This media is not supported in your browser
VIEW IN TELEGRAM
📦 zju-real/perceive-to-reason
perceive-to-reason
Visual language models often fail at complex tasks because they try to look and think at the exact same time, mixing up simple observation with deep logic. The perceive-to-reason framework solves this problem by completely separating the visual perception stage from the logical reasoning stage. By using an alternating reinforcement learning strategy, the system trains one model to act as a dedicated perceiver and another as a focused reasoner, passing clean visual details to the logic engine. This division of labor achieves much higher accuracy on complex, high-resolution visual puzzles without getting overwhelmed. It is a brilliant way to build smarter, more analytical visual AI.
🆔 @hackernewsgithubprojects
perceive-to-reason
Visual language models often fail at complex tasks because they try to look and think at the exact same time, mixing up simple observation with deep logic. The perceive-to-reason framework solves this problem by completely separating the visual perception stage from the logical reasoning stage. By using an alternating reinforcement learning strategy, the system trains one model to act as a dedicated perceiver and another as a focused reasoner, passing clean visual details to the logic engine. This division of labor achieves much higher accuracy on complex, high-resolution visual puzzles without getting overwhelmed. It is a brilliant way to build smarter, more analytical visual AI.
🆔 @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
📦 openrouterteam/awesome-openrouter
awesome-openrouter
Find the perfect, pre-built application to plug your AI models straight into by exploring a hand-curated registry of tools designed for OpenRouter. Instead of building your own user interfaces or coding complex integrations from scratch, awesome-openrouter acts as a master directory connecting you to dozens of projects like terminal coding assistants, browser automation agents, and visual data tools. It solves the massive headache of trying to figure out which applications actually support a unified API key for hundreds of different models. Grab a key, pick any tool from this collection, and start experimenting instantly.
🆔 @hackernewsgithubprojects
awesome-openrouter
Find the perfect, pre-built application to plug your AI models straight into by exploring a hand-curated registry of tools designed for OpenRouter. Instead of building your own user interfaces or coding complex integrations from scratch, awesome-openrouter acts as a master directory connecting you to dozens of projects like terminal coding assistants, browser automation agents, and visual data tools. It solves the massive headache of trying to figure out which applications actually support a unified API key for hundreds of different models. Grab a key, pick any tool from this collection, and start experimenting instantly.
🆔 @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
📦 dramaclaw/dramaclaw
dramaclaw
dramaclaw is the open-source video engine that turns a raw script into a finished film in one single pipeline. This incredible tool handles the entire drama-production chain by automatically parsing your manuscript into a story graph, planning episodes, generating storyboards, synthesizing emotional voice-overs, and rendering the final cut. Instead of stitching together a dozen disconnected programs, creators can run an entire studio on their own infrastructure. The coolest part is its infinite canvas feature, which lets you visually drag in assets to generate and test media before pushing them back into your main timeline. It is the ultimate sandbox for independent directors.
🆔 @hackernewsgithubprojects
dramaclaw
dramaclaw is the open-source video engine that turns a raw script into a finished film in one single pipeline. This incredible tool handles the entire drama-production chain by automatically parsing your manuscript into a story graph, planning episodes, generating storyboards, synthesizing emotional voice-overs, and rendering the final cut. Instead of stitching together a dozen disconnected programs, creators can run an entire studio on their own infrastructure. The coolest part is its infinite canvas feature, which lets you visually drag in assets to generate and test media before pushing them back into your main timeline. It is the ultimate sandbox for independent directors.
🆔 @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
📦 juliusbrussee/cavemem
Cavemem
Your coding assistant is wasting memory on massive text logs, but cavemem solves this by running all conversational history through a custom compression system before it ever touches the database. It captures observations from your editor sessions, strips private information, and uses a deterministic grammar to squeeze prose down to its absolute essentials while keeping technical details like code blocks, file paths, and shell commands perfectly intact. Backed by a local database and vector index, it runs semantic search and acts as a central memory hub across multiple AI agents. It is the perfect way to give your local coding tools persistent, fast memory without bloating your storage.
🆔 @hackernewsgithubprojects
Cavemem
Your coding assistant is wasting memory on massive text logs, but cavemem solves this by running all conversational history through a custom compression system before it ever touches the database. It captures observations from your editor sessions, strips private information, and uses a deterministic grammar to squeeze prose down to its absolute essentials while keeping technical details like code blocks, file paths, and shell commands perfectly intact. Backed by a local database and vector index, it runs semantic search and acts as a central memory hub across multiple AI agents. It is the perfect way to give your local coding tools persistent, fast memory without bloating your storage.
🆔 @hackernewsgithubprojects
Media is too big
VIEW IN TELEGRAM
📦 mcg-nju/steadydancer
SteadyDancer
Animate any still portrait into a smooth, high-fidelity dance video without losing the original face and clothing details. Traditional animation models often warp the subject's face or body shape during fast movements because they struggle to match the original photo with the target motion data. This project solves that mismatch by directly anchoring the video generation process to your starting image. It locks in the first frame's details so the character looks identical from start to finish, even during complex, high-energy dance routines. If you want to create highly realistic character animations that actually stay on model, this tool is a massive step forward.
🆔 @hackernewsgithubprojects
SteadyDancer
Animate any still portrait into a smooth, high-fidelity dance video without losing the original face and clothing details. Traditional animation models often warp the subject's face or body shape during fast movements because they struggle to match the original photo with the target motion data. This project solves that mismatch by directly anchoring the video generation process to your starting image. It locks in the first frame's details so the character looks identical from start to finish, even during complex, high-energy dance routines. If you want to create highly realistic character animations that actually stay on model, this tool is a massive step forward.
🆔 @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
📦 amap-ml/omnidance
OmniDance
An AI model can now generate highly realistic dance videos from a single photo combined with your choice of music, text prompts, or both. The project is called omnidance, and it solves the difficult challenge of keeping a dancer's identity and movement natural and consistent across a generated video. Built on a dataset mined from internet videos, it uses advanced filtering to remove camera shakes and low-quality clips while utilizing detailed choreography-informed captions. It is a fascinating tool for creators wanting to experiment with artificial choreography, showing how multimodal AI is making motion transfer incredibly accessible.
🆔 @hackernewsgithubprojects
OmniDance
An AI model can now generate highly realistic dance videos from a single photo combined with your choice of music, text prompts, or both. The project is called omnidance, and it solves the difficult challenge of keeping a dancer's identity and movement natural and consistent across a generated video. Built on a dataset mined from internet videos, it uses advanced filtering to remove camera shakes and low-quality clips while utilizing detailed choreography-informed captions. It is a fascinating tool for creators wanting to experiment with artificial choreography, showing how multimodal AI is making motion transfer incredibly accessible.
🆔 @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
📦 inlineresearch/inline-studio
Inline Studio
You can now orchestrate an entire AI-generated film on a free-form visual canvas using your own ComfyUI as the render engine. Inline Studio is an open-source desktop app that transforms generative chaos into structured filmmaking. Instead of losing your best renders to a disorganized history folder, the app treats every generation as an immutable, non-destructive take under a single frame. You can visually chain frames together to pass assets downstream, trim video clips on a timeline, layer audio, and assemble everything into a final cut. It lets you organize, iterate, and export complete generative pipelines so your creative process is fully repeatable.
🆔 @hackernewsgithubprojects
Inline Studio
You can now orchestrate an entire AI-generated film on a free-form visual canvas using your own ComfyUI as the render engine. Inline Studio is an open-source desktop app that transforms generative chaos into structured filmmaking. Instead of losing your best renders to a disorganized history folder, the app treats every generation as an immutable, non-destructive take under a single frame. You can visually chain frames together to pass assets downstream, trim video clips on a timeline, layer audio, and assemble everything into a final cut. It lets you organize, iterate, and export complete generative pipelines so your creative process is fully repeatable.
🆔 @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
📦 corbenicai/aneirin
Slash Your AI Token Costs with Aneirin
Slash your AI bills and trim down your token usage without changing a single answer you get from your models. There is a clever local proxy called aneirin that intercepts the outgoing traffic from tools like Claude Code and GitHub Copilot right on your computer. It performs lossless reductions by wiping out stale thinking blocks and duplicate context you have already paid for, saving massive amounts of billed tokens. Everything runs locally on your machine with absolutely no telemetry, so your sensitive prompts and code never leave your device. Download it to start saving your budget today while keeping your exact AI workflows.
🆔 @hackernewsgithubprojects
Slash Your AI Token Costs with Aneirin
Slash your AI bills and trim down your token usage without changing a single answer you get from your models. There is a clever local proxy called aneirin that intercepts the outgoing traffic from tools like Claude Code and GitHub Copilot right on your computer. It performs lossless reductions by wiping out stale thinking blocks and duplicate context you have already paid for, saving massive amounts of billed tokens. Everything runs locally on your machine with absolutely no telemetry, so your sensitive prompts and code never leave your device. Download it to start saving your budget today while keeping your exact AI workflows.
🆔 @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
📦 ducphamngoc08/codevisualizer
CodeVisualizer
CodeVisualizer is the VS Code extension that finally turns your complex code files into interactive flowcharts and dependency graphs directly inside your editor. Instead of getting lost in deep nested loops or trying to manually trace how modules import each other, you just right-click a function or folder to map out the entire control flow instantly. It runs entirely locally on your machine using clever parsing tools to build clean, color-coded diagrams that update as you type. Plus, you can even connect a local AI model to swap out cryptic variable names with friendly, readable labels. It makes jumping into a messy, unfamiliar project actually fun.
🆔 @hackernewsgithubprojects
CodeVisualizer
CodeVisualizer is the VS Code extension that finally turns your complex code files into interactive flowcharts and dependency graphs directly inside your editor. Instead of getting lost in deep nested loops or trying to manually trace how modules import each other, you just right-click a function or folder to map out the entire control flow instantly. It runs entirely locally on your machine using clever parsing tools to build clean, color-coded diagrams that update as you type. Plus, you can even connect a local AI model to swap out cryptic variable names with friendly, readable labels. It makes jumping into a messy, unfamiliar project actually fun.
🆔 @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
📦 fuchengsu/worldstereo
worldstereo
Turn a single flat image into a fully realized, three-dimensional scene with precise camera control. The repository does exactly that by solving a classic problem in digital art: when you try to generate a video walkthrough from a single picture, the perspective usually warps and gets messy. By using clever 3D geometric memories, this tool keeps everything locked in place, maintaining perfect structural consistency as your virtual camera moves. It is incredibly cool because you can create seamless flythroughs of physical spaces or build dense point clouds that actually line up. You get clean, multi-view consistent scenes without the usual distortion.
🆔 @hackernewsgithubprojects
worldstereo
Turn a single flat image into a fully realized, three-dimensional scene with precise camera control. The repository does exactly that by solving a classic problem in digital art: when you try to generate a video walkthrough from a single picture, the perspective usually warps and gets messy. By using clever 3D geometric memories, this tool keeps everything locked in place, maintaining perfect structural consistency as your virtual camera moves. It is incredibly cool because you can create seamless flythroughs of physical spaces or build dense point clouds that actually line up. You get clean, multi-view consistent scenes without the usual distortion.
🆔 @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
📦 qqqqqf-q/ai-model-fingerprint
AI Model Fingerprint
AI Model Fingerprint is the analytical dataset that catches sneaky AI providers trying to swap out premium models for cheaper alternatives under the hood. It works on a simple, brilliant premise: large language models are terrible at generating truly random numbers. By asking seventeen different models to randomly choose a number between one and three hundred fifty-five thousands of times, this project maps out the distinct, unchangeable statistical habits unique to each engine. Because these patterns bypass system prompts entirely, you can easily verify exactly which model is actually responding to your API requests. It is a incredibly clever way to keep providers honest and study how AI architectures secretly...
🆔 @hackernewsgithubprojects
AI Model Fingerprint
AI Model Fingerprint is the analytical dataset that catches sneaky AI providers trying to swap out premium models for cheaper alternatives under the hood. It works on a simple, brilliant premise: large language models are terrible at generating truly random numbers. By asking seventeen different models to randomly choose a number between one and three hundred fifty-five thousands of times, this project maps out the distinct, unchangeable statistical habits unique to each engine. Because these patterns bypass system prompts entirely, you can easily verify exactly which model is actually responding to your API requests. It is a incredibly clever way to keep providers honest and study how AI architectures secretly...
🆔 @hackernewsgithubprojects
Media is too big
VIEW IN TELEGRAM
📦 bjgreenberg/senior-engineering-partner
Senior Engineering Partner
Enforce a highly disciplined, security-first workflow directly inside your AI coding sessions by turning your assistant into a strict developer mentor. Instead of letting an AI immediately spit out unverified code, this project structure drives a systematic process that forces the assistant to write a specification, draft a plan, write failing tests first, and run real commands to verify everything before declaring a task complete. It holds a non-negotiable security floor across different project phases, from quick prototypes to multi-tenant production apps, ensuring you never commit hardcoded secrets or skip input validation. You get a reliable, repeatable engineering partner that acts as a guardrail for your entire development cycle.
🆔 @hackernewsgithubprojects
Senior Engineering Partner
Enforce a highly disciplined, security-first workflow directly inside your AI coding sessions by turning your assistant into a strict developer mentor. Instead of letting an AI immediately spit out unverified code, this project structure drives a systematic process that forces the assistant to write a specification, draft a plan, write failing tests first, and run real commands to verify everything before declaring a task complete. It holds a non-negotiable security floor across different project phases, from quick prototypes to multi-tenant production apps, ensuring you never commit hardcoded secrets or skip input validation. You get a reliable, repeatable engineering partner that acts as a guardrail for your entire development cycle.
🆔 @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
📦 nvidia/nvcf
nvcf
Run heavy GPU workloads across multiple servers without managing the brutal infrastructure yourself. With nvcf, you get a self-managed platform that automatically routes your massive AI inference and batch jobs to wherever GPU power is actually free. Instead of manual scaling headaches, it acts like a smart traffic cop, balancing HTTP, gRPC, and streaming tasks from zero to max across mixed GPU clusters. You just deploy your code as a container, and it handles the rest. It is like having your own private cloud functions specifically tuned for heavy AI lifting, making massive scale feel incredibly simple.
📰 https://news.ycombinator.com/item?id=48772345
🆔 @hackernewsgithubprojects
nvcf
Run heavy GPU workloads across multiple servers without managing the brutal infrastructure yourself. With nvcf, you get a self-managed platform that automatically routes your massive AI inference and batch jobs to wherever GPU power is actually free. Instead of manual scaling headaches, it acts like a smart traffic cop, balancing HTTP, gRPC, and streaming tasks from zero to max across mixed GPU clusters. You just deploy your code as a container, and it handles the rest. It is like having your own private cloud functions specifically tuned for heavy AI lifting, making massive scale feel incredibly simple.
📰 https://news.ycombinator.com/item?id=48772345
🆔 @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
📦 alexvilelabah/bah-browser
Bah Browser
Operate the web using simple, everyday language while letting an intelligent assistant handle the clicking and typing for you. This open-source application loads websites inside a familiar tabbed interface and uses a clever decision loop to read the screen, scroll, and interact with elements using real, natural input events. It solves the friction of manual web navigation by translating your plain-text prompts into direct browser actions, making it incredibly easy to automate repetitive tasks or search for information. Best of all, it works entirely free right out of the box with zero setup, but also lets you connect your own cloud keys or run models completely offline. Give this smart...
🆔 @hackernewsgithubprojects
Bah Browser
Operate the web using simple, everyday language while letting an intelligent assistant handle the clicking and typing for you. This open-source application loads websites inside a familiar tabbed interface and uses a clever decision loop to read the screen, scroll, and interact with elements using real, natural input events. It solves the friction of manual web navigation by translating your plain-text prompts into direct browser actions, making it incredibly easy to automate repetitive tasks or search for information. Best of all, it works entirely free right out of the box with zero setup, but also lets you connect your own cloud keys or run models completely offline. Give this smart...
🆔 @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
📦 xmudeeplit/memsyco-bench
memsyco-bench
memsyco-bench is the evaluation toolkit that finally tests whether your personalized AI agents are just telling you what you want to hear. Instead of assuming more memory is always better, this benchmark measures if language models can handle tricky memory traps, like ignoring outdated preferences, overriding user bias with hard facts, or ignoring a favorite brand when a better option exists. By testing systems across fifteen hundred scenarios, it exposes when an AI prioritizes pleasing you over being correct. It is a fantastic tool for developers who want to build personalized agents that are genuinely helpful rather than just sycophantic yes-men.
🆔 @hackernewsgithubprojects
memsyco-bench
memsyco-bench is the evaluation toolkit that finally tests whether your personalized AI agents are just telling you what you want to hear. Instead of assuming more memory is always better, this benchmark measures if language models can handle tricky memory traps, like ignoring outdated preferences, overriding user bias with hard facts, or ignoring a favorite brand when a better option exists. By testing systems across fifteen hundred scenarios, it exposes when an AI prioritizes pleasing you over being correct. It is a fantastic tool for developers who want to build personalized agents that are genuinely helpful rather than just sycophantic yes-men.
🆔 @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
📦 desplega-ai/agent-swarm
Agent Swarm
Coordinate multiple AI agents to work together seamlessly on complex coding tasks, pull requests, and system debugging. agent-swarm acts as an orchestrator that lets you deploy cooperative teams of AI workers that connect directly to your GitHub, Slack, Jira, and development environments. Instead of relying on a single, isolated chatbot, this setup lets specialized agents pass tasks back and forth, search your codebase, write code in secure sandboxes, and even run automated testing pipelines. It is a game-changer for automating repetitive development chores because the agents share a unified memory system, meaning they actually learn and get smarter over time.
🆔 @hackernewsgithubprojects
Agent Swarm
Coordinate multiple AI agents to work together seamlessly on complex coding tasks, pull requests, and system debugging. agent-swarm acts as an orchestrator that lets you deploy cooperative teams of AI workers that connect directly to your GitHub, Slack, Jira, and development environments. Instead of relying on a single, isolated chatbot, this setup lets specialized agents pass tasks back and forth, search your codebase, write code in secure sandboxes, and even run automated testing pipelines. It is a game-changer for automating repetitive development chores because the agents share a unified memory system, meaning they actually learn and get smarter over time.
🆔 @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
📦 helloyanis/age-verification-bypass
Age Verification Bypass
A browser add-on weighing under ten kilobytes can completely skip mandatory identity checks on several popular platforms. The age-verification-bypass extension for Firefox acts as a privacy shield by intercepting the digital requests that trigger verification popups on supported websites. Instead of letting those trackers load, it instantly sends back a simulated signal confirming you are approved, letting you right through without ever uploading your sensitive ID documents. It protects your personal data from potential database leaks while keeping your browsing private. It is a fascinating proof of concept showing how easily web-based gating can be safely sidestepped.
📰 https://news.ycombinator.com/item?id=48772921
🆔 @hackernewsgithubprojects
Age Verification Bypass
A browser add-on weighing under ten kilobytes can completely skip mandatory identity checks on several popular platforms. The age-verification-bypass extension for Firefox acts as a privacy shield by intercepting the digital requests that trigger verification popups on supported websites. Instead of letting those trackers load, it instantly sends back a simulated signal confirming you are approved, letting you right through without ever uploading your sensitive ID documents. It protects your personal data from potential database leaks while keeping your browsing private. It is a fascinating proof of concept showing how easily web-based gating can be safely sidestepped.
📰 https://news.ycombinator.com/item?id=48772921
🆔 @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
📦 ntd4996/agentpet
agentpet
The desktop companion that turns your software development sessions into a virtual pet game, agentpet brings a playful twist to modern programming. Available for macOS and Windows, it monitors your running artificial intelligence coding assistants and translates their work into nourishment for a pixelated desktop companion. As your AI assistants burn through tokens and complete tasks, your pet earns experience points, levels up, and evolves through five distinct stages. It provides a helpful visual indicator of whether your automation is actively running or waiting for feedback, making your active workspaces much easier to manage at a glance.
🆔 @hackernewsgithubprojects
agentpet
The desktop companion that turns your software development sessions into a virtual pet game, agentpet brings a playful twist to modern programming. Available for macOS and Windows, it monitors your running artificial intelligence coding assistants and translates their work into nourishment for a pixelated desktop companion. As your AI assistants burn through tokens and complete tasks, your pet earns experience points, levels up, and evolves through five distinct stages. It provides a helpful visual indicator of whether your automation is actively running or waiting for feedback, making your active workspaces much easier to manage at a glance.
🆔 @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
📦 crafter-station/petdex
Petdex
Your coding agent can now have a living, breathing companion right on your desktop. Petdex is a clever community platform and toolset that lets you browse, install, and run animated pets that react to your AI programming assistants in real time. It serves as a public gallery for cute sprites, but the real magic is the companion app that floats on your screen and hooks directly into tools like Claude Code and Codex. You can install any pet with a quick command, test them out, and even submit your own custom creations. It is the perfect, slightly silly way to bring some life to those long, quiet coding sessions.
🆔 @hackernewsgithubprojects
Petdex
Your coding agent can now have a living, breathing companion right on your desktop. Petdex is a clever community platform and toolset that lets you browse, install, and run animated pets that react to your AI programming assistants in real time. It serves as a public gallery for cute sprites, but the real magic is the companion app that floats on your screen and hooks directly into tools like Claude Code and Codex. You can install any pet with a quick command, test them out, and even submit your own custom creations. It is the perfect, slightly silly way to bring some life to those long, quiet coding sessions.
🆔 @hackernewsgithubprojects
This media is not supported in your browser
VIEW IN TELEGRAM
📦 aqua5230/usage
Usage
Keep your Claude Code and Codex quotas pinned directly to your macOS menu bar without ever burning through your actual API limits. This clever utility reads your usage metrics passively from local log files already stored on your machine, requiring zero API calls and never touching your secure keychain. It displays color-coded percentages from green to red at a quick glance, warning you before you hit a surprise quota wall. You can click the menu bar to open breakdowns, view beautiful HTML reports, and even pass your previous progress directly to new AI sessions. It is the ultimate local-only dashboard for developers wanting to keep tabs on their token costs.
🆔 @hackernewsgithubprojects
Usage
Keep your Claude Code and Codex quotas pinned directly to your macOS menu bar without ever burning through your actual API limits. This clever utility reads your usage metrics passively from local log files already stored on your machine, requiring zero API calls and never touching your secure keychain. It displays color-coded percentages from green to red at a quick glance, warning you before you hit a surprise quota wall. You can click the menu bar to open breakdowns, view beautiful HTML reports, and even pass your previous progress directly to new AI sessions. It is the ultimate local-only dashboard for developers wanting to keep tabs on their token costs.
🆔 @hackernewsgithubprojects