Developer tools, APIs, SDKs, open-source libraries, and frameworks
40 stories in the last 7 days
OpenAI's new Agents API gives developers the infrastructure behind Codex and ChatGPT
OpenAI releases a public beta Agents API enabling developers to build autonomous cloud agents. The API lets agents run for hours, execute…
Amazon Quick is now generally available on desktop
Amazon Quick is a desktop AI assistant for teams that keeps data private. Amazon Quick is now generally available on macOS and Windows, a…
Build an end-to-end RFI questionnaire workflow using Amazon Quick Automate
Amazon Quick Automate streamlines RFI questionnaire workflows by reading multi‑tab workbooks from S3, using natural‑language prompts to e…
Model-agnostic PII detection with LLMs
A new model-agnostic PII detector turns any Bedrock LLM
Meta’s Muse AI works and creeps me out
Meta launches Muse, an AI assistant that handles shopping, emails, and trip planning. Muse claims to automate busywork by pulling data fr…
Cloudera and Mistral Partner to Bring Specialized, Sovereign Intelligence to Enterprise Data
Cloudera and Mistral partner to embed sovereign AI intelligence into enterprise data platforms. The collaboration integrates Mistral’s sp…
Introducing ChatGPT for Financial Services
ChatGPT for Financial Services is a specialized AI platform that blends GPT‑6 Astra with built‑in financial data. It delivers research, m…
Introducing the Agents API
Agents API is a managed service that lets developers build and launch cloud agents. It uses the Codex harness to provide orchestration, l…
Rebuilding AUTOMATIC1111 with Gradio Workflow
AUTOMATIC1111 is rebuilt as a Gradio workflow, offering a new interface for Stable Diffusion. The rewrite replaces the original web UI wi…
IBM releases SOTA Granite Time Series PatchTST-FM-r2 model with commercial-friendly license
IBM releases a state‑of‑the‑art time‑series model, Granite PatchTST‑FM‑r2, under a commercial‑friendly license. The new model builds on t…
Modernizing complex legacy code with AI agents.
Mistr
Hugging Face's new ML Intern lets anyone run machine learning experiments through a simple chat
Hugging Face introduces ML Intern, an AI assistant that lets users run machine learning experiments via chat. The tool plugs into the Hug…
OpenAI offers AI for chip design, touts cost advantage over open-source
OpenAI launches an AI tool for chip design that claims cost advantages over open-source. The new service targets chip design and life sci…
Govern models with MLflow and Amazon SageMaker AI Model Registry sync: Part 2
MLflow and SageMaker AI Model Registry now support cross‑account governance with hub‑and‑spoke and hybrid topologies
Govern models with MLflow and Amazon SageMaker AI Model Registry sync: Part 1
MLflow now syncs richer model metadata into SageMaker AI Model Registry. The integration pushes training metrics, evaluation results, inf…
Automated agent evaluation with Amazon Bedrock AgentCore and GitHub Actions
Amazon Bedrock AgentCore can now be evaluated automatically in GitHub Actions. The new pipeline deploys an AI agent and an OAuth‑protecte…
Adobe is trying to make its AI generators idiot-proof in Premiere
Adobe Premiere introduces a new Generative Media tool that lets editors create AI‑generated video and audio directly within the timeline.…
Introducing ChatGPT Images 2.5
ChatGPT Images 2.5 is a new image generation tool that turns ideas, sketches, and reference photos into polished visuals. The update impr…
1Password increases engineering productivity 21% with Codex
1Password uses Codex to boost engineering productivity by 21%. Engineers employ Codex to quickly build new features and internal tools, a…
The Frontier AEO Tracker: What Astra Chooses (and every other frontier model, and what you can do about it)
The Frontier AEO Tracker is a tool that monitors AI expenditure optimization trends. It is part of Astra's first project, focusing on AEO…
Clipnote
Clipnote is a tool that saves AI conversations for later retrieval. It lets users persist ChatGPT and Claude chats after closing the tab,…
OpenAI developer claims Astra boosted productivity so much it pulled some plans forward by six months
Astra is an internal OpenAI tool that boosts developer productivity. A developer claims it accelerated some plans by six months, showing …
Stripping safety guardrails from open-weight AI models is now a turnkey commercial service
A startup sells stripped‑down open‑weight AI models for offensive cybersecurity. Abliteration.ai offers access to GLM‑5.3 with its safety…
DocsAlot Visual Editor
DocsAlot Visual Editor is a visual documentation tool that supports Markdown and AI‑assisted edits. It lets users write, structure, and p…
Kit by Speakeasy
Kit is a coding agent runtime that lets Claude run code quickly and cheaply. It bundles a terminal client, an Agent Client Protocol serve…
AI Toolbox 3.0
AI Toolbox 3.0 is a browser extension that aggregates chats from ChatGPT, Claude, Gemini, and Grok into a single searchable interface. It…
Tadata
Tadata is an AI employee that lives inside Slack, automating tasks based on company context. It connects to your tools, learns your compa…
Using Blender with coding agents on macOS
Blender can be driven by ChatGPT Codex on macOS using its Python API.
OpenClaw Power, MacBook Simplicity: Five Days With Grok Bot
SpaceXAI’s Grok Bot matches OpenClaw’s programming power while offering a new abstraction level. The bot lets developers write code in a …
Ponytail
Ponytail is a plugin that helps coding agents write minimal code. It inspects whether a change is necessary, already exists, or can be re…
BrickForgerAI
BrickForgerAI turns prompts into buildable LEGO models in real time. The system generates an image and mesh, voxelizes the shape, tiles i…
GitWarren
GitWarren is a local code‑review app that lets developers use AI agents to inspect changes before committing. It works directly on the wo…
Hyperprobe
Hyperprobe is a debugging tool that lets AI agents probe live services without redeploying. It lets agents such as Claude Code, Codex, or…
The Pelican comparison grid for Astra is pretty interesting
GPT-6 Astra outperforms GPT-5.6 models in generating SVG pelican images. The new model uses fewer tokens across all reasoning levels, cut…
Deploy a multimodal WhatsApp ordering assistant with Amazon Bedrock AgentCore
Amazon Bedrock AgentCore powers a multimodal WhatsApp ordering assistant. The assistant handles text, voice notes, and real‑time voice ca…
Designing lifecycle policies for AgentCore memory
Amazon Bedrock AgentCore gains guidance for memory lifecycle management in long-running AI agents. The approach uses a nightly AWS Step F…
Run agent-driven Amazon SageMaker HyperPod operations with InstantStart
HyperPod InstantStart is an open‑source control plane that orchestrates Amazon EKS and SageMaker HyperPod. It enables agent‑driven operat…
How Intuit built an agentic disaster recovery assistant with Amazon Bedrock
EWOK Agent is an agentic disaster recovery assistant built by Intuit on Amazon Bedrock. It lets on‑call engineers trigger production fail…
Microsoft says virtually nobody was grabbing NYT articles through its chatbot
Microsoft Copilot rarely reproduces full sentences from news articles, according to new legal filings. The company analyzed 8.2 million c…
Project HydraFusion: Frontier quality via multi-model orchestration
HydraFusion is a multi-model orchestration feature for GitHub Copilot. It matches or exceeds the Opus 5 baseline while cutting estimated …