@aashna_doshi2 · X

Fiverr for AI agents

oomol-lab · GitHub

open-connector Open-source auth gateway connecting 1000+ SaaS providers to AI agents through SDK, CLI, MCP, HTTP, and OpenAPI.

@ServerForAgent · X

@0xanukul · X

@n_surendar29293 · X

@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

@adazlife · X

building milestone billing for digital agencies. invoice generates automatically when work is done, client approves, payment clears before the next phase starts. no more chasing

@CRYPtoKong32 · X

also Join our $MUSKOX Ai Ecosystem built on Base Coin. 🪙 $AGWC Websites:

taosx · HN

I created a simulation for coding harnesses based on my own pi sessions. When taking into account all factors, DS-v4-Pro is cheaper than gpt-5.6-luna due to caching. Look at the bill segments difference for cache read cost and uncached cost between deepseek and the other models. At this point is cheaper to use ds-v4-pro than the luna models from openai. ignore the numbers except the classic and keep in mind that classic is based on pi with the only change limiting tool output to 10kb https://har

mariusbolik · HN

Webstractor – Pay-as-You-Go Web Data API for AI Agents

@k_mansourizadeh · X

Curious to learn more, building

@gonelf · X

So many things - dead simple way to share projects within your team - dead simple base - no backend forms - ez directory submissions - a Lego event