The integration puts a model built for typed decisions beside a conventional language model, including an experimental gate that can stop selected tool calls before they run.

3 min

Sep 17, 2026Tools

Launch Tools

UN Launches Data Commons to Put Global Statistics Within AI Reach

The open-source platform lets people and AI assistants query connected UN data in plain language. Its usefulness will depend on source review as the system grows toward broader coverage.

2 min

Sep 17, 2026Tools

Launch Tools

Mapbox Adds Live Maps and Route Controls for AI Agents

The BUILD release moves Mapbox beyond supplying location data: agents can now query places, assess traffic and alter parts of a mapping workflow. The remaining test is whether developers trust those tools with real-world decisions.

3 min

Sep 17, 2026Tools

Research Tools

Google Researchers Introduce Dream-RSI, Reporting 162x Fewer Agent Calls

The research framework treats an agent’s prior search tree as a reusable simulator, shifting policy experiments away from costly candidate evaluations. Its strongest reported savings come from benchmark comparisons with different underlying setups.

3 min

Sep 17, 2026Tools

Research Tools

Lambda Publishes an AI Evaluator for Multi-Turn Image Edits

The research argues that one overall image score misses the harder question: whether a model makes the requested change without damaging earlier edits or untouched content.

3 min

Sep 17, 2026Tools

Benchmark Tools

Mozilla.ai Benchmarks Local AI Servers, Finds Setup Drives Bigger Gains

Across three machines, matching model files narrowed most prompt-speed gaps. Build options, graphics toolchains and platform-specific decoding settings delivered the larger swings.

3 min

Sep 16, 2026Tools

Tools

Perplexity Publishes a Search Pipeline for Coding Agents Before They Edit Code

The cookbook turns documentation lookup into a saved, inspectable artifact—but it explicitly leaves the final migration judgment to the agent, repository review and tests.

3 min

Sep 16, 2026Tools

Research Tools

Stanford Publishes Paper2Agent to Turn Research Papers Into Working AI Tools

The Nature study packages a paper’s methods into an agent that can run workflows on new data. Its ADHD case study is a useful lead, not a lab-confirmed result.

2 min

Sep 16, 2026Tools

Launch Tools

Meta Adds Native Windows Support to Muse Code, Removing the Need for WSL

The command-line coding tool now supports Windows x64 and ARM64 systems, with a sandboxed default and an installer designed to work without administrator access.

2 min

Sep 16, 2026Tools

Open release Tools

AWS Open-Sources Pizza Bot to Manage AI Agents Outside the Chat Window

The self-hosted tool turns agent work into threads, review queues and approval requests. Its appeal is less waiting; its risk is letting errors and stale decisions sit unseen.

4 min

Sep 16, 2026Tools

Research Tools

Salesforce Introduces DarwinX, Reporting a Browser-Agent Score Jump to 93%

The framework searches for better prompts, tools and workflows around a fixed model. Its large benchmark gains depend on a harder operational requirement: reliable tests that catch regressions.

3 min

Sep 16, 2026Tools

Research Tools

Scale AI Details a Human-Routing Rule for Credit-Recovery Agents

The company says its pre-deployment system found more recoverable vendor credits by reserving analyst time for decisions where a mistake would be costly and hard to undo.

3 min

Sep 15, 2026Tools

Launch Tools

Ryan Greenblatt Launches an AI Hotline That Works Through Restricted Web Access

The service gives agents a route to report information even when they can only fetch web pages. But its fallback method puts messages into URLs, where they can be logged more widely than a standard submission.

3 min

Sep 15, 2026Tools

Launch Tools

Meta Lets AI Agents Set Up WhatsApp Business Through Chat

The new connection shifts account setup, template work and troubleshooting from a string of business tools into instructions an AI coding agent can carry out.

2 min

Sep 15, 2026Tools

Platform shift Tools

LlamaIndex Begins Stainless Exit, Seeking to Preserve SDK Interfaces

The hard part is not finding another generator. It is retaining the methods, types and behavior LlamaParse developers already use.

2 min

Sep 15, 2026Tools

Research Tools

Developers Turn a New Fruit Fly Brain Map Into Viral Simulations

The online experiments followed the release of a complete male fruit fly nervous-system map. The underlying resource is a scientific wiring diagram, not a functioning digital animal.

2 min

Sep 15, 2026Tools

Research Tools

IBM Research Says Its Agent Tool Cut a Repeatability Gap in Half

The workflow measures whether an agent succeeds every time, not just on average. Its promising gains come from IBM’s AppWorld tests, rather than evidence from live deployments.

2 min

Sep 15, 2026Tools

Launch Tools

OpenArt Launches Creative AI Arena That Splits Model Rankings by Job

The new public benchmark separates filmmaking, design, editing and lip sync. Its first results support that approach—but its undisclosed active prompts leave users with a trust question.

3 min

Load more stories18 more next