Articles Tagged “Developer Tools”
53 articles found
GitHub AI Secret Detection: How Push Protection Gets Smarter
GitHub is adding a ModernBERT classifier to push protection that spots unstructured passwords in under 2 ms and could more than double blocked secrets.
What Claude Code Mods Can Change, and What to Check First
Claude Code mods are TypeScript functions that rewrite prompts, add UI and replace built-in features. Here is how they install and what to check first.
Legit Security Agent Auto-Fixes Vulnerable Dependencies
Legit Security's agentic remediation now fixes vulnerable open-source dependencies, re-scans before and after, and opens a pull request for review.
GPT-6.1 Sol vs GPT-6 Astra: Which Fits Your Workload?
GPT-6.1 Sol lists at $2/$10 per million tokens, one-fifth of Astra's price, and OpenAI says it nearly matches Astra on coding and computer use.
MemBrowse: How to Catch Firmware Memory Growth Early
MemBrowse tracks firmware RAM and flash across commits, with local analysis and pull-request reports that help developers catch memory growth early.
run-assert-eval: How Microsoft Tests AI Agent Fixes
Microsoft’s run-assert-eval links AI agent risk discovery, repeatable tests and runtime policies, helping teams check whether a proposed fix works.
GPT-6 Sol vs Luna vs Astra: Which Model Should You Use?
GPT-6 Sol costs $2 per million input tokens and Luna $0.10, half of GPT-5.6's current rates. Here's how they compare with Astra and how to migrate.
Claude Opus 5.5 Pricing, Benchmarks and When to Switch
Claude Opus 5.5 lands at $4 per million input tokens — 20% below Opus 5 — and tops Artificial Analysis's independent intelligence index at 58.
Agentic Code Migration: GitHub's 800K-Line Rust Port
GitHub's coding agents rewrote 430,000 lines of TypeScript into 832,000 lines of production Rust in 14.5 weeks, at a 96% prompt-cache hit rate.
Jev Is a New AI Model That Answers in Probabilities
TypeSafe AI's Jev skips text generation entirely and returns calibrated probability scores instead, priced at $0.042 per million input tokens.
AndroidX Security State Tracks Patches by Component
Google's AndroidX Security State 1.1.0 lets apps check three patch levels per component, covering the OS, Play system modules and the kernel LTS version.
OpenAI Agents API: What the Codex Harness Gives You
OpenAI's Agents API is in public beta with durable sessions and nine sandbox partners, and it adds no extra fee — you pay only for tokens, tools and time.
Revocable API Keys Get an Open Standard Called ORKS
A draft open standard, ORKS, would let anyone who finds a leaked API key revoke it instantly — no account, no ticket, no waiting for a reply.
Commerce Agent Blueprints Let Retailers Ship in Days
Anthropic's commerce agent blueprint ships reference code for shopping and merchant agents, with early users reporting carts up to 35% larger.
ArduinoCore-Zephyr 1.0 Adds VENTUNO Q and 11 Boards
ArduinoCore-Zephyr 1.0.0 leaves beta with Zephyr 4.4.1, VENTUNO Q support, Nicla Vision camera capture and 40+ fixes across eleven Arduino boards.
Gemini Agentic Video Understanding Cuts Tokens 88%
Gemini agentic video understanding cuts token use up to 88% and cost up to 66% while raising accuracy 7%, with no extra fee on the Gemini API.
Openterface KeyMod Turns Your Phone Into a Keyboard
The $42 Openterface KeyMod turns a phone into a USB keyboard, mouse, gamepad, or SSH terminal for any PC, server, or Raspberry Pi board, even at the BIOS.
Nordic nRF93M1 Dev Kit Brings LTE Cat 1 bis for $60
Nordic's nRF93M1 development kit pairs a 10 Mbps LTE Cat 1 bis modem with an nRF54L15 host MCU, and prices start at $60 with a trial SIM card.
GPT-5.6 Sol API Price Falls to $4 Per Million Tokens
OpenAI cut GPT-5.6 Sol API pricing on August 21: input drops 20% to $4 and output falls 33% to $20 per million tokens through November 21, 2026.
TrueForge Open Source Agent Harness Cuts Costs 75%
TrueFoundry's MIT-licensed TrueForge harness completed Enterprise-Bench tasks for $2.90 against $11.80, a 75% cost cut driven by context engineering.
Mojo 1.0 Compiler Goes Open Source Under Apache 2.0
Modular open-sourced the entire Mojo compiler and toolchain under Apache 2.0 at ModCon 2026, alongside 450,000 lines of GPU kernel code.
Palomar Registry Puts AI Math Proofs Under Lean Review
Palomar, incubated by the Lean FRO and ICARM, is now open for submissions and gives machine-checked math proofs a public registry with real metadata.
PwrBlock 323 Is a $230 Programmable USB-C PD Supply
The open-hardware PwrBlock 323 turns a 100W USB-C PD charger into a scriptable 1-32V bench supply for test fixtures, at $230 on Crowd Supply.
Embedding Models Guide: Dense vs Multi-Vector RAG
A practical 2026 guide to choosing embedding models for RAG: dense bi-encoders, multi-vector late interaction, and rerankers, with cost and memory math.
Hazmat Locks AI Coding Agents Out of Your SSH Keys
Hazmat is a free open-source tool that runs AI coding agents under a separate user with a kernel sandbox and firewall, keeping SSH keys out of reach.
Stripe Buys OpenRouter in a $7 Billion AI Gateway Deal
Stripe has agreed to acquire OpenRouter for more than $7 billion, more than five times the AI gateway startup's $1.3 billion valuation in May.
Kog Inference Engine Squeezes 30x From Existing GPUs
French startup Kog hit 3,000 tokens per second on standard AMD and NVIDIA datacenter GPUs, claiming a path to 30x faster LLM inference in software.
PyBLE Programs MicroPython Boards Over Bluetooth LE
PyBLE is an MIT-licensed MicroPython IDE for iPad and Android tablets that edits, runs, and debugs ESP32 boards wirelessly over Bluetooth Low Energy.
Chainloop Signs Every Artifact Your CI Pipeline Builds
Chainloop is an open-source evidence store that collects, signs, and policy-checks CI output across 17 formats including CycloneDX and SPDX SBOMs.
FLUX 3 Video Goes GA With 20-Second Clips and Audio
Black Forest Labs opened FLUX 3 Video to every developer on August 4: 20-second clips with natively generated audio, starting at $0.06 per second.
NVIDIA NOOA Turns an AI Agent Into One Python Class
NVIDIA open-sourced NOOA, an agent framework where a 253-line agent hits 82.2% on SWE-bench Verified using half the tokens of rival harnesses.
Token Monitor Shows AI Coding Usage on a 4-Inch Screen
Token Monitor is an ESP32-S3 desktop display tracking Claude Code, Codex CLI, and Antigravity quota, starting at 99 euros with an Apache-2.0 local broker.
CtrlVibe AI Console Keypad Starts at $109 on Kickstarter
CtrlVibe AI Console packs nine hot-swappable keys, a rotary encoder, and a three-way permission toggle into a CNC aluminum keypad starting at $109.
Cloudflare OS Open-Sources an Agent Workspace Platform
Cloudflare released Cloudflare OS as open source — an agent workspace with isolated code runtimes, a governance layer, and user-modifiable internal apps.
Stream32 Builds an Open-Source Stream Deck on ESP32
Stream32 pairs an ESP32 with a 4-inch or 10.1-inch touchscreen to make a fully customizable open-source Stream Deck alternative you can reflash yourself.
Groundcover Raises $100M for AI Agent Observability
Observability startup groundcover raised $100 million on July 29 at a $500 million valuation to monitor AI agents running live in production.
Cursor Router Auto-Picks the Cheapest Capable Model
Cursor Router, launched July 22, routes each coding request to the cheapest capable model, delivering frontier quality at up to 60% lower cost.
Gemini 3.6 Flash Trims Output Tokens by 17% for Devs
Google's Gemini 3.6 Flash uses 17% fewer output tokens at equal quality, costs $1.50 per million input, and jumps to 49% on the DeepSWE benchmark.
Microsoft Dusseldorf Brings Open-Source OAST to Your Servers
Microsoft open-sourced Dusseldorf, a self-hosted OAST platform catching 4 blind bug classes while keeping callback data on your own servers.
MIT's GIFT Turns 2D Designs Into CAD at 20% Compute
MIT's GIFT system converts a 2D image and text into executable CAD code using about 20% of the compute rival methods need, with no human labeling.
Gemini Notebook Replaces NotebookLM and Runs Your Code
Google renamed NotebookLM to Gemini Notebook and added secure cloud code execution, serving 30 million users and over 600,000 organizations.
CVE Lite CLI Scans npm Projects Right in Your Terminal
CVE Lite CLI, now an OWASP Incubator project, checks JavaScript lockfiles against the OSV database and suggests one-line fixes for npm, pnpm, Yarn, and Bun.
Cursor's First Mobile App Lets You Steer Coding Agents From Your Phone
Cursor launched its first mobile app on June 29, 2026, letting developers start and supervise autonomous coding agents from iOS or an Android PWA, anywhere they go.
Nano Banana 2 Lite Brings Fast, Low-Cost Image Generation
Google's Nano Banana 2 Lite delivers fast image generation at about $0.034 per 1,000 images, making high-volume AI visuals affordable for builders.
Grok Build's New Dashboard Lets Developers Run Coding Agents in Parallel
xAI's June 17 Agent Dashboard for Grok Build puts every coding session on one screen, surfacing the ones that need input so developers can orchestrate multiple AI agents at once.
Hugging Face Hub 1.18 Adds an AI Skills Marketplace to Its CLI
The new huggingface-hub 1.18 release introduces an 'hf skills' command, surfacing a growing marketplace of reusable AI skills for the open-source community.
Microsoft's MAI-Code-1-Flash Brings a Tiny, Fast Coding Model to Copilot's Free Tier
Microsoft launched MAI-Code-1-Flash on June 2, 2026 — a compact 5B-parameter in-house coding model now rolling out across GitHub Copilot, including the free tier.
Google's Gemini 3.1 Flash-Lite Goes GA — 2.5x Faster, $0.25 Per Million Tokens
Gemini 3.1 Flash-Lite hit general availability on May 7, 2026 with 2.5x faster Time to First Answer Token and $0.25/$1.50 per 1M tokens — the cheapest, fastest Gemini 3 model for high-volume AI workloads.
Anthropic's New 'Dreaming' Feature Teaches Claude Agents to Learn From Their Own Sessions
At Code with Claude on May 6, 2026 Anthropic shipped Dreaming, Outcomes, and Multi-Agent Orchestration — turning Claude Managed Agents into systems that review their own runs and improve over time.
OpenAI Drops Three Voice Models Into the API — GPT-Realtime-2, Translate, and Whisper
OpenAI shipped GPT-Realtime-2, Realtime-Translate, and Realtime-Whisper into the API on May 6, 2026 — bringing live voice reasoning, 70-language translation, and streaming transcription to developers.
Google Makes Gemini API File Search Multimodal With Page-Level Citations
Google's Gemini API File Search now indexes images alongside text, ties responses to original page numbers, and ships free storage and query embeddings — turning verifiable RAG into a one-call developer primitive.
Google Launches Gemini 3.1 Flash-Lite — A Lightning-Fast AI Model at Just $0.25 Per Million Tokens
Google DeepMind's new Flash-Lite model delivers 2.5x faster responses than its predecessor at a fraction of the cost, making production-scale AI deployment dramatically more affordable.
Model Context Protocol Goes Mainstream as OpenAI, Google, and Microsoft Adopt Anthropic's Standard
The protocol that lets AI systems connect to databases and tools is now governed by the Linux Foundation, with every major AI lab on board.