Archive

Google just killed the agent framework industry. ADK 2.0: Open-source. Free. Better than $50K enterprise tools. What it does: → Graph-based execution with routing, fan-out/fan-in, loops, retry → Structured agent-to-agent delegation via Task API → State management, dynamic nodes, human-in-the-loop, nested workflows → Interactive CLI (adk run) and Web UI (adk web) for local dev → Multi-turn task mode with single-turn controlled output → Works with Gemini 2.5 Flash, extensions via pip What it replaces: → LangChain orchestration boilerplate → LangGraph state machines → Vertex AI Agent Builder lock-in → Custom agent-to-agent delegation code Define your Agent class with instructions and tools. Compose a Workflow class as a graph. Run it locally with adk run or adk web. No hosted platform. No vendor lock-in. Customer support bots, research agents, multi-agent pipelines - same library. This is what open-source from Google looks like. → github.com/google/adk-pyt…

@gippp69 that's exactly why everyone should try it

@ArchiveExplorer graph-based execution with routing and fan-out right out of the box? wild shift honestly

@poly0015iew and that sounds really interesting might actually be true

@ArchiveExplorer google's strategy is just waiting for an industry to exist and then making it free

@mikenevermiss saw this repo, think there's still stuff to add

MOONSHOT JUST MADE A FREE REPLICA OF CLAUDE CODE. It’s called Kimi Code CLI. It’s open source, free to use, and built by the team behind Kimi K3. It comes with features you won’t find in Claude Code: → upload a screen recording as input → built-in coding, planning, and research agents that work in separate contexts → plan your changes before editing any files → set up MCP servers directly from the CLI with /mcp-config → works with VS Code, JetBrains, and Zed → lightweight - no Node.js setup, starts in seconds The CLI is completely free. The Kimi K3 model behind it starts at $3 per million input tokens. Grab it below 👇

@gippp69 what??? 1k+ ready made skills? no way studying it today

I FOUND A 60,000+ STAR GITHUB REPO WITH 1,000+ READY MADE SKILLS THAT TURN CLAUDE CODE INTO A LIBRARY OF PERMANENT WORKFLOWS 00:06 it opens to more than 1,000 skills for coding, research, documents, automation, marketing, security, and dozens of other jobs. one skill is basically a folder with a SKILL MD file that tells claude when to activate, what steps to follow, and what the final output should look like. install it once and claude loads the workflow whenever your request matches, instead of making you paste the same instructions into every new session. stronger skill packs also include validation scripts, deeper references, reusable assets, and templates that keep the result consistent every time. one repository gives claude code repeatable workflows that can also run across Codex, Cursor, Gemini CLI, and other coding agents.

The guy behind Tavily just put a project on GitHub that turns any LLM into an autonomous research agent. it's called gpt-researcher, and the trick is stupidly simple: one LLM plans the research questions, N execution agents fetch the web sources in parallel, another LLM aggregates it all into a fully cited report. / works with any LLM - OpenAI, Anthropic, Groq, Ollama, or local / every fact cited to a source - no hallucination cover-up / installs as a Claude skill: npx skills add assafelovic/gpt-researcher / built by Assaf Elovic - also runs Tavily, the search API AI agents use apache 2.0, and already past 28,000 stars. -> github.com/assafelovic/gp… bookmark it.

@EXM7777 real alpha recommending everyone read it!

@0xRicker must have saved !

@ArchiveExplorer saved this alpha

@0xSlyth yeahhhh, main thing is to know how to structure the info it gives you and i'd add 1-2 more repos that help you not get lost

@ArchiveExplorer this changes everything no more fact checking chaos

@yaolei11 exactly, love this repo

@ArchiveExplorer having cited reports from an autonomous researcher is going to save so much time

@shevaxgod really good analogy and personally i also think it's a really useful tool

@ArchiveExplorer gpt-researcher like a breath of fresh air among hundreds of other LMM models

Anthropic researcher just dropped a paper most AI engineers missed. Xiaotian Luo published it 2 days ago. It unpacks the entire self-evolving harness playbook: how the code around the agent rewrites itself. You stop tuning the model. You tune the code around it. → arxiv.org/abs/2607.13683 Bookmark it. Then read this setup ↓

@tolik12308 appreciate it thanks

@ArchiveExplorer This is an interesting article, friend

@0xCodila really useful to listen to his talk rn was just about to start using kimi

Kimi CEO Zhilin Yang: "The biggest mistake in agent systems - people trying to build one smarter agent we didn't make one smarter - Kimi made a thousand: one brain, a thousand hands" here's how: step 1 → stop polishing one agent, split the task and run many in parallel - that's the real ceiling-break step 2 → give each agent a long context so it can run for days, not seconds - long context is what lets an agent run long step 3 → give each agent a strong prior, so agent-RL can search for a good solution instead of starting from zero step 4 → don't just add more data - make each token count. they hit the data wall, so they made every token 2x smarter step 5 → don't scale one brain, scale the swarm - many agents working in parallel beat one agent thinking harder he just dropped Kimi K3 - and this 40-min workflow is the best on how to actually use it watch & bookmark - then read the article on saving on agents ↓

@ai_rohitt a year ago i wouldn't have believed stuff like this could be publicly available to everyone literally gold

🚨 Anthropic just showed a 27-minute workshop on how to actually do prompts for Claude. Taught by the people who built it. Free. No registration. No paywall. I've seen $300 courses that don't cover what they teach in the first 8 minutes. Watch the session

@Granite0x def gonna use this kimi code think i can build a lot with it

Everyone's racing to run Kimi K3 - the model that just beat Claude. But nobody noticed Moonshot did the reverse: their official agent quietly made itself compatible with Claude Code. An official command migrates your entire setup over from Claude Code. It runs over an Anthropic-compatible endpoint - you can even point Claude Code itself at Kimi. The model everyone calls a Claude killer built itself to speak Claude's language. The Anthropic API is becoming the standard interface for agents - even rivals build for it. 3,309 stars. switch between Kimi K3 and Fable 5 with one command. → github.com/MoonshotAI/kim… bookmark this before it gets taken ↓

@Granite0x woahhh Granite, been hearing about this project for a while if they made skills for claude, it's def a gem

Almost every AI model on the internet lives in one place - Hugging Face. Claude is one of the few that isn't there. And yesterday Hugging Face shipped 25 ready-made skills - made specifically for Claude Code. Claude starts running the entire Hugging Face platform for you, right from the terminal: - find and download any of thousands of models with one command - fine-tune your own model on their cloud GPUs - without buying one - build and ship a working demo ap, for free 10,800 stars on GitHub. Installs in one line. → github.com/huggingface/sk… bookmark this before it spreads.