AdvertiseWatchSubscribe
Last scan 55 h agoMonday, November 16, 2026

Early Signal: today's fastest-growing AI repos, models and papers

Edition · Friday, November 13, 2026152 new signals · 3.5k repos watched · 9 sources
apex-compute/ANR▲ 492stars in the last day 1.5k total
5 days old

▲ 492 todayNew · 5d old

Open-source frame generation rivals DLSS, now on Windows and Linux

ANR adds AI-powered frame generation to games, letting supported GPUs render extra frames for smoother motion. It works via a simple installer that hooks into the game's executable and can be compared against DLSS, FSR, XeSS and others.

Why it matters. Game developers and modders who want a free alternative to proprietary upscalers can test ANR in their titles.

spotted Nov 13

Today in one paragraph. Today's wave of open-source AI is eroding the monopoly of big-tech, with projects like apex-compute's ANR delivering frame-generation quality that rivals Nvidia's DLSS on both Windows and Linux. From cheaper speech-to-text on Spot instances to a 300 M LLM running on an iPad, the toolbox keeps expanding.

More stories

▲ 148 todayNew · 3d old

Manus lets AI run code and browse for you

Manus is an autonomous AI agent that can write, execute scripts and control a web browser based on natural language instructions. It runs tasks like form-filling, data gathering or small code jobs without you typing each step.

Reach the people who try new AI tools first. Advertise on Early Signal, from $19 a day →

The repo market

Open-source projects ranked by stars gained today, top 5 of 86

ProjectTodayTotal
agdinis/ai--manusNew · 3d oldAutonomous AI Agent Executes Code and Controls Browsers for YouManus is an AI-powered assistant that can write and run scripts and operate a web browser on your behalf. You describe a task and it figures out the steps, handling forms, data gathering, and small automation without you typing each command. ▲ 148148
PrathmeshYa/ai--manusNew · 3d oldAutonomous AI Agent Executes Code and Controls BrowsersManus is an AI agent that can write and run code and operate a web browser for you. You describe a task and it carries out the steps, from filling forms to running scripts, without manual typing. ▲ 148148
python001-dev/manus--aiNew · 3d oldManus lets AI run code and browse for youManus is an autonomous AI agent that can write and execute scripts and control a web browser on your behalf. You describe a task and it figures out the steps, from opening pages to filling forms. ▲ 148148
ITprogamatikDedSec/ai--manusNew · 3d oldManus lets AI run code and control browsers autonomouslyManus is an AI agent that can write, execute, and debug code while also navigating web pages for you. You describe a task and it turns the description into real actions without manual clicks. ▲ 148148
mtn-imran-khan/manus--aiNew · 3d oldManus lets AI agents code and browse for youManus is an autonomous AI agent that can write and run code and control a web browser based on natural language prompts. It can fill forms, scrape data, and execute scripts without you typing each step. ▲ 148148

New models

Trending on Hugging Face, top 3 of 5

From the labs

Straight from the companies building them, top 9 of 14

  1. AWS ML

    Bedrock AgentCore V2 cuts session startup to a snap

    Amazon’s new AgentCore runtime V2 snapshots the initialized environment and restores it for each new session, so startup time no longer scales with image size. The post walks through measuring startup latency and presents four architecture patterns for fast sessions.

  2. AWS ML

    OpenFold3 on SageMaker lets you predict protein structures in the cloud

    OpenFold3-preview is now available as a SageMaker JumpStart model, enabling you to run asynchronous inference on proteins, DNA, RNA and ligand complexes directly in your AWS account. It supports multi-GPU parallelism, custom multiple sequence alignments for higher accuracy, and keeps your data private.

  3. AWS ML

    AssemblyAI cuts speech-to-text costs 70% with EC2 Spot

    AssemblyAI demonstrates a pipeline that runs large-scale speech-to-text inference on AWS using ECS and Spot GPU instances. An SQS-based retry loop keeps latency in-line with SLAs while delivering about 70 % cost savings versus on-demand servers.

  4. AWS ML

    Bedrock adds zero-instrumentation per-user cost tracking

    Amazon Bedrock now automatically tags each inference request with the IAM principal that issued it, so you can see exactly who is spending on AI models. No code changes or extra instrumentation are required.

  5. AWS ML

    SageMaker HyperPod captures live inference data for continuous model tuning

    Amazon SageMaker HyperPod Data Capture automatically stores the inputs and outputs of a running inference endpoint into an Amazon S3 bucket. The stored traffic can then be queried with Athena to spot blind spots and used to fine-tune a new model version.

  6. Hugging Face

    NVIDIA releases SimReady pick-and-place demo for robot testing

    The walkthrough shows how to set up a UR17G arm with a Robotiq 2F-140 gripper and a beverage can in Isaac Sim using pre-validated SimReady assets. The assets include collision, mass and joint-drive data so the simulated robot can actually pick up and move the can with agent-generated controls.

  7. Hugging Face

    XYBench flags hidden misconceptions in AI assistant queries

    XYBench is a benchmark of over 8,000 real questions that test whether AI assistants can spot the XY problem, when users ask for the wrong solution. It measures a model’s ability to redirect users to the real issue instead of just answering the misguided request.

  8. OpenAI

    ChatGPT Wallet lets agents process purchases with user approval

    ChatGPT Wallet adds a built-in payment flow for agents in ChatGPT Work, Codex and related tools. Users approve each transaction and the feature uses existing card protections to keep payment data safe.

  9. Hugging Face

    llama.cpp 1.0 launches stable C++ LLM inference library

    llama.cpp v1.0.0 offers a portable C/C++ library that runs large language models on everything from a laptop to a server, using quantization and optimized backends. It gives developers a lightweight way to embed private AI inference without relying on the cloud.

Research

The papers researchers upvoted most today, top 9 of 33

  1. Paper

    BirdDreams Generates Joint Front-View and Bird-Eye Driving Video

    BirdDreams is a neural model that creates both the driver’s camera view and a top-down bird’s-eye view of a road scene as it evolves under different vehicle actions. By learning motion separately from appearance it produces more plausible traffic behavior.

    45 upvotes

  2. Paper

    PhysLoop lets LLMs teach video generators physics

    PhysLoop uses a large language model’s physics knowledge to evaluate and correct videos generated by AI models. The feedback loop creates fine-grained supervision without human labelling, helping the video model learn more realistic dynamics.

    42 upvotes

  3. Paper

    New token compression method speeds up autoregressive image generation

    G-STAR lets image generators pack more visual detail into fewer tokens, cutting generation time. It groups tokens and applies product quantization to keep quality while compressing the sequence.

    40 upvotes

  4. Paper

    Duo offers real-time two-way AI perception and response

    Duo is a full-duplex world model that watches video and listens to audio while simultaneously generating spoken replies. It runs continuously, treating the AI’s mind and the physical scene as one shared world.

    36 upvotes

  5. Paper

    Study Breaks Down Decision Models for Long-Horizon AI Agents

    The paper classifies decision models into three roles, actor, judge, and teacher, based on whether they pick actions, evaluate past actions, or assign scores for learning. It then measures how each role performs on tasks that require planning many steps ahead.

    29 upvotes

  6. Paper

    Open Vision Banana releases full code for generative visual perception

    It provides an open-source implementation that turns vision problems into conditional image-editing using a pretrained diffusion model. Users can run the model to perform tasks like segmentation or object detection by editing images rather than training a separate network.

    29 upvotes

  7. Paper

    Researchers simplify hyper-connections to speed up LLM training

    The study dissects the hyper-connection blocks used in cutting-edge language models, identifying which pieces are essential and which waste compute. It then proposes a leaner version that retains accuracy while lowering training overhead.

    26 upvotes

  8. Paper

    Ropedia Xperience 2 sets new bar for robot learning benchmarks

    Ropedia Xperience 2 is a large-scale collection of physical AI environments and recorded robot behaviors. It lets researchers train and evaluate models on long-horizon, contact-rich tasks using visual inputs.

    25 upvotes

  9. Paper

    Test-time Baking speeds up decoder-only view synthesis

    TTB pre-computes the test-time training layers of large view synthesis models so they can render new camera angles faster. It keeps the quality of KV-cached decoder-only models while cutting inference cost.

    19 upvotes

The conversation

What builders are arguing about on Hacker News, top 7 of 14

  1. Hacker News

    Forensic tool detects Blackwell GPU fingerprints in Chinese AI models

    The analysis scans publicly released model checkpoints for numerical patterns that only arise when training on NVIDIA’s Blackwell GPUs. It shows that DeepSeek, Moonshot AI, MiniMax and Ant Group have been using the restricted hardware despite export bans.

    355 points51 commentsRead the thread

  2. Hacker News

    Open-Source 145B Model Now Runs on Your Laptop

    Edge0-145B is an open-source AI model with 145 billion parameters that can be run locally on a personal computer. It offers coding, reasoning, and agent capabilities comparable to cloud-based frontier models without any usage fees.

    338 points47 commentsRead the thread

  3. Hacker News

    AI deciphers Gödel’s shorthand, revealing hidden theorems

    A machine-learning system was trained to read Gödel’s 1,009 pages of German Gabelsberger shorthand and translate them into modern mathematical notation. The output shows dozens of previously unknown proved theorems in logic and set theory.

    321 points60 commentsRead the thread

  4. Hacker News

    AI Is Destroying the Trust Between Writers and Readers

    309 points77 commentsRead the thread

  5. Hacker News

    Apple launches Swift framework for on-device AI models

    The Foundation Models framework gives Swift developers a built-in way to call large language models, either the on-device Apple model or any remote model you point it at. It also supports multimodal prompts, tool calling and image understanding, so you can add summarisation, chat agents or visual analysis to an iOS or macOS app with a few lines of code.

    265 points26 commentsRead the thread

  6. Hacker News

    Brave Search API now accepts instant USDC payments via x402

    Developers and autonomous AI agents can call the Brave Search API and pay per query with USDC, using the open x402 payment protocol. The API returns a 402 response with price details when no payment is attached, and the client retries with a signed payment.

    256 points87 commentsRead the thread

  7. Hacker News

    600 Experiments Reveal JEPA World Model’s Surprising Weak Spot

    The author ran 600 trials on LeWM, a joint-embedding predictive architecture that plans actions in a compact embedding space instead of pixels. The study shows that a tiny visual detail in the goal image can impact success more than swapping the predictor for a physics engine.

    211 points32 commentsRead the thread

Get the signal first.

Join the list for the morning email: the day's biggest AI launches, explained in five minutes. Unsubscribe any time.

Prefer a reader? Follow the RSS feed.