-Image-2.1

Qwen's most powerful open-source image generation model

first seen 46d ago, repo created 14 Sep 2026

TOO EARLY 58 1 +17 to +52 +1 Watching
59 verl

verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework

first seen 46d ago, repo created 21 Sep 2026

MID 13 6 +7 +1 Watching
60 transformers5-qwen3.5-recipe

Qwen and DeepSeek low-VRAM LoRA training with GGUF base model, compatible with Transformer...

first seen 46d ago, repo created 21 Jul 2026

SLEEPER 4 48 -44 0 Watching
61 CLM

Contrastive Language Models (CLMs) are a new class of System One model trained with a cont...

first seen 46d ago, repo created 23 Sep 2026

MID 26 11 +15 -1 Watching
62 jev-baselines-eval

Pre-registered independent eval of TypeSafe Jev against a nano-class LLM, a frontier LLM,...

first seen 46d ago, repo created 18 Sep 2026

TOO EARLY 42 11 -9 to +31 0 Watching
63 dust

Pretraining Transformers Without Backpropagation

first seen 46d ago, repo created 2 Oct 2026

MID 18 1 +17 0 Watching
64 TalkLikeYou-Streaming-RealTime-Demo

Real-time browser demo for Talk Like You

first seen 46d ago, repo created 4 Oct 2026

MID 3 5 -2 0 Watching
65 alphaprotein-novo

AlphaProtein Novo

first seen 46d ago, repo created 5 Oct 2026

MID 9 4 +6 0 Watching
66 kandinsky-6

Kandinsky 6.0 Video: Foundation Models for Synchronized Video and Audio Generation

first seen 46d ago, repo created 5 Oct 2026

SLEEPER 2 34 -31 0 Slipping
67 laya

Non-autoregressive System 1 decision engine. Typed choice, score and yes/no decisions over...

first seen 46d ago, repo created 18 Sep 2026

REAL 81 94 -14 +54 Watching
68 jev-trader

One AI trade decision every Monad block. Jev on Kuru MON-USDC.

first seen 46d ago, repo created 16 Sep 2026

MID 26 5 +22 +2 Watching
69 youtube-sponsor-detection

Detect youtube sponsor segment with live audio and transcript powered by Jev

first seen 46d ago, repo created 17 Sep 2026

MID 2 3 -1 0 Watching
70 brewery-ai

An intuitive console agent to fine-tune AI models with little to no experience required!

first seen 46d ago, repo created 4 Oct 2026

MID 5 4 +1 0 Watching
71 GLM-5.3-Flash-EXL3-2x-DGX-Sparks-TensorFold

GLM-5.3-Flash EXL3 on 2x DGX Spark with TensorFold

first seen 46d ago, repo created 30 Sep 2026

SLEEPER 24 68 -44 -1 Watching
72 EvoVLM

Evolving Multimodal Inference Programs: LLM-guided evolutionary search for accurate and ef...

first seen 46d ago, repo created 2 Oct 2026

MID 2 9 -7 0 Watching
73 ODS

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

first seen 46d ago, repo created 9 Feb 2026

REAL 62 78 -16 +24 Watching
74 transformers

🤗 Transformers: the model-definition framework for state-of-the-art machine learning model...

first seen 46d ago, repo created 29 Oct 2018

REAL 82 98 -17 +7 Quiet climber
75 marin

Open-source framework for the research and development of foundation models.

first seen 46d ago, repo created 22 Mar 2024

SLEEPER 55 91 -35 +2 Watching
76 FluidAudio

Frontier CoreML audio models in your apps — text-to-speech, speech-to-text, voice activity...

first seen 46d ago, repo created 21 Jun 2025

SLEEPER 55 87 -32 +1 Watching
77 Kronos

Kronos: A Foundation Model for the Language of Financial Markets

first seen 46d ago, repo created 1 Jul 2025

TOO EARLY 85 2 +24 Gone quiet
78 heretic

Training-free language model modification: Remove censorship, suppress slop, reduce sycoph...

first seen 46d ago, repo created 21 Sep 2025

TOO EARLY 98 67 +24 to +46 +120 Surging
79 Open-Generative-AI

Uncensored Open-source alternative to AI video platforms — Free AI image & video generatio...

first seen 46d ago, repo created 9 May 2023

REAL 88 69 +19 +90 Quiet climber
80 unsloth

Local UI to run and train LLMs and diffusion models. Supports GGUF, MLX, Qwen3.8, DeepSeek...

first seen 46d ago, repo created 29 Nov 2023

REAL 81 98 -17 +64 Quiet climber
81 OpenMontage

World's first open-source, agentic video production system. 12 production pipelines, 100+...

first seen 46d ago, repo created 29 Mar 2026

REAL 90 85 +5 +205 Surging
82 MoneyPrinterTurbo

利用 AI 大模型和自动化工作流,根据主题或关键词一键生成高清短视频。Generate HD short videos from a topic or keyword with a...

first seen 46d ago, repo created 11 Mar 2024

REAL 90 84 +6 +129 Surging
83 VoiceStudio

VoiceStudio is the open-source, fully-local ElevenLabs alternative — voice cloning, voice...

first seen 46d ago, repo created 9 Apr 2026

REAL 99 99 +0 +483 Surging