Guac Chat: Unleashing Your Voice in a Censorship-Free Worldpen_spark
Ever feel like your voice is getting drowned out on social media? Tired of platforms dictating what you can and can't say? We hear you.
The next evolution of Hermes Agent is here!
Introducing Hermes Desktop: everything you love about Hermes, now native on your machine.
First demoed in Jensen's GTC keynote, it's now in public preview.
A DEVELOPER TAUGHT GIT WITH A BOX OF CHILDREN'S TOYS AND ENGINEERS WITH TEN YEARS IN SAY IT'S THE FIRST TIME THE THING EVER ACTUALLY MADE SENSE
90 minutes, one table, a pile of Tinkertoys. No wall of jargon -- he builds a real Git repo out of plastic rods right in front of you.
-> The moment he snaps the first pieces together, Git stops being scary command-line magic and becomes what it really is: a chain of tiny objects pointing at each other.
Branches, merges, rebase, the staging area -- every concept that's ever burned you at 2am -- he rebuilds with toys until a four year old could follow. He calls Git a two-trick pony. After this you'll see exactly why.
Memorizing commands was never the skill -> holding the graph in your head is. And with an AI agent now committing and rebasing on your machine all day, that mental model is the only thing between you and a history you can't read.
Scroll the comments and you'll see the same thing over and over: this is the talk that finally made Git click and made people the one their whole team comes to when it breaks.
Bookmark & watch it today. It's the 1.5 hours that pays you back for the rest of your career ↓
Your GLB is probably way too heavy.
AI models, scans, exports, they often land at 5–60MB+ with millions of tris. Brutal for games, apps, and real-time 3D.
I built GLB Shrink to help the dev community fix this:
drop → preview before/after → download
Real test: 58 MB → 869 KB (−99%)
Draco + WebP. No Blender. No CLI.
Free & open source 🎮
https://t.co/fe3MqDbfNK
#gamedev #indiegame
Someone just dropped a GitHub repo that basically breaks the “paywall” around Claude Code 👀
And no, it’s not a hack — it’s smarter than that.
It routes your Claude Code requests through multiple free-tier providers like DeepSeek, Kimi, and others… so you’re not locked into a single paid model.
Setup takes like 5 minutes. That’s it.
And somehow it’s already being used by 20,000+ devs.
No subscriptions. No vendor lock-in. Just plug, configure, and run.
Feels less like a tool… more like someone quietly removed the toll gate from the highway.
PREDICTION MARKET RESEARCH JUST GOT KILLED BY ONE .MD FILE.
The .md file in the video plugs any AI agent into 1,800 live data sources -> Polymarket orderbooks, satellite imagery, vessel tracking, NOAA weather, SEC filings, sports lines, and the top 100 KOL wallets.
It's @preftrade.
No APIs, no scraping, no signup and no card.
An agent with this installed doesn't ask "What's the price".
It pulls the orderbook depth on Polymarket, cross-references vessel positions in the Strait of Hormuz, scans the latest SEC filings on the names mentioned, and watches what the top 100 KOL wallets did in the last 4 hours.
Before it makes a single call.
The numbers are insane:
> $0 in API fees.
> $0 in data subscriptions.
> 670+ capabilities behind a single endpoint.
Every datapoint with full provenance back to the source.
The mechanism is wild too: It's called Preference.
An MCP server that gives any AI agent structured access to prediction markets -> Polymarket, Kalshi, Hyperliquid, dFlow AND the real-world signals that price them.
Your agent asks one question, gets the full picture before it acts.
It goes way past Polymarket: Smart-money mirroring on the top 100 wallets in real time.
Cross-venue arb scanners and event-driven agents that watch tanker traffic in the Strait of Hormuz and trade oil-linked markets.
Backtesting pipelines over historical data plus the world signals that moved each market.
The model was never the bottleneck. The data was.
One agent, one .md file and Live world data on tap.
-> https://t.co/ljPv4Et7sr
Retail still has 12 CoinGecko tabs open.
Agents already have the orderbook.
Full info and guide at https://t.co/jwRPxReFrs.
Don't forget to save.
Casually rendering ~a hundred million triangles, in the browser.
All thanks to @sea3dformat's cool Nanite-style renderer for @threejs.
I've added GLB-to-meshlet and PBR rendering to it, very exciting to see where this is going!
Amazon Ring died on May 22, 2026.
It just doesn't know yet.
One dad in Nashville, Tennessee built a free MIT-licensed app that watches your driveway, your porch, your baby monitor, your garage.
No cloud. No subscription. No cop ever gets the footage.
32,057 stars. 3,103 forks. Pushed today.
Here is the wildest part:
You: "How much is Ring Protect Pro?"
Ring: "$19.99 a month. $199.99 a year. Per house."
You: "How much is Google Home Premium Advanced?"
Google: "$20 a month. $200 a year. Per house."
You: "What do I get?"
Both: "We store your footage in our cloud. Ring already paid the FTC $5.8 million in 2023 for letting employees and contractors watch your videos without your consent. Google just raised Nest prices again in 2025."
You: "What does Frigate cost?"
Blake Blackshear: "Nothing. It runs on the Raspberry Pi already on your shelf. The footage never leaves your house. I have a day job."
Ring sells the camera. Then sells your fear back to you, monthly, forever.
Frigate sells nothing. Because Blake isn't selling.
He's a dad with 1,267 followers who got tired of Amazon owning his front door.
100% Opensource.
100% Local.
100% Yours.
The smart camera industry made one bad assumption.
That you'd keep paying rent on a camera you already bought.
That assumption just died in Nashville.
We are investigating unauthorized access to GitHub’s internal repositories. While we currently have no evidence of impact to customer information stored outside of GitHub’s internal repositories (such as our customers’ enterprises, organizations, and repositories), we are closely monitoring our infrastructure for follow-on activity.
Microsoft has released a 4B parameter model that turns any image into a 3D asset in 3 seconds.
It uses a new geometry format called O-Voxel that converts to a textured mesh in under 100ms on CUDA.
Outputs GLB files with full PBR textures, ready for Blender, Unity, and Unreal.
100% Open Source.
BREAKING: Someone open sourced a stealth Chromium browser that passes every single bot detection test on the internet.
It's called CloakBrowser. 13.4K GitHub stars in days.
→ Not a wrapper. The actual Chromium source code is modified at the C++ level.
→ Canvas, WebGL, AudioContext, Navigator, CDP leaks: all patched before compilation.
→ Drop-in Playwright replacement. Swap one import. Your scripts just work.
→ Passes CreepJS, BotD, Fingerprint.js, Cloudflare Turnstile, DataDome.
→ Zero CAPTCHAs. Zero blocks. Zero detection from any major bot protection service.
Anti-detect browser companies charge $100+/month for JavaScript overrides on a leaky browser.
This does it at the source level. For free.
8,600+ stars gained in one week. 100% Open Source.
Vapi charges $0.05/minute per call.
Retell charges $0.07/minute per call.
A 10-person sales team running 8 hours of AI calls a day pays Vapi $1,200/month. $14,400/year.
Someone built the open source alternative to both.
It's called Dograh. 1,516 stars on GitHub.
You open the drag-and-drop workflow builder. You name your bot. You describe the use case in a sentence. You have a working voice agent in under 2 minutes. No API contracts. No per-minute billing. No vendor lock-in.
Here's what it does:
→ Drag-and-drop workflow builder for inbound and outbound voice agents. No code required.
→ Bring your own LLM. OpenAI, Anthropic, or any provider you already use.
→ Bring your own STT. Swap speech-to-text engines without rebuilding your agent.
→ Bring your own TTS. Full control over voice, latency, and cost.
→ Outbound calling campaigns. Dial lists, lead qualification, follow-ups.
→ Inbound call handling. Receptionists, support bots, appointment schedulers.
→ WebRTC and VoIP support. Real phone calls and browser-based voice.
→ Built on Pipecat and FastAPI. Production-grade Python backend.
→ Next.js frontend. Runs entirely in your browser. No desktop app needed.
→ One Docker command to self-host everything. Running in under 60 seconds.
→ Full source-level customization. Every line of code is yours to modify.
→ Data residency on your own infrastructure. No call audio leaves your server.
Here's the wildest part:
There is no Dograh cloud you are forced to use. There is no per-minute meter running on someone else's servers. There is no closed-source black box deciding what your voice agent can and cannot do.
Vapi is SaaS only. Retell is SaaS only. Both are proprietary. Neither lets you see the code. Neither lets you change the code. Neither lets you own the infrastructure.
Dograh can never lock you out. Because the code is sitting on your own machine.
Vapi: $0.05/minute. A 10-person team at 8 hours/day of calls pays $14,400/year.
Retell: $0.07/minute. Same team. Same usage. $20,160/year.
Dograh: $0. Unlimited agents. Unlimited calls. Your hardware. Your data. Forever.
344 forks. Built in Python. Maintained by YC alumni and exit founders.
BSD-2-Clause licensed. Self-hosted. Free forever.
100% Open Source.
MICROSOFT'S FARA-7B CAN USE YOUR COMPUTER FOR YOU
7b params...clicks, scrolls, fills forms, books tickets all on its own
▫️ runs on-device, data stays local
▫️ beats openai computer-use on benchmarks
small model...big moves
https://t.co/GLTAfpet0N