📦 smithersai/smithers

Smithers: Your Codebase's New Copilot

Smithers is the workflow framework that finally makes AI coding agents actually useful for your specific codebase. It lets you define exactly how those agents should plan, run, and review changes using simple TypeScript files right next to your code. Instead of just chatting with a bot, you build durable, reliable workflows that automate the heavy lifting. It is basically a way to teach your AI helpers to work smarter, faster, and cheaper by giving them a clear map of your project. If you are tired of generic AI answers, this is the tool that gives them context and structure.

🆔 @hackernewsgithubprojects

📦 station-sciences/bot-crossing

Bot Crossing

Bot Crossing turns your scattered coding agent sessions into a tiny, living space colony. Every active thread becomes an astronaut that walks out of the ship, claims a plot, and builds a structure. The map stays fixed so you can learn the layout, and the astronauts only show badges when they actually need you, which cuts through the noise of silent background tasks. It reads local files to track status, so nothing uploads and no accounts are required. If an agent is stuck, it holds up a question mark until you click it and jump back into the app.

🆔 @hackernewsgithubprojects

📦 agentdesktop-dev/agentdesktop

Agentdesktop: Control AI Tools

Agentdesktop is the open-source layer that finally gives companies control over every AI tool on their employees' computers. It solves the messy problem of tracking which coding assistants are installed, what settings they use, and how they connect to model servers, all without stealing your private code. The standout feature is its ability to manage settings natively for tools like Claude Code and Cursor, meaning it can safely apply security rules directly into each app's own configuration file. This works on Windows, macOS, and Linux, letting IT teams enforce safety standards without forcing developers to switch tools.

📰 https://news.ycombinator.com/item?id=49604626

🆔 @hackernewsgithubprojects

📦 agricidaniel/youtubepro

YouTube Pro: Local-First AI Research

YouTube Pro runs entirely on your own machine, which means your API keys and project data never leave your computer. It connects directly to the YouTube Data API to pull real performance metrics from up to fifty videos, then feeds that exact snapshot into Gemini for analysis. The surprising part is that every AI insight is tied to specific source video IDs, so you can verify where every claim actually comes from instead of trusting a generic summary. This workflow covers the whole process, from finding data-backed ideas to writing the script and generating the thumbnail.

🆔 @hackernewsgithubprojects

📦 codejunkie99/agentic-stack-desktop

Agentic Stack: Give Your Coding Agents a Shared Brain

Agentic Stack solves the biggest headache of using multiple AI coding tools: they all forget what the other ones learned. This native macOS app acts as a single shared memory hub for Claude Code, Codex, OpenCode, and Cursor. Instead of starting from scratch every time you switch tools, it builds one local knowledge graph from your past conversations. That means you can ask your current agent to recall what you discussed weeks ago in a completely different editor. Your data never leaves your machine, and you stay in full control. It turns your scattered chats into one continuous, searchable brain that actually remembers your project.

🆔 @hackernewsgithubprojects

📦 atomburstofficial/geiger

Geiger: Know Your AI Agents

A single command can now reveal every artificial intelligence tool quietly installed on your computer. Geiger acts as a safety detector for digital assistants, scanning your system to find hidden programs that have access to your files and private keys. It does not just list these tools; it warns you exactly what each one is capable of doing, such as running code or reaching the internet. This simple inventory helps you understand your digital footprint before something goes wrong. Knowing what is running on your machine is the first step toward keeping your data secure. Use this tool to take control of your digital environment today.

📰 https://news.ycombinator.com/item?id=49627646

🆔 @hackernewsgithubprojects

📦 galaxy-io/filament

Filament: The Self-Healing Data Pipeline

Filament moves data from apps to databases without losing a single record. It copies records in batches, checks that every batch landed correctly, and remembers exactly where it left off. If the system crashes, it just picks up right where it stopped, so no data disappears and nothing gets written twice. You can connect almost anything to anything else, from Slack to Stripe to Postgres. It handles the tricky parts like pausing, resuming, and checking that your data is actually there. You get a simple tool that does the heavy lifting of moving data around without you having to build your own complex logic.

📰 https://news.ycombinator.com/item?id=49611112

🆔 @hackernewsgithubprojects

📦 deepseek-ai/deepselect

DeepSelect: 20x Faster TopK for DeepSeek

DeepSelect makes picking the most important data points from a massive list up to twenty times faster than standard tools. It is the engine behind DeepSeek’s latest models, helping them decide which words to focus on and which to ignore in an instant. Think of it as a super-fast filter that sorts through thousands of options without breaking a sweat, turning a slow, heavy calculation into a quick, efficient scan. By optimizing this specific task, it helps these large AI models run smoother and faster. If you are building with next-gen language models, knowing that this kind of low-level speed boost exists is the real difference maker.

🆔 @hackernewsgithubprojects

📦 deepseek-ai/deepseek-recipe

What Is DeepSeek Recipe?

DeepSeek Recipe is the translation layer that finally stops your apps from speaking different languages. You know that annoying moment when your frontend sends one kind of message, but the AI model expects a completely different format? That’s where this library steps in. It takes those messy, varied API requests and turns them into the exact prompt structure DeepSeek models actually understand. Think of it as a universal adapter for your AI setup. Whether you are building a quick script or a complex server, it handles the heavy lifting of formatting so you can focus on the logic, not the syntax.

🆔 @hackernewsgithubprojects

📦 kevinzakka/mjbatch

mjbatch

A Go1 robot learning to walk on a five-year-old laptop takes less than a minute when you use mjbatch. This Python library lets you run thousands of MuJoCo physics simulations in parallel using your computer's standard processor, without needing any expensive graphics hardware. It handles the heavy math on the background so you can focus on your code. The magic is that you treat all those robots like one giant spreadsheet. You write to a single array, and every simulation updates instantly. It is perfect for training controllers or testing designs quickly.

🆔 @hackernewsgithubprojects

📦 ktwu01/benchmark-radar

Benchmark Radar: The AI Test Tracker

Benchmark Radar is the living database that tracks every new AI benchmark as it appears. The creator built this tool because finding relevant tests was becoming a nightmare. It continuously scans thirty-seven sources to collect over eleven thousand records, so you never miss a new evaluation method. The most fascinating part is seeing how model scores change over time. You can watch a popular test become saturated as AI models improve. This visual history shows exactly when a benchmark stops being challenging. It is a free, open source way to understand the state of AI research without digging through thousands of papers yourself.

🆔 @hackernewsgithubprojects

📦 r44vc0rp/opensend

OpenSend: Self-Hosted Email Control

Take back full control of your email by running your own sending layer on top of Amazon Simple Email Service. OpenSend is a self-hosted tool that handles both transactional and marketing emails, giving you a clear dashboard to manage campaigns, track deliveries, and manage your audience without relying on a third-party service. It solves the problem of vendor lock-in and gives you complete visibility into your email infrastructure. You get a single API and dashboard that works with your own AWS account, making it easy to see exactly who opened your messages and where they went.

📰 https://news.ycombinator.com/item?id=49638274

🆔 @hackernewsgithubprojects

📦 pixelpaw-labs/codex-trace

Codex Trace: See Every Move Your AI Coding Agent Makes

Codex Trace turns the invisible memory of your AI coding assistant into a clear, readable timeline. When you use the Codex command line tool, every conversation, command, and code change gets saved as a dense, hard-to-read data file. This application takes those messy files and transforms them into a clean, visual interface where you can watch your AI work in real time. You can see exactly which tools it used, how many resources it consumed, and even how it collaborated with other AI workers on complex tasks. It is the missing window into the black box of AI coding, letting you understand the thought process behind every line of code.

📰 https://news.ycombinator.com/item?id=47909579

🆔 @hackernewsgithubprojects

📦 projectdxai/continuous-record-llm-trading-agents

continuous record llm trading agents

Continuous Record LLM Trading Agents is the research record that exposes what AI traders actually do with real money. This repository holds the data for a six-month study of over three thousand agents trading Ethereum, revealing that these bots mostly ignore risk settings and let profits slide away. The most surprising find? The simple interface details shown to the AI, like a leaderboard, drove nearly half of all trades, proving that how information is presented matters more than the model itself. It is a sobering look at how these systems fail in the real world, giving developers a clear map of where to fix agent control before deploying their own.

🆔 @hackernewsgithubprojects

📦 jasonxu114514/opencode2api

opencode2api: Your All-in-One AI Gateway

opencode2api is the Go-based proxy that makes any AI client work with OpenCode Zen, no matter the interface. If you want to use OpenAI or Anthropic tools but prefer the Zen ecosystem, this tool is your bridge. It automatically converts your requests so you do not have to write extra code. It also handles multiple API keys and proxy connections, letting it fail over to a backup if one connection drops. This keeps your AI assistant online and responsive, even when the network is unstable. You get a standard API endpoint that speaks everyone's language, so your favorite apps just work.

🆔 @hackernewsgithubprojects

📦 yudaprasetya007/routevscode

Routevscode: Switch AI Models Instantly

Routevscode is the Visual Studio Code extension that swaps your AI model without closing your editor. Normally, changing your AI assistant requires restarting your code editor or editing complex settings files, which breaks your workflow. This tool fixes that by acting as a live bridge, allowing you to click a button in a web dashboard to instantly switch between models like GPT or Claude while you keep typing. It removes the friction of reloading, so you can test different AI brains on your code in real-time without losing your train of thought. If you code with AI, this simple tool keeps your flow uninterrupted and your options flexible.

🆔 @hackernewsgithubprojects

📦 donvito/local-evals

Local Evals: Test AI Models On Your Computer

Run your own tests to check if an AI model is actually doing what you want, without ever sending your data to the cloud. Local Evals is a desktop app that takes a set of questions, feeds them to your chosen model, and scores the answers against a list of correct results. It lets you see exactly where a model succeeds and where it fails, comparing different versions side by side in a clear dashboard. This is perfect for developers who need to verify that their AI behaves correctly before deploying it, keeping all their sensitive data safe on their own machine.

🆔 @hackernewsgithubprojects

📦 vincentwei1021/anything2explainer

Anything to Explainer: The AI Video Factory

You can now turn any random topic into a fully animated explainer video with a real voiceover, all generated by AI coding agents. This project is called Anything to Explainer. It is not a video generator; it is a set of instructions for AI programmers like Claude Code. You give it a subject, and it handles the research, writes the script, and records a voice. Then, it splits the video into separate shots and assigns different AI agents to code each animation in parallel. It uses a tool called Remotion to draw every single frame from code, ensuring no two videos look the same.

🆔 @hackernewsgithubprojects

📦 miqdadbadjuber/anti-slop

Anti Slop: The Filter for AI Design

Your AI coding agent is probably handing you designs that look like every other AI app, complete with generic blue gradients and empty buzzwords. Anti Slop is a rulebook that stops that from happening. It acts as a filter, checking every visual choice to ensure it actually serves a purpose rather than just looking like a safe default. It doesn’t tell your agent what colors to pick, but it demands a real reason for every design decision. The result is software that feels crafted by a human designer, not generated by a machine.

🆔 @hackernewsgithubprojects

📦 chengyi-ai/native-subtitle-quote-image

Turn Video Clips Into Shareable Quote Images

Turn real video moments into crisp, vertical images ready for social sharing. This project grabs the exact frame where a subtitle appears and stitches it into a compact, portrait-friendly picture. It solves the hassle of manually finding and cropping perfect quotes by automating the extraction process. The standout feature is its strict honesty: it clearly distinguishes between text originally baked into the video and text added later, so you never risk misrepresenting the source material. It’s a clever way to create authentic visual highlights without messy manual editing. If you share video content, this tool makes creating accurate quote cards simple and reliable.

🆔 @hackernewsgithubprojects

📦 jinzijian/evotrace

EvoTrace: Turn Your Coding History into Training Data

Your messy chat logs with AI coding assistants are secretly valuable data that can be turned into rigorous, verified training assets for future models. EvoTrace is a local tool that imports your existing Claude Code and Codex history to find the best problem-solving sessions and compile them into reproducible coding tasks and independent verifiers. This solves the critical gap between raw transcripts and usable post-training data by ensuring every generated task is validated in a secure sandbox environment. It lets you evaluate agent performance today and generate high-quality reinforcement learning data for tomorrow.

🆔 @hackernewsgithubprojects