Neural Forge

@GithubProjects Thanks so much Now i can spectate models's pricing here

Models.dev is an open-source database of AI model specs, pricing, and capabilities, maintained through community contributions. - Data accessible via a JSON API at models.dev/api.json - Provider logos available as SVG files through a simple endpoint - Model definitions stored as TOML files organized by provider - Uses Model IDs compatible with the AI SDK for lookups

@NVIDIAAI Same me

We 💚 open source

@perplexity_ai @PPLXDevs So amazing

Introducing Search as Code, our new search architecture for AI agents. It writes Python that calls our search stack directly, instead of looping through function calls one at a time. Available in the Perplexity Agent API, and now default in Computer. research.perplexity.ai/articles/rethi…

@CultureCrave Asking Meta AI to get OTP from another account sounds good 🤣🤣

Hackers say they hijacked tons of high-profile Instagram accounts by tricking Meta AI support chatbot into granting access • They simply asked the AI to change the email associated to the account after using a VPN to spoof the page's location • Accounts associated with Obama and the U.S. Government were included in the hack • Meta claims the issue has been resolved

@GithubProjects Love it so much Any benchmark versus Remotion ??

HyperFrames is an open-source framework that turns HTML, CSS, and animations into deterministic MP4 videos, built for AI coding agents and automated pipelines. - Define videos as HTML with data attributes for timing and tracks - Works with GSAP, CSS, Lottie, Three.js, and other animation libraries - CLI for local preview with live reload and MP4 rendering - Agent skills for planning, writing, linting, previewing, and rendering videos

@birdabo @cursor_ai Wow grok build + composer sounds overpowered

Composer 2.5 from @cursor_ai is now available inside Grok Build. if you have X premium+ or SuperGrok subscriptions you can get instant access to it. x.com/xai/status/206…

@Polymarket Google raising ??

NEW: Google reportedly plans to raise $80,000,000,000.00 to fund its AI spending push.

@jxnlco @ah20im Bro shipped Codex for python 😭

wow we just shipped codex app server for python shoutouts to @ah20im

@daniel_mac8 Wow Codex is now better than ClaudeCode

Killer new Codex feature that went unannounced: Codex can now coordinate threads for local projects/worktrees. Includes separate background threads. Transforms Codex into a meta-agent that can orchestrate its own workspace.

@nicdunz Thats incredible he created an agent himself br

pewdiepie just released his own vibecoded ai slop

@nicdunz Pewds building an agent So wild

pewdiepie on his local ai setup: "you can also create your own characters to chat with, my favorite is goblino. what a guy"

@MyWestLord Hermes ships anything we want ☠️☠️

Hermes + AI agent + workspace + 1 click. $0 tools. Free plugin. Your Hermes AI agent just got a chat, a terminal, memory, and a skills layer. All from 1 free plugin. It’s called Hermes Workspace. And almost nobody is using it yet. Here’s what it actually does: A standard Hermes agent runs 1 task at a time. It forgets context the moment the session ends. You manage it across 4 different windows. Hermes Workspace collapses all of that into 1 dashboard. → Chat window: talk to your agent in real time → Terminal: watch it execute live, catch errors instantly → Memory: it remembers what it built last week → Skills: pre-loaded behaviors it pulls automatically Before: 4 tabs, lost context, start over every session. After: 1 screen. Persistent. 10x faster iteration. The practical difference is real. An agent without memory rewrites from scratch every time. An agent with Workspace memory picks up where it stopped, applies the skill it already learned, and skips the 20-minute setup loop. That’s not a marginal upgrade. That’s a different tool. And the cost is $0. Free plugin. One install. If you’re already running Hermes agents you’re leaving performance on the table without this. Install it. Open the dashboard. Your agent just got smarter than it was this morning.

@JulianGoldieSEO Ran hermes update 3 times today

Hermes Agent just got a free update. And one feature turns it from “one AI helper” into a full AI team. Here’s what to do first: → Run Hermes update. → Turn on push notifications. → Build one skill bundle for your most-used workflow. → Move your API keys into Bitwarden Secrets Manager. → Test the new instant search. → Try the new multi-agent swarm on a small task. The big win? Hermes can now split one big task into smaller jobs and assign them to multiple agents at the same time.

@HermesAgentTips Wow, can you share detailed steps ??

my hermes agent queued my commute playlist, set the volume, and transferred to my kitchen speaker while I was asleep no shortcuts. no automations app. just a cron job and a single prompt it's been running every morning for weeks

👉 Start printing high-performing short videos here: github.com/harry0703/Mone…

Whether you're building a faceless side hustle, scaling a personal brand, or automating client assets, this is the ultimate content leverage tool for 2026. Stop wasting time on manual timelines and let AI print the content. I've placed the direct GitHub repository link in the first reply below! 👇

Stop spending 4 hours editing TikToks. Use this 1-click AI "Money Printer" instead. Faceless YouTube Shorts and TikTok accounts are absolute goldmines. But writing scripts, finding royalty-free clips, generating voiceovers, and aligning subtitles takes hours. If you don't scale, you burn out. Enter MoneyPrinterTurbo—the open-source AI tool with 76k+ GitHub stars that automates the entire video-creation pipeline from a single keyword: 🧵👇