@coleywoleyyy · X

Yup, it’s buns. I vibe coded my own tool at Helicone, might make it easier

@pengsonal · X

500+ Hugging Face models through a single free API no credit card just an email signup 😳 launched on July 3 as a unified gateway for Hugging Face models one API key one endpoint 500+ models what you get for $0: • 500+ open-source models through an OpenAI-compatible API • no separate API keys for different providers • works with Cursor, Claude Code, Hermes, OpenCode, and anything that supports a custom base URL • email signup only setup takes about 2 minutes: 1. Go to 2. Sign up with your email 3. Generate an API key 4. Set your base URL to 5. Choose any model from the catalog and start building a few things worth knowing: • is a third-party gateway, not an official Hugging Face product • the free tier is rate-limited, but the exact limits haven't been published yet • i wouldn't build production apps that depend entirely on a free aggregator what i like is the simplicity instead

@Boltchh · X

@zeynepavann · X

Thank you to everyone who joined our "map your TAM from the terminal" session with last week. We built live in the terminal using Claude Code and the MCP. I wrote up the whole thing afterwards. The seven stages, why each one exists, what to do with the list once you have it, and the outreach half we covered at the end. The recording is linked inside. The skill is public too, so you can run it on your closed-won book. You bring your own accounts; the engine does the expansion, scoring, and contact-finding. Comment "TAM" and I'll send you both skill and guide.

@rofarkas · X

@vaiossx · X

Thanks, what about ?

@xiaoheihei257 · X

📢 大消息！Gemini 3.6 Flash 和 Gemini 3.5 Flash-Lite 已经在 API 正式上线了！🚀 最近模型更新越来越频繁，这次 直接把两个新版本推出来，实际用起来感觉又进了一步。 先说 Gemini 3.6 Flash： 它是 3.5 Flash 的升级版，输出质量明显更好，但价格完全没变。最关键的是 token 消耗减少了大概 17%，遇到 DeepSWE 这种复杂代码生成任务，最多能省下 65% 的 token，成本直接降下来了，性价比很高。 再看 Gemini 3.5 Flash-Lite： 这是 3.5 系列里跑得最快、最省钱的那个，输出速度最高能达到 350 tokens/s。特别适合做高频任务，比如批量处理文档、Agent 实时搜索这些场景，用起来又快又稳，不会卡顿。 的模型生态现在越来越丰富了，两个新模型都支持官方 API 直接调用，开发者用着也方便。整体看下来，AI Agent 时代的底层支持又扎实了不少。 有在做 AI 项目或者日常调用大模型的朋友，不妨去试试新版本，体验应该会挺惊喜的～ @justinsuntron @BAI_AGI #TRONEcoStar

@mageofweb3 · X

@MixRoute_ai · X

cdnsteve · HN

Tokenstead, find AI models for your hardware

@fort_ink_games · X

You guys should check out I busted my something or other vibe coding it so I feel all the pain you were describing in the space, but it certainly works now. It's the x402 gateway for @KorraFinance. There are QuantFi elements (check her track record). But her greatest value to you would be (social media sentiment x actual market price) divergence signals your agents can just pay-per-call for. Talk to @MatiGreenspan about it on a @QE4Everyone space... they get mad reach.

@pvdyck1 · X

: marketplace where you publish an n8n-compatible automation agent, set a per-run price, and get paid every run. builders keep 100% of their price (10% only at cash-out), buyers need no crypto. beta opened this week: or