GitHub热门项目 | Generation of diagrams like flowcharts or sequence diagrams from text in a similar manner as markdown | Stars: 88,583 | 36 stars today | 语言: TypeScript

GitHub热门项目 | The web framework for content-driven websites. ⭐️ Star to support our work! | Stars: 60,034 | 50 stars today | 语言: TypeScript

GitHub热门项目 | Learn Kubernetes by playing. Deploy pods, fix CrashLoopBackOff, type real kubectl commands: 3D browser game, no install needed. | Stars: 1,028 | 40 stars today | 语言: JavaScript

GitHub热门项目 | Extracted system prompts from Anthropic - Claude Fable 5, Opus 4.8, Claude Code, Claude Design. OpenAI - ChatGPT 5.5 Thinking, GPT 5.5 Instant, Codex. Google - Gemini 3.5 Flash, 3.1 Pro, Antigravity. xAI - Grok, Cursor, Copilot, VS Code, Perplexity, and more. Updated regularly. | Stars: 41,640 | 96 stars today | 语言: JavaScript

GitHub热门项目 | SIA is a Self Improving AI framework to autonomously improve the performance of any AI system (Model / Agent) on a benchmark task. | Stars: 1,047 | 177 stars today | 语言: Python

GitHub热门项目 | AI agents running research on single-GPU nanochat training automatically | Stars: 86,119 | 201 stars today | 语言: Python

GitHub热门项目 | Open Source AI Platform - AI Chat with advanced features that works with every LLM | Stars: 30,241 | 30 stars today | 语言: Python

GitHub热门项目 | QuantMind is an intelligent knowledge extraction and retrieval framework for quantitative finance. | Stars: 1,071 | 336 stars today | 语言: Python

GitHub热门项目 | A tool for creating and running Linux containers using lightweight virtual machines on a Mac. It is written in Swift, and optimized for Apple silicon. | Stars: 30,953 | 2,419 stars today | 语言: Swift

GitHub热门项目 | Security scanner for AI agent skills. Detect vulnerabilities, malicious patterns, and security risks. | Stars: 2,305 | 308 stars today | 语言: Python

GitHub热门项目 | Fast, secure, efficient backup program | Stars: 34,020 | 33 stars today | 语言: Go

I deployed a Slack bot app built on the Claude Agent SDK to Railway, and immediately hit a string of landmines around the SDK itself. Every one of them was the "the logs don't tell you what's wrong" kind, and the second one in particular ate a lot of my time. Since other people are likely to get stuck in the same spots, I'm writing it down. This is aimed at junior-to-mid-level devs using @anthropic-ai/claude-agent-sdk ( query() ) in Node.js. TL;DR Gotcha 1 : In a root container, bypassPermissions isn't allowed, and the child process dies with code 1 . Worse, stderr is swallowed, so you can't see why. Gotcha 2 : stdio MCP servers don't wait for connection by default, so on turn 1 the tool list is empty — and the model "acts out" tool calls and fabricates the results. Gotcha 3 : haiku shows up in your API logs, but that's not the model degrading — it's by design. It's used for internal chores. Gotcha 1: bypassPermissions doesn't work in a root container What happened Code that ran fine locally started dying with code 1 the moment I deployed it to Railway — the agent did nothing and just exited. The entire error message was essentially this: Error: Claude Code process exited with code 1 That tells you nothing. The only stack trace was from my app; what the child process (the claude binary) actually said before dying was a complete black box. The cause query() spawns a claude binary internally. That binary refuses --dangerously-skip-permissions (which the SDK calls permissionMode: "bypassPermissions" ) when running as root or under sudo . It's a safety measure — skipping all permission checks as root is far too dangerous. Railway, like many container environments, runs as root by default, so if you've set bypassPermissions you will always hit this. You can't catch it locally if you're running as a normal user. Why there are no logs This is the nasty part. Unless you pass an options.stderr callback, the SDK discards the child process's stderr with "ignore" . In other wor

The Gem necklace can track your UV exposure.

Lara get your gun(s).

Cash App's AT&T-based MVNO will offer an unlimited 5G data plan for $40 per month including taxes and fees. The new mobile service is powered by Gigs, the same firm behind the Klarna mobile service that launched last year with the same pricing and is "rolling out to select users, with broader availability planned in […]

A free model that runs 4x faster on your own GPU — and two more shifts for builders Three things landed for builders at once: a free open model that generates text far faster, a more autonomous Codex, and Anthropic owning up to a model that was quietly holding back. Two of them you can act on right now. Here's the 2-minute video version if you want the quick pass first: 1. Google shipped DiffusionGemma — a free open model that runs 4x faster Google released DiffusionGemma , an open-weights model that uses text diffusion instead of standard autoregressive decoding. Instead of generating one token at a time, it generates whole blocks in parallel. It writes blocks of 256 tokens at once , for up to 4x faster generation on a dedicated GPU. It hits 700+ tokens per second on a single RTX 5090 , and fits in 18GB of VRAM quantized — inside consumer GPU limits. It's a 26B Mixture-of-Experts (only 3.8B parameters active), ships under Apache 2.0 , and runs natively in vLLM . The tradeoff Google states openly: output quality is lower than standard Gemma 4, so it's a speed play, not a quality play. Why it matters: this is a fast, free, local draft model you can run on your own hardware. Use it for low-latency drafts and agent loops, then route the hard calls to a stronger model. No inference bill for the cheap 80%. 2. OpenAI gave Codex web search and autonomous goals OpenAI shipped a major Codex update that pushes it further toward an autonomous agent. Code mode can now call web search directly , even from nested JavaScript tool calls — so it can look up current API docs mid-implementation. Goal mode is generally available across the Codex app, the IDE extension, and the CLI. Appshots (macOS) attach an app window to a Codex thread with a hotkey, and MCP tool schemas now preserve oneOf / allOf for richer connectors. Why it matters: Codex can research and chase a goal on its own across every surface. Still — hand it a clear, scoped goal in a branch. Full hand-offs go sideways witho

The general shape of the problem is that every public LLM benchmark is on a saturation clock that runs from the moment of its publication to the moment a model's training corpus has eaten it. The clock has been running, on the visible benchmarks of the last five years, for somewhere between twelve and thirty months before each one is no longer useful for differentiating frontier models. The benchmarks are not failing. They are doing exactly what they were designed to do, in the order they were designed to do it, and the field has been running through them faster than the people designing them anticipated. I want to put numbers on the saturation pattern, walk through what the contamination evidence actually says, and then sit with the question of what an honest benchmark would have to look like in 2026 — because the "private held-out eval" answer that the labs are converging on has economics that are worth examining carefully before any of us salute it as the solution. The saturation timeline, with numbers HumanEval (Chen et al., OpenAI, July 2021). 164 hand-written Python problems. The benchmark was published with Codex at 28.8% pass@1; the underlying GPT-3 base model scored 0%. GPT-4 (March 2023) hit 67% in the original Technical Report. By late 2024, OpenAI's o1-preview and o1-mini both reached 96.3% pass@1 ; Claude 3.5 Sonnet sat at 93.7%. The benchmark is saturated in the operational sense — the relative spread across the top ten models is around 10 percentage points, which is too small a gap to differentiate them on, and most of the new models arrive within a percentage point or two of the ceiling. The successor variants (HumanEval+ from EvalPlus, with augmented test cases) are the field's response. Lifespan from publication to operational saturation: about 36 months. MMLU (Hendrycks et al., September 2020). 57 subjects, ~14,000 multiple-choice questions, taken from publicly-available test prep and academic sources. The problem with MMLU is not that it's satura

Computer-based assessments have a quiet accessibility problem. Most platforms assume the user can read text on a screen, click through options, and type their responses. For visually impaired students — particularly in India — this assumption effectively shuts them out entirely. I wanted to fix that. Not with a workaround, but with an experience that feels native to voice from the ground up. The Problem Screen readers exist, but they're clunky, require separate setup, and often mispronounce Indian names, words, and sentence structures in ways that feel jarring and unnatural. The experience breaks down fast. What visually impaired Indian students actually need is a system that speaks to them the way people around them speak — in a familiar accent, at a natural pace, without sounding like a robot reading out a manual. That's what led me to Sarvam AI. Why Sarvam I had tried other TTS APIs before. They worked, technically. But there was always something off — a flatness to the voice, a slightly Western lilt, a pronunciation of common Hindi-origin words that made it obvious the model had never really heard Indian English spoken naturally. Sarvam's TTS was different. The first time I ran a test question through it, the output sounded like something a real person would say. The accent was warm and familiar — the kind of voice an Indian student would actually trust and follow without friction. That moment changed how I thought about the project. This wasn't just a convenience feature anymore. It was the core of the experience. What I Built The platform is a full-stack web app built with React and Tailwind on the frontend, Express.js on the backend, and PostgreSQL for storing user data and scores. The interaction model is deliberately simple. A single click anywhere on the screen triggers Sarvam TTS to read the current question aloud. A double click starts listening and transcribes the user's spoken answer using Sarvam STT. No keyboard required. No mouse precision required.

Database Migration Strategies for Next.js and Supabase Production Apps You've built your Next.js app with Supabase. It works perfectly in development. Now you need to deploy to production and realize: how do I safely change the database schema without breaking everything? Database migrations are how you version control your schema and deploy changes safely. This guide covers everything from basic migrations to zero-downtime production deployments. Prerequisites Supabase project (local and production) Supabase CLI installed Next.js application Git for version control Understanding Migrations A migration is a SQL file that changes your database schema: -- supabase/migrations/20260314120000_add_posts_table.sql CREATE TABLE posts ( id UUID PRIMARY KEY DEFAULT uuid_generate_v4 (), title TEXT NOT NULL , content TEXT , user_id UUID REFERENCES auth . users ( id ), created_at TIMESTAMPTZ DEFAULT NOW () ); ALTER TABLE posts ENABLE ROW LEVEL SECURITY ; CREATE POLICY "Users can view own posts" ON posts FOR SELECT USING ( auth . uid () = user_id ); Migrations are: Versioned: Timestamped filenames ensure order Tracked: Supabase knows which migrations have run Repeatable: Same migrations produce same result Reversible: You can write rollback logic Setting Up Migrations Initialize Supabase locally: npx supabase init This creates: supabase/ config.toml seed.sql migrations/ Link to your remote project: npx supabase link --project-ref your-project-ref Creating Your First Migration Create a new migration: npx supabase migration new create_posts_table This creates: supabase / migrations / 20260314120000 _create_posts_table . sql Write your schema changes: -- Create posts table CREATE TABLE posts ( id UUID PRIMARY KEY DEFAULT uuid_generate_v4 (), title TEXT NOT NULL , content TEXT NOT NULL , slug TEXT UNIQUE NOT NULL , user_id UUID REFERENCES auth . users ( id ) ON DELETE CASCADE , published BOOLEAN DEFAULT FALSE , created_at TIMESTAMPTZ DEFAULT NOW (), updated_at TIMESTAMPTZ DEFAULT NOW

7 Things I Wish I Knew Before Scaling Next.js + Supabase to 100K Users Six months ago, we launched our SaaS with Next.js and Supabase. The stack was perfect for our MVP: fast development, great DX, and it just worked. Then we hit 10K users. Then 50K. Then 100K. Everything that worked beautifully at small scale started breaking. Database queries that took 50ms now took 5 seconds. Our Supabase bill went from $25/month to $800/month. Users complained about slow page loads. Here's what I wish someone had told me before we started. 1. RLS Policies Are Not Optional (Even in Development) We skipped RLS in development. "We'll add it before launch," we said. Launch day came. We enabled RLS on all tables. The app broke in 47 different places. Queries that worked suddenly returned empty arrays. Inserts failed with permission errors. We spent 12 hours fixing RLS policies while users waited. What I'd do differently: Enable RLS from day one. Write policies as you create tables: CREATE TABLE posts ( id UUID PRIMARY KEY DEFAULT uuid_generate_v4 (), title TEXT NOT NULL , user_id UUID REFERENCES auth . users ( id ) ); -- Enable RLS immediately ALTER TABLE posts ENABLE ROW LEVEL SECURITY ; -- Write policies now, not later CREATE POLICY "Users can view own posts" ON posts FOR SELECT USING ( auth . uid () = user_id ); Test with RLS enabled. If it works in development, it'll work in production. 2. Database Indexes Are Not Premature Optimization "We'll add indexes when we need them." We needed them on day 3. Our posts feed query went from 50ms to 8 seconds as we hit 10K posts. Users complained. We scrambled to add indexes during peak traffic. The query: const { data } = await supabase . from ( ' posts ' ) . select ( ' *, profiles(*) ' ) . eq ( ' published ' , true ) . order ( ' created_at ' , { ascending : false }) . limit ( 20 ) The fix: CREATE INDEX posts_published_created_at_idx ON posts ( published , created_at DESC ) WHERE published = true ; Query time dropped to 12ms. What I'd do di