Claude Managed Agents dynamic workflows are now available in public beta. It's a new type of multiagent orchestration, built for your most ambitious workloads.
A lead agent writes a plan that runs across many agents in phases, combining the results at the end.
ESTE ARCHIVO CLAUDE.md CONVIERTE A CLAUDE EN UN INGENIERO SENIOR
Boris Cherny, creador de Claude Code, compartió los trucos y flujos de trabajo que su equipo usa a diario.
La mayoría pueden integrarse directamente en un CLAUDE.md para cualquier proyecto:
> Orquestación de flujos de trabajo
> Estrategia de subagentes
> Bucle de auto-mejora
> Verificación antes de finalizar
> Corrección automática de errores
> Principios fundamentales
Lo interesante es que funciona como un sistema acumulativo.
Cada vez que corriges a Claude, esa corrección puede quedar registrada y convertirse en una regla para futuras tareas.
Con el tiempo, Claude aprende de tu feedback y puede reducir los mismos errores una y otra vez.
Si utilizas IA para programar todos los días, tener un CLAUDE.md bien estructurado puede ahorrarte muchísimo tiempo.
Guárdate esto👇
ANTHROPIC PUBLICÓ UN TALLER GRATUITO SOBRE CÓMO CONSTRUIR UNA EMPRESA USANDO SOLO AGENTES DE IA
agentes que se dividen las tareas, colaboran entre sí y ejecutan procesos de forma autónoma, sin intervención humana
subtitulado al español
📕 guárdalo, te va a servir
UN CHINO FILTRÓ LA FORMA MÁS FÁCIL DE HACER DINERO
y acaba de publicar gratis lo que otros estan cobrando $300
se llama AutoClip. le pegas el link de un vídeo y te devuelve los cortes ya montados, con título viral incluido, sin tocar el ratón.
esto es lo que hace solo:
→ descarga el vídeo y los subtítulos
→ lee la transcripción entera y saca el guion
→ detecta dónde empieza y acaba cada tema
→ puntúa cada trozo del 1 al 10
→ corta solo los que valen la pena
→ le pone título a cada uno
→ agrupa los que van juntos en un pack
siete pasos. tú solo pegas el link.
un podcast de 2 horas se convierte en 15 cortes verticales listos para subir. tiktok, shorts, reels y x, los cuatro pagan por views.
interfaz web con progreso en tiempo real. funciona con youtube, bilibili o archivo local: docker-compose up -d y listo.
6.300 estrellas, 1.200 forks, licencia MIT.
resultado: lo que antes costaba 300 dólares por vídeo ahora es gratis y corre en tu propia máquina.
esto cambia el juego para cualquiera que viva de cortar contenido largo.
repo y más info en comentarios 👇🏻
i just cancelled my chatgpt subscription
you can use jev for free now, and after a week on it i'm not going back
it's called openjev. a community of volunteers builds it in the open on github and it runs straight in your browser
it does the job people are paying for:
→ no api key
→ no waitlist
→ nothing to install
→ nothing you paste ever leaves your laptop
but the features aren't what got me. it's the speed
the answer comes back in milliseconds. no thinking out loud, no typing animation, no paragraph to read before you find the point. just the decision and a number for how sure it is
on top of that you can:
→ drop 400 emails in and get reply today, later, never
→ split 300 comments into questions, complaints, praise
→ sort 200 job ads into worth it and not
→ run it on a phone with the 639 mb model
→ load the big one and score 84.5% against the paid jev's 88.3%
honest warning: the good model is a 3 gb download the first time and the small one is noticeably dumber. and the real jev is free on vercel's gateway right now, they just aren't shouting about it
100% open source. $0 a month
repo below
We're open-sourcing Claude Commerce Agents.
This is a blueprint for building shopping and merchant agents, with reference implementations across retail, travel, telecom, and entertainment.
Google's team just dropped a 9-page PDF on Harness Engineering - one formula replaced prompt engineering:
the twist: same Claude Sonnet, same benchmark - change only the harness
the formula: Agent = Model + Harness
here's the playbook in 6 steps:
step 1 → add guides - AGENTS.md, rule files, constraint docs - each line is a past agent failure turned into a permanent fix
step 2 → add sensors - linters, tests, validation scripts the agent runs on its own output before a human sees it
step 3 → build the agentic loop - plan, execute, verify, fix - bounded retries, budget caps, escalation when stuck
step 4 → externalize memory - the model forgets every session. the harness remembers state, decisions, and artifacts across all of them
step 5 → enforce permissions - which tools, how many writes, what needs approval. the model doesn't enforce safety. the harness does
step 6 → wire observability - track every tool call, cost, retry. trip wires fire when behavior drifts
the result: your agent stops being a demo and starts being infrastructure - every failure makes the system permanently better, not just the next conversation
this 9-page PDF is what comes after prompt engineering and context engineering
bookmark and build the full system from the article below ↓
Claude Academy is now live.
Whether you're figuring out what AI is or already using Claude every day, there's a path that meets you where you are. The courses and tutorials are free and open to anyone at https://t.co/WRiSRAvK6l
🚨 THIS IS ABSOLUTELY INSANE
A Chinese developer has just released a free tool capable of automatically creating videos for TikTok, Reels, and YouTube Shorts.
It’s called MoneyPrinterTurbo.
And it has already surpassed 100,000 stars on GitHub.
Here’s how it works:
1.- You enter a topic or a keyword.
2.- The AI generates the script, the narration, and the subtitles.
3.- The tool finds the visual footage, edits the video, and delivers the final result.
It all happens in a single workflow.
Save this tool; I’m sure you can get a lot of value out of it.
I’ve left the link in the next comment 👇
20 GitHub repos with 2.4M+ combined stars that replace tools costing $60,000+/year
1. public-apis ⭐456k - 1,500+ free APIs across every category, weather to finance to games, all documented. https://t.co/R9WQGOQZBx
2. awesome-selfhosted ⭐312k - self-hosted replacements for Notion, Google Photos, Zapier, and dozens more paid subscriptions. https://t.co/OgExTiZ5Ta
3. hermes-agent ⭐230k - self-improving personal agent with persistent memory, cron scheduling, MCP built in. Free alternative to paid always-on agent platforms. https://t.co/PbkmM1v2cD
4. n8n ⭐200k - visual automation with native AI agents. Replaces Zapier/Make entirely, self-hosted. https://t.co/DNvBpff9g4
5. ollama ⭐178k - run Llama, Mistral, DeepSeek locally with one command. No API bill, no rate limits. https://t.co/a7ZqZcIxkF
6. dify ⭐152k - visual builder for AI agents and RAG pipelines. Skip the $500/mo no-code AI builder subscription. https://t.co/zx7UDJbysl
7. free-for-dev ⭐132k - hundreds of services with permanent free tiers. No trials, no credit card. https://t.co/G5aQgbSJ3d
8. awesome-llm-apps ⭐132k - 100+ ready AI agents and RAG apps with full code. https://t.co/iXDCiIYPsw
9. awesome-mcp-servers ⭐92k - thousands of MCP servers connecting your agent to browsers, databases, anything. https://t.co/RFLgyKY6W7
10. supabase ⭐108k - Firebase alternative that's actually free to start. Auth, DB, storage in one Claude Code prompt. https://t.co/JySIJ4IwUP
11. strapi ⭐73k - open-source headless CMS, generates a full API from your content model in minutes. No Contentful bill. https://t.co/81imGEu7G9
12. immich ⭐110k - self-hosted photo and video backup with face recognition. Cancel the Google Photos storage plan. https://t.co/DXd6o4nXWu
13. appwrite ⭐57k - complete backend-as-a-service, self-hosted. Auth, DB, functions, storage, one prompt away from Firebase money. https://t.co/LMMyeQIO8a
14. medusa ⭐36k - full ecommerce backend, open source. Skip Shopify Plus fees entirely on your next vibe-coded store. https://t.co/uKdBCv1o8R
15. novu ⭐39k - notification infrastructure for email, SMS, push, in-app, all in one API. Replaces OneSignal's paid tiers. https://t.co/wRVeTyuIf3
16. tooljet ⭐38k - drag-and-drop internal tool builder connected to any database or API. Retool's seat pricing gone. https://t.co/DHd670P06t
17. mattermost ⭐38k - self-hosted team chat built for engineering orgs. Slack without the per-seat bill. https://t.co/mAapO6Rjzl
18. outline ⭐40k - fast, clean team wiki and docs. Replaces Confluence and Notion's team plan. https://t.co/77ZGW3UOHC
19. plausible ⭐28.5k - privacy-friendly analytics, lightweight script, real dashboards. No GA360 contract needed. https://t.co/bdkPQm000q
20. openwork ⭐22k - open-source Claude Cowork alternative. Share skills and MCPs across Claude Code, Cursor, Codex, one setup for every agent. https://t.co/bgOq628zfp
Save this before you pay for another tool this list already replaces for free 👇
11 GitHub repos with 1.5M+ combined stars replace tools you'd otherwise pay $50K+/year for
1. free-for-dev (131k⭐) - hundreds of services with permanent free tiers. No trials, the repo's own rule.
https://t.co/khghGq7fYL
2. public-apis (453k⭐) - 1,500+ free APIs: weather, finance, images, games.
https://t.co/R9WQGOQZBx
3. awesome-selfhosted (309k⭐)- self-hosted replacements for Notion, Google Photos, Zapier and dozens more subscriptions.
https://t.co/OgExTiZ5Ta
4. awesome-claude-code (51k⭐) - skills, hooks, slash commands, orchestrators for Claude Code.
https://t.co/gx84bE8l2s
5. anthropics/skills (165k⭐) - the official skills repo. Start here before third-party ones.
https://t.co/YSohdu4ETJ
6. awesome-mcp-servers (91k⭐) - thousands of MCP servers connecting your agent to browsers, databases, anything.
https://t.co/RFLgyKY6W7
7. awesome-llm-apps (116k⭐) - 100+ ready AI agents and RAG apps with full code.
https://t.co/iXDCiIYPsw
8. system-prompts-and-models-of-ai-tools (142k⭐) - leaked system prompts of Cursor, Devin, v0, Claude Code.
https://t.co/YtXP0bSXDo
9. awesome-codex-skills (15k⭐) - curated Codex skills sorted by category: data & analytics, writing, productivity, development.
https://t.co/7k24MvDmr0
10. awesome (490k⭐) - the list of every other list. Whatever's missing above, it's here.
https://t.co/JaRNcrD6W0
Bookmark this before you pay for something that's already free 👇
ANTHROPIC ENGINEER:
"DON'T PROMPT CLAUDE. BUILD A SYSTEM THAT PROMPTS ITSELF."
In this free workshop, he explains why most people use Claude the wrong way.
And how to turn one AI into an entire team of AI agents.
He covers:
• Proper CLAUDE.md setup
• Plugins almost nobody uses
• Advanced prompt caching (95% cache hit rate)
• Why starting every chat from scratch is a mistake
Worth more than most paid Claude courses.
Watch this and bookmark it.
MICROSOFT JUST OPEN-SOURCED SELF-EVOLVING AGENT SKILLS.
it's called skillopt.
skills that improve themselves the same way you train an ai model.
no more guessing whether your prompt tweaks helped. a base model runs the task, an optimizer evaluates the output and rewrites the instructions itself.
→ isolates successful paths from failures to find precise improvements
→ auto-rejects any edit that doesn't beat your benchmark score
→ beats hand-crafted prompts and optimizers like textgrad
→ zero model lock-in, the skill transfers to any model you switch to
100% free. open source.
Anthropic engineer:
"At Anthropic, >90% of our engineers are building with self-improving loops.
In 4-6 months, it will be 100%. my agentic loops can run for days without spending hundreds of dollars."
in this 40-minute podcast, an Anthropic engineer reveals how to build effective agents from scratch.
Agent → harness → loops → memory = modern agent
This one video will replace 10 paid courses on vibe-coding.
Watch it today, then explore the same setup in the article below.