Thiago Moreira

Founder em construção 🚀
IA • Tecnologia • E-commerce • Automação
Sempre testando novas ideias.

[Kimi.ai @Kimi_Moonshot]

🌘 Kimi-K2.7-Code, our latest coding model, is now released and open-sourced!

🔷 Improved coding & agent performance over K2.6: +21.8% on Kimi Code Bench v2, +11.0% on Program Bench, and +31.5% on MLS Bench Lite.
🔷 Reasoning efficiency: Less overthinking, with 30% lower reasoning-token usage compared to K2.6.
🔷 Long-horizon coding: Improved instruction following, higher end-to-end coding task success rates.

⚡️ 6x High-Speed Mode coming soon!
🔌 Available today via Kimi API and Kimi Code.

🔗 Kimi Code: https://t.co/uvoSJKyGCY
🔗 API: https://t.co/EOZkbOwCN4

[Tom Dörr @tom_doerr]

A curated list of vetted self-hosted Docker applications

https://t.co/UWtjN74jVU

[Tom Dörr @tom_doerr]

Turns AI coding chats into a repeatable engineering workflow

https://t.co/4ZoG6o2PT0

[Marco Ramilli @Marco_Ramilli]

🤖 TTS
⭐ 45,528 stars

Stream cloned voices in 16 languages with under 200ms latency. This deep learning toolkit brings production-ready text-to-speech to life.

🔗 https://t.co/XNnVPbOxh9
🌐 https://t.co/Q8rvbAy5Xi

#AI #MachineLearning

[Tom Dörr @tom_doerr]

Generates technical diagrams from natural language descriptions

https://t.co/eBOnW3KulY

[Xiaomi MiMo @XiaomiMiMo]

🚀 MiMo Code V0.1 is now live and open-source！

More than an AI coding assistant in your terminal — it's the smartest coding partner you'll ever work with.

Comes with MiMo V2.5, a multimodal model available free for a limited time, featuring a million-token context window—ready to use out of the box.

♾️ Infinite Context: Knowledge accumulates automatically, and with lossless compression, even million-line projects keep every critical detail intact—quality never drops.
🧠 Agent-Model Synergy: An Agent framework deeply optimized for MiMo, with a full closed loop of testing, review, and validation—so complex tasks get done in one pass.
📝 Compose Mode: Specs → Plans → Build → Report. Design first, code second—clear thinking, no rework.
🔄 Self-Evolving System: Every session is automatically reviewed, distilling experience and best practices—the more you use it, the smarter it gets.
🎙️ Voice Input: Powered by MiMo-V2.5-ASR — just speak instead of type, and your voice becomes the prompt for truly hands-free coding.
🔌 Claude Code Compatible: Automatically loads your existing skills, MCP servers and commands, and reuses your API configuration—zero-cost migration, no setup required.
🌐 Open & Flexible: MIT licensed, with support for leading model providers including Anthropic, OpenAI, DeepSeek, Kimi, GLM and more.

Install in one line:
Mac & Linux
curl -fsSL https://t.co/ViHsb4eGns | bash
(For the best experience，we recommand Mac user use it on iTerm or vscode terminal)
Windows
npm install -g @mimo-ai/cli

🔗 Learn more
Website ↓
https://t.co/Aq9BVuyA9a
Blog ↓
https://t.co/f40wLgQicK
GitHub ↓
https://t.co/O5Mj3rzl9g

[Yash @dew_yashtwt]

Launching Supercode soon 🚀 — the open source SWE agent.

Free and open models.

access over your entire machine from your terminal — read files, run commands, edit code, open apps, manage settings.

Control your entire system directly from SUPERCODE with your voice. Granular permissions so it only does what you allow.

better and longer memory that persists across sessions. No vendor lock-in.

Just an agent that actually ships.

[Thiago Moreira @parabastech]

Pois eh 😬

[Tom Dörr @tom_doerr]

Open-source collection of optimized company SVG logos

https://t.co/bCFke2uEQL

[Alpha Batcher @alphabatcher]

Boris Cherny: "My job is to write loops."

5-day version you can copy for Claude Code

Day 1: repo memory
- write CLAUDE.md
- include stack, test commands, code style, release rules, gotchas
- add .claude/settings.json with the shell commands Claude can run

Day 2: verification skill
- pick 1 flow Claude keeps breaking
- put the browser/API test in .claude/skills/<flow>/scripts/
- make it return: pass/fail, failing step, screenshot/log path

Day 3: commands
Add these files:

.claude/commands/babysit.md
- checks your PRs
- reads CI
- handles obvious review nits
- surfaces design questions

.claude/commands/triage-issues.md
- labels new issues
- dedupes against existing ones
- assigns owners

.claude/commands/deploy-watch.md
- checks the live app
- reports regressions
- avoids touching production

Day 4: loops
> /loop 5m /babysit
> /loop 15m /triage-issues
> /loop 5m /deploy-watch

Day 5: overnight work
- schedule /morning-report
- schedule /deep-audit
- write results to .claude/inbox/
- let your morning loop read from that folder

The rule: every code-writing loop gets a separate verifier.

Builder makes the change.
Verifier runs the real app.
You read the diff.

Skip that and you wake up to 14 broken PRs with very confident summaries.

Video: "Reflecting on a year of Claude Code" with Boris Cherny & Cat Wu

[Kevin @kevincodex]

Smart Routing is now live across OpenGateway and OpenClaude

to test its performance we are dropping unlimited while it last API key

API key: ogw_live_4dbfa495092f917e8c78476905c9dbdf

enjoy

[Kushal Byatnal @kushalbyatnal]

available here today: https://t.co/ytMFbGWKVd

[Ren @FakeMaidenMaker]

⚡ 又发现一个能让 Claude Code、Codex 这类 AI 编程工具搜代码又快又省 token 的神器——semble

刚开源没多久，GitHub 已有将近 5k star，持续飙升中，而且它自证比 grep+read 的方式省约 98% token

https://t.co/3C0L6qcSDc

它真正解决了搜索上下文的痛点：

你让 Claude Code 在一个大仓库里找「账号验证逻辑在哪里」，以前 agent 要先 grep、再把好几个整文件塞进上下文，token 一烧一大截。

接上 semble 之后，直接用自然语言问一句，它只把最相关的那几段代码片段拿回来，索引一整个普通仓库约 250ms，单次查询约 1.5ms，全跑在 CPU 上，不需要 API key，不需要 GPU，不依赖外部服务。

它本身就是一个 MCP server，明确支持 Claude Code、Codex、Cursor、VS Code，任何 MCP 兼容的 coding agent 都能接进来。

部署也很简单，uv tool install semble 装好后跑 semble install，交互式安装器自动检测你已装的 agent，一步接入。

[Thiago Moreira @parabastech]

@heliotsx Kkkkkkkkkkkkkk o final da frase eh um ploit twists!!!! Kkkkkkkkk

[How To AI @HowToAI_]

https://t.co/Uovtkidgiv

[Tom Dörr @tom_doerr]

Unified dashboard for Proxmox, Docker, Kubernetes

https://t.co/JU5FkMRKqP

[Tom Dörr @tom_doerr]

35 agentic AI architectures with comparative benchmarks

https://t.co/jLl89WZ80p

[Geek Lite @QingQ77]

一个 Docker 容器搞定整个 Homelab 的监控：GPU、容器、服务、磁盘、多机器，不用装 Prometheus/Grafana

https://t.co/E0I4vvLFL1

聚合多台机器（Linux、Pi、Windows）的 GPU 显存/功耗/温度、容器真实内存与显存占用、systemd 服务状态、磁盘树状图、模型服务器调用情况，全部在单页面展示。

核心特点：无 Agent、仅需 SSH 密钥即可多机采集、SQLite 本地存储历史、Discord/ntfy.sh 告警、内置 30+ 模型服务器识别。

[Tom Dörr @tom_doerr]

Adds object detection and AI summaries to security cameras

https://t.co/pzdwatS4sG

[Tom Dörr @tom_doerr]

Teaches building modular Agentic RAG with LangGraph and conversation memory

https://t.co/Gvf35SRinf