Thinking Machines Lab
Today we are introducing the second generation of Inkling models with the release of Inkling 2 Small.
LiveUpdated 2026-11-07 02:11 UTC
The newest dev tools, ranked every hour.
Every library, CLI, framework and open-source repo shared by the developers who matter on X, read and ranked by AGK Intelligence.
The top dev tools right now (updated 2026-11-07 02:11 UTC): Thinking Machines Lab, openai.com, ricursive.com, boat, Plugin Catalog, strata, context.dev, Introducing Unsloth Studio, project-maya, niklaslenz.com.
Every post is read and classified by AGK Intelligence: what it is, which market it belongs to, and whether the link is a real tool. 31.9k posts from 5k X accounts over the last 21 days, 9.5k tools, 12 markets. New posts are collected several times an hour and the full ranking is recomputed every hour — last update 2026-11-07 02:11 UTC. Full method.
openai.com
ricursive.com
Ripple-65B Preview: U.S. Open-Weight SOTA on Agentic Coding
boat
omfg @theo just released a video that talks about
Plugin Catalog
Open a pull request that adds your plugin to the Hermes plugin catalog
strata
Strata: how it works
context.dev
came out #1 (by a lot)
Introducing Unsloth Studio
Run and train AI models locally with Unsloth Studio.
project-maya
Plus a round of fixes, UI improvements and community PRs.
niklaslenz.com
Play the world in your browser. Every number, the exact command and the raw output
qwen3.8-flash-next-gguf
Image-Text-to-Text model with 177B parameters. Download, explore files and run it on Hugging Face.
flashprove
Further progress in provable inference will likely be an important part of improving trust in AI deployment. To that end, we're open-sourcing FlashProve’s code,
Airlock
@WorkOS – how do you deal with agents and permissions? WorkOS built Airlock, the authorization layer for AI agents. Works with Claude Code, Codex and MCP gatewa
kimi-k3.1-pro
Releasing the model weights of Kimi K3.1 Pro
modelscope.ai
📄 Paper
Vercel for Platforms
Vercel for Platforms lets you build hosted products that create, deploy, and operate web applications for customers or teams.
security-audit-skill
I highly recommend cloudflare's security audit skill
Firecrawl
@firecrawl - Give your AI agents web data and beyond
Agents in flight
Setup guide
NVIDIA Technical Blog
Announced at GTC Berlin
Z.ai
4️⃣GLM-5.5（ ）
deepseek-v4.1-flash-1017-gguf
Image-Text-to-Text model with 748B parameters. Download, explore files and run it on Hugging Face.
Console by Nace.AI
Cloud Inference
Aether
It’s free to start.
dsh-superagent-prototype
DeepSeek open-sourced the design behind its always-on 'Super-agent': no chat window, and reportedly nearly half the slow-tail task time of single-session agent
Introducing Vercel Schedules
Vercel Schedules is now in Public Beta. Create and manage one-time and recurring schedules at runtime, and test scheduled work in Preview.
Vercel
Vercel Security Review is now in public beta. Every push to your GitHub repositories is reviewed for vulnerabilities, and Vercel Agent can open PRs with fixes.
deepseek-harness
详见 GitHub：
harness-lens
Harness Lens
harness-leaderboard
Which coding-agent harness should you use for your model?
Pydantic Docs
Make Pydantic AI agents durable with Temporal, running model requests and tool calls as activities so agents recover from crashes and resume long-running work.
hermes-voice
the code, the setup skill and the "hey hermes" wake word
Reason Machines
Tell your agent "Join the Reason Network"
together.ai
Together AI
Introducing LongCat-2.5
1.6万亿总参大模型，训练全程由国产芯片完成
OrcaRouter
Cyber Tier API
moe-blogpost
A hands-on guide to training Mixture-of-Experts models
Kimi API Platform
Kimi API Platform, providing the 2.8-trillion-parameter Kimi K3 large language model API with a 1M-token context window and Tool Calling. Professional code…
composio.dev
You can run the same kind of check on your own product. Your first $2 is free
Kimi AI Official Site
Kimi K3.1 Pro is now live. Easily tackle complex coding projects, build 3D models, and conduct in-depth financial research. More powerful agentic capabilities…
twil-8b
Text Generation model with 9B parameters. Download, explore files and run it on Hugging Face.
Databricks
Databricks AI Runtime (AIR) is now GA, offering an easy and super-fast way to launch GPU workloads. Unlike provisioning your own GPU servers, you get GPUs with
deepseek-v4.1-flash-1017-uncensored-gsq-rco-gguf
Text Generation model with 552B parameters. Download, explore files and run it on Hugging Face.
AI/ML API
Run both models via API ->
Entire
Source control is at a breaking point. Today, we open the portal to a new kind of Git forge: reimagined review, CI integrations, code hosting, and continuous…
Neon
We wrote about the changes, our MCP usage numbers, and the spec update
Gemini Omni 1.2 Flash just launched in Gemini API and @GoogleAIStudio, with 15s clips, improved conversational video editing, better consistency. Still fast but
llm-bench-rig
the prompt, the gate and the clip script
ernie-5.5-flash-base
Text Generation model with 286B parameters. Download, explore files and run it on Hugging Face.
auto-ontology
Auto Ontology 🔥
Devin Docs
Copy your rules and workflows from other coding agents into Devin with one prompt. Your other agents’ files stay as they are.
pgx
Postgres for AI agents. In Rust.
app-store-connect-cli
Fast, scriptable CLI for the App Store Connect API. Automate TestFlight, builds, submissions, signing, analytics, screenshots, subscriptions, and more -…
OpenComputer
Anyways try
Reppo
1️⃣ EVAL staking is now live. Stake 1,000,000 EVAL to unlock up to $1.00/day in Eval API credits that refresh every 24 hours. We’re supporting it with a 15% APR
Show HN: Orthogonal
And then multiple Anthropic employees confirmed this on HN
Particle
Particle is building a new AI inference layer for open weight models—fast, low-cost, and reliable. Use our API to power your apps with frontier AI.
OpenCode
Go costs $10/month, with generous usage limits and reliable access to leading coding models. Go Plus costs $40/month with higher limits. Go Teams costs…
msft.it
The China state-aligned threat actor Storm-0940 used the agentic AI penetration testing framework ARTEX to automate attacks targeting hundreds of organizations
opencommerce
today we are announcing openrouter for commerce
FAQ
What are the newest dev tools right now?
Thinking Machines Lab, openai.com, ricursive.com, boat, Plugin Catalog, strata, context.dev, Introducing Unsloth Studio — ranked by how much they are being shared on X, updated 2026-11-07 02:11 UTC.
How many new dev tools appear each day?
88 new tools were found in the last 24 hours, out of 9530 tracked over 21 days.
How are these tools ranked?
Hot = engagement on X with a 72-hour half-life, plus the number of different curators sharing it and a quality judgment by AGK Intelligence. Top = total engagement. New = first seen.