📦 xytom/coding-tools-mcp

Turn Your Local Editor into a Coding Powerhouse

Stop fighting with limited tools and start supercharging your local development workflow. This project is a specialized coding agent runtime that exposes essential local primitives directly to any standard protocol client. Instead of relying on clunky wrappers, you get direct control over file searching, structured code patching, git status tracking, and command execution, all while keeping your data securely within a defined workspace boundary. It is designed to be model-neutral and highly configurable, allowing you to run complex tasks with robust permission gates. Give your AI agent real, safe access to your local environment and watch your productivity soar.

📰 https://news.ycombinator.com/item?id=48594594

🆔 @hackernewsgithubprojects

📦 dagroup-pku/humannet

HumanNet: Scaling Embodied AI with 1 Million Hours of Video

Are you ready to see the future of robotics? Meet HumanNet, a groundbreaking research hub focused on scaling embodied AI through massive human-centric video learning. By curating a massive one-million-hour corpus of first and third-person footage, this project provides the essential data needed for robots to understand fine-grained human activities. It even includes StableVLA, a vision-language-action model for robust policy learning, and the extensive RoVid-X dataset for training physics-aware models. HumanNet demonstrates that egocentric video is a powerful, cost-effective substitute for limited robot data, paving the way for smarter, more capable robots. Explore this repository to revolutionize your next project.

🆔 @hackernewsgithubprojects

📦 agentic-in/inferoa

Take Control of Your AI Agents with Inferoa

Are your AI agents struggling to maintain focus during long tasks? Stop relying on simple prompting and start mastering loop engineering with Inferoa. This inference-native agent harness gives your AI a durable runtime, allowing it to inspect, edit, and verify complex work across recursive loops until the objective is proven. By optimizing your token usage through prefix-cache discipline and intelligent model routing, Inferoa keeps your context clean and your costs under control. Whether you are automating coding workflows or running research tasks, this powerful harness ensures your agents self-correct and deliver results effectively. Try it today to elevate your agentic workflow.

🆔 @hackernewsgithubprojects

📦 abhinavkale-dev/fynt

Build Powerful Automations with Fynt

Stop juggling manual tasks and start building custom automation pipelines with Fynt. This self-hostable platform provides a clean visual node editor where you can drag, connect, and configure complex workflows without the headache. Whether you need to chain together AI models, sync data between apps like Notion and Slack, or build conditional branching logic, Fynt makes it simple. It features live execution streaming through WebSockets and handles your credentials with secure encryption at rest. If you are looking for a flexible, open-source way to automate your daily operations, this powerful toolkit is the perfect place to start your journey.

🆔 @hackernewsgithubprojects

📦 smithhenryd/cgm

Calibrating Generative Models: Align Your AI Outputs

Ever wonder how to make generative models behave exactly how you want? This repository provides a powerful, general-purpose framework for fine-tuning generative models to meet specific distribution-level constraints. Whether you need to control the mean of black-box features with CGM or match full feature distributions using kCGM with MMD objectives, this tool offers a flexible base interface. By implementing simple sample and log probability methods, you can calibrate diverse models, from molecular design to protein structures. Dive into this codebase to gain precise control over your model outputs and bridge the gap between generation and your specific target statistics.

🆔 @hackernewsgithubprojects

📦 harryhsing/omniagent

OmniAgent: The Future of Efficient Video Perception

Tired of AI models wasting resources by watching every single frame of a long video? Meet OmniAgent, a breakthrough framework that completely changes how machines understand video. Instead of a passive, brute-force approach, this native omni-modal agent acts like a human, iteratively observing, thinking, and choosing exactly when to grab frames, audio, or clips. By focusing only on the information that matters, it slashes frame consumption by 73 percent while outperforming massive models. It is an end-to-end reasoning cycle that makes video understanding smarter and faster than ever before. Check out the project to see the new standard in efficient perception.

🆔 @hackernewsgithubprojects

📦 techenthusiast167/webrecon

Master Your OSINT Reconnaissance with WebRecon

Struggling to map out complex digital footprints for your security research? Meet WebRecon, a powerful open-source tool designed to automate web reconnaissance for cybersecurity professionals. Unlike simple crawlers, this tool specializes in intelligence gathering, from harvesting emails and identifying technology stacks to discovering cloud storage. Its standout feature is the advanced relationship graph visualization, which maps connections between domains, profiles, and infrastructure into an interactive network map. Whether you are performing attack surface management or deep-dive investigations, WebRecon turns raw data into clear, actionable visual insights. Start mapping your targets smarter today and take your security analysis to the next level.

🆔 @hackernewsgithubprojects

📦 hp-luo/stare

Stop Model Entropy Collapse with STARE

Are you tired of your reasoning models losing their edge during training? Reinforcement Learning with Verifiable Rewards often suffers from policy entropy collapse, where models stop exploring effectively. STARE, or Surprisal-guided Token-level Advantage Reweighting, solves this by identifying entropy-critical tokens and selectively reweighting their advantages to sustain exploration. It uses a smart closed-loop gating mechanism that intervenes only when necessary to keep training stable. By effectively managing entropy during complex reasoning tasks, STARE consistently outperforms standard baselines like GRPO. Whether you are working with small or large models, STARE helps maintain the vital balance between exploration and exploitation.

🆔 @hackernewsgithubprojects

📦 mingyuchoi-run/lsm

Boost Image Quality with Linear Recurrent Units

Ever wonder how to sharpen blurry images while keeping computation efficient? This repository features an innovative approach to image super-resolution using a Linear Recurrent Unit combined with a special semantic modulating unit. By integrating spatial categorization and feature enhancement, this method achieves state-of-the-art results that balance performance with efficiency. Whether you are dealing with classical or lightweight super-resolution tasks, this project offers the official code and pretrained models needed to elevate your visual processing projects. Dive into the code to see how these advanced techniques can help you achieve clearer, more detailed images today.

🆔 @hackernewsgithubprojects

📦 gy65896/cotir

Fix Any Image with CoTIR: Internalized Chain-of-Thought Restoration

Struggling to fix complex, degraded photos? Most all-in-one restoration models fall short when things get complicated, but there is a better way. Meet CoTIR, a breakthrough framework that brings Internalized Chain-of-Thought reasoning to image restoration. By treating restoration as a specialized editing subtask, it optimizes results using pre-trained models without the need for slow, multi-step processing. It effectively encodes structured reasoning directly into its learning objective, leading to superior perceptual quality across various scenes. Whether you are dealing with mixed noise or blur, CoTIR provides a powerful, holistic solution for cleaner, sharper images. Experience the next level of image recovery today.

🆔 @hackernewsgithubprojects

📦 malik-group/do-as-i-do

Teach Robots Human Skills from Video!

Ever wondered how to teach a robot to mimic human actions? This repository makes it possible by converting simple hand-object demo videos into precise robot motion trajectories. It breaks the complex process into a multi-stage pipeline that starts by reconstructing 3D hand and object meshes from your footage. It then retargets those movements onto a robot hand using physics-based optimization to ensure the motion is physically consistent. Finally, you can stream these trajectories directly to real hardware. Whether you are into robotics or computer vision, this project offers a fascinating way to turn human demonstrations into actionable robotic tasks.

🆔 @hackernewsgithubprojects

📦 mingyuee88/sae-post-intervention-recovery

Are LLM Interventions Actually Reliable?

Ever wonder if suppressing model behavior through latent interventions is as secure as we think? This project dives into the reliability of Sparse Autoencoder feature clamps by testing whether suppressed behaviors can be recovered from the residual state without reversing the initial intervention. Using tools like encoder-orthogonal projection and cross-layer Jacobian methods, the researchers investigate if these interventions truly form effective behavioral bottlenecks. It covers various settings including refusal, unlearning, and circuit analysis. Explore the core utilities provided in the repository to evaluate your own safety interventions and see if your model defenses are truly holding firm.

🆔 @hackernewsgithubprojects

📦 comfy-org/comfy-kitchen

Supercharge Diffusion Models with Comfy Kitchen

Are your diffusion models running slower than you want? Meet the library that acts as a high-performance kernel engine for your inference tasks. This project provides optimized kernels specifically for diffusion workflows, supporting multiple backends like CUDA and Triton to maximize your hardware potential. By using specialized tensor subclasses, it automatically selects the fastest available backend for your operations, handling complex quantization tasks effortlessly behind the scenes. Whether you are running on Blackwell or older architectures, it optimizes your compute paths for peak efficiency. Give your AI projects a significant speed boost and optimize your inference pipelines today.

🆔 @hackernewsgithubprojects

📦 ctxrs/ctx

Stop Managing Coding Agents Manually: Meet Ctx

Are you tired of juggling coding agents across endless terminal tabs and disconnected files? Meet Ctx, an open-source Agentic Development Environment designed to be a hackable desktop workbench for your AI coding tasks. Instead of scattering work, Ctx centralizes your sessions, transcripts, artifacts, and diffs into one cohesive review surface. It runs agents in isolated containers with strict disk and network controls, ensuring safety without constant approval prompts. Whether you are using local machines or remote devboxes, Ctx keeps your workflow stable and independent. Simplify your agent-powered development and keep your coding process organized with this powerful tool.

📰 https://news.ycombinator.com/item?id=48570577

🆔 @hackernewsgithubprojects

📦 lcy362/agnes-video-generator

Create AI Videos for Free with This Open Source Tool

Stop paying for subscriptions just to create AI videos! This project offers a completely free, open-source platform that turns your text ideas into narrated, multi-scene videos with just one click. By leveraging Agnes AI, you get access to text-to-video, image-to-video, and keyframe generation without any credit card or token limits. It even handles TTS narration and auto-subtitles, giving you full control over the creative process through a simple web interface. Whether you are building stories or generating content from articles, this tool makes AI video production accessible to everyone at zero cost. Start creating your own cinematic content today.

🆔 @hackernewsgithubprojects

📦 leyten/shard

Run Massive AI Models Across Any Consumer GPU

Have you ever wanted to run a massive, frontier-sized artificial intelligence model that simply won't fit on your local hardware? Shard changes the game by enabling pipeline-parallel inference across a distributed swarm of consumer GPUs located on different machines. Instead of needing a single powerful datacenter, Shard splits a model into contiguous layer blocks and distributes them, allowing your devices to stream activations over the internet to serve complex requests. By combining speculative decoding and CUDA-graphed drafts, this engine makes large-scale model inference across geographic distances fast, usable, and verifiable. It is time to rethink where your AI lives.

🆔 @hackernewsgithubprojects

📦 anomalyco/opentui

Build High-Performance Terminal UIs with OpenTUI

Tired of dull terminal interfaces? Meet OpenTUI, a powerful, high-performance library designed for building sophisticated terminal user interfaces. At its heart, OpenTUI utilizes a native core written in Zig, which ensures rock-solid stability and speed. It provides a flexible, component-based architecture that lets you create complex terminal apps with ease. Whether you prefer React or SolidJS, this library offers seamless reconcilers to build your vision. It is already powering production tools, giving you the professional edge needed for your next project. Dive into this extensible toolkit today and start crafting your own advanced terminal experiences with native performance.

🆔 @hackernewsgithubprojects

📦 entireio/cli

Stop Losing Your AI Coding Context

Ever feel like you have lost the thread of your AI coding session? Meet Entire, a tool that hooks directly into your Git workflow to capture every move your AI agent makes. Instead of just seeing code changes, Entire indexes prompts, responses, and session data alongside your commits. It effectively creates a searchable, versioned record of how your code evolved. If you ever need to rewind, you can jump back to a specific checkpoint to resume work seamlessly. It keeps your main Git history clean while ensuring you never lose your AI context again. Give it a try.

🆔 @hackernewsgithubprojects

📦 vercel/workflow

Build Bulletproof AI Agents and Apps with This SDK

Ever struggle with complex, long-running processes in your code? Discover this powerful TypeScript SDK designed to help you build durable, reliable, and observable applications and AI agents. It simplifies challenging tasks like managing long-running states, handling retries, and implementing complex workflows by providing built-in tools for scheduling, sleep functions, and human-in-the-loop interactions. By using this framework, you can ensure your logic runs reliably even when faced with failures. Whether you are creating advanced AI agents or distributed systems, this toolset provides the essential structure to build with confidence. Start building more resilient applications today.

🆔 @hackernewsgithubprojects

📦 palmier-io/palmier-pro

The Future of Video Editing is AI-Native

Are you tired of jumping between web browsers and video editors just to create AI-generated content? Palmier Pro is a swift-native video editor for macOS designed to change that by integrating AI directly into your timeline. It acts as a single source of truth where you can collaborate with AI agents to script, generate, and edit footage seamlessly. By connecting through the Model Context Protocol, you can bridge your video projects with powerful tools like Claude or Cursor. Whether you are automating workflows or iterating on complex shots, this editor brings professional AI-assisted production right to your desktop. Try it out today.

🆔 @hackernewsgithubprojects