Noureddine

Beads replaces flat task lists with a Dolt-backed graph using hash IDs for conflict-free multi-agent workflows. Its semantic compaction summarizes closed tasks to cut context bloat—solving AI agents' long-horizon memory limits without git or locks.

@VincentVentalon @MennelDev Est-ce que tu l'utilises toute la journée ? genre entre 16-19h ? le niveau d'effort ?

@MennelDev Pareil, je pense que certaines personnes ont vraiment des code base degeulasse et que les gens qui payent 20$ sont frustrés Mais person j'ai aucun interet a reapprendre comment fonctionne et trust Codex ca serait plus galère

j'ai l'impression d'être un ovni mais opus 4.7 me convient, il hallucine pas tant que ça, répond à ce que je demande et les outputs sont ok

Mercury Agent embeds a "Second Brain" with SQLite+FTS5 for persistent, auto-concise memory that resolves conflicts and consolidates diverse inputs into an adaptive AI persona. Its permission-hardened tools and token budget enforcement ensure control in 24/7 CLI or Telegram ops.

@justalexoki Bubble game !

wait why is google investing in anthropic isn't that a literal competitor

@OpenSwarm_ @tienedev 👀

Introducing Open Swarm 👾 One Canvas. An army of AI Agents Be the boss openswarm.com

@MichLieben Is that what the skills also do? Posts with engagement on words like "ads"!

I'm giving away the Claude Code skills we use to manage $300k/mo in ad spend at ColdIQ. 4X ROAS on $1M+ spent. Ivan, our head of growth, built them off 300+ hours running ad campaigns for our clients. They run Google, Meta, and LinkedIn ads from the terminal in plain English: → bulk edits across platforms → custom audiences from CRM lists → creative fatigue detection before CTR dips → bid adjustments at scale → performance audits across periods Reply "ads" and I'll send the full repo. Must be following.

PinchTab rethinks browser automation for AI agents with token efficiency: 800 tokens/page via text extraction, 5-13x cheaper than screenshots. This tradeoff slashes LLM token costs while enabling multi-instance Chrome orchestration. Worth understanding for agentic workflows.

Cloudflare Agents runs LLM-generated TypeScript code inside a sandboxed environment — not just tool calls but dynamic program generation on the fly. Powered by Durable Objects, it offers real-time, stateful AI agents that hibernate to save costs. Code Mode flips AI agent design.

Browser Harness builds LLM browser agents that self-heal by writing missing helper functions on the fly. No fixed tools, just 592 lines of Python driving Chrome DevTools Protocol for dynamic, autonomous browser automation. This rethinks agentic system design from the ground up.

@tienedev @sudoingX Oui c’est dans les plans ! C’est une très belle nouvelle !

@sudoingX @OurDin c’est le moment de brancher la 5090 🤯

okay this is absolutely insane. my undisputed king qwen 3.5-27b dense on single RTX 3090 just got replaced by the same team today. qwen drops 3.6-27b dense just now and the chart says it beats its predecessor on every single benchmark, beats qwen 3.5-397b-a17b moe which is 15x larger, and matches claude 4.5 opus on terminal-bench 2.0 at 59.3 flat, while beating claude on skillsbench, gpqa diamond, mmmu, and realworldqa. a 27 billion parameter open weight model matching a frontier proprietary model on agentic coding. let that sit for a second. pulling weights right now. testing on my 3090 desktop first because that is where the crown lives, then 5090 mobile for the same 24gb class speed story. same quant, same hermes agent, head to head against 3.5-27b dense on same hardware. if this chart holds even half the gain in real agentic runs it's a gamechanger for every builder sitting on a single consumer card. thank you @alibaba_qwen, this is what open source looks like when a team is serious. the corporate salesmen telling you local ai is not ready yet are getting lapped every week by teams that actually ship. new 27b dense is here. open is winning. the best model for a single 24gb gpu just changed in the middle of my benchmark. data drops soon anon

@dylansz_ Yeah but speed as hell

El secreto es pagar modelos chinos directo en la página de china a precio de banana. No avivo mas

🚀 Meet Qwen3.6-27B, our latest dense, open-source model, packing flagship-level coding power! Yes, 27B, and Qwen3.6-27B punches way above its weight. 👇 What's new: 🧠 Outstanding agentic coding — surpasses Qwen3.5-397B-A17B across all major coding benchmarks 💡 Strong reasoning across text & multimodal tasks 🔄 Supports thinking & non-thinking modes ✅ Apache 2.0 — fully open, fully yours Smaller model. Bigger results. Community's favorite. ❤️ We can't wait to see what you build with Qwen3.6-27B! 👀 🔗👇 Blog: qwen.ai/blog?id=qwen3.… Qwen Studio: chat.qwen.ai/?models=qwen3.… Github: github.com/QwenLM/Qwen3.6 Hugging Face: huggingface.co/Qwen/Qwen3.6-2… huggingface.co/Qwen/Qwen3.6-2… ModelScope: modelscope.cn/models/Qwen/Qw… modelscope.cn/models/Qwen/Qw…

@tienedev 🚀

Ten minutes. That's how long it takes to rebuild my homelab from scratch on new hardware. NixOS + Incus + OpenTofu, built to nuke and pave. Wrote about how I got there: tiene.dev/articles/homel…

bro using windows ?

Meet Kimi K2.6: Advancing Open-Source Coding 🔹Open-source SOTA on HLE w/ tools (54.0), SWE-Bench Pro (58.6), SWE-bench Multilingual (76.7), BrowseComp (83.2), Toolathlon (50.0), Charxiv w/ python(86.7), Math Vision w/ python (93.2) What's new: 🔹Long-horizon coding - 4,000+ tool calls, over 12 hours of continuous execution, with generalization across languages (Rust, Go, Python) and tasks (frontend, devops, perf optimization). 🔹Motion-rich frontend - Videos in hero sections, WebGL shaders, GSAP + Framer Motion, Three.js 3D. 🔹Agent Swarms, elevated - 300 parallel sub-agents × 4,000 steps per run (up from K2.5's 100 / 1,500). One prompt, 100+ files. 🔹Proactive Agents - K2.6 model powers OpenClaw, Hermes Agent, etc for 24/7 autonomous ops. 🔹Claw Groups (research preview) - bring your own agents, command your friends', bots & humans in the loop. - K2.6 is now live on kimi.com in chat mode and agent mode. For production-grade coding, pair K2.6 with Kimi Code: kimi.com/code - 🔗 API: platform.moonshot.ai 🔗 Tech blog: kimi.com/blog/kimi-k2-6 🔗 Weights & code: huggingface.co/moonshotai/Kim…