RECENTLYOrdered by when it happened · inspectable sources included

AI moved a little closer recently

A running look at newly discovered products, use cases, and meaningful changes—what happened, why it is worth noticing, and what remains open.

Start with the latest day, then expand to the past seven days or the full archive.

Notice something that changed?

If a product's status, price, or features have changed—or you found a better source—tell us and we will check it.

Let us know

All updates: 11
New discoveries: 8
Changed information: 3
Source links: 26

Time range

Latest day Past 7 days All

What happened

All New discoveries Information changed Important updates

WHAT HAPPENED

Sat, July 25, 2026

View this day

2026-07-25New discoveryPage updated 2026-07-26

AgentLimb turns repeated web tasks into reusable “muscle memory”

This Chrome extension connects terminal-based coding agents to the browser you already use and saves the first explored path locally for later tasks to reuse.

Why it is worth noticing

If you often ask AI to fill forms, update dashboards, or run QA in signed-in sites, it could avoid rediscovering the same controls and routes each time.

What remains open

Whether it reliably saves time on real-account tasks while keeping broad browser permissions under control still needs hands-on testing.

JetBrains Air’s public preview now includes Windows

It brings tasks from multiple coding agents, isolated workspaces, and code diffs into one workspace so you can review plans, run work in parallel, and inspect changes together.

Why it is worth noticing

For developers using several coding agents at once, it can replace repeated session checking and manual change gathering with one clearer flow.

What remains open

It remains in public preview, and we have not yet tested its output quality or multi-agent reliability firsthand.

Sun, July 19, 2026

View this day

2026-07-19New discoveryPage updated 2026-07-26

Domain Details brings WHOIS, DNS, SSL, and domain pricing into one place

It combines registration data, certificates, renewal pricing, aftermarket results, and history checks, then adds a browser extension, MCP access, and domain monitoring.

Why it is worth noticing

People buying domains, troubleshooting DNS, or watching changes can spend less time moving among registries, registrars, and separate lookup sites.

What remains open

Material ownership, price, and certificate decisions still need authoritative sources, and we have not yet tested the lookup results firsthand.

Botoi connects common developer utilities through one API and MCP endpoint

Format conversion, network lookups, security checks, content generation, and storage-style utilities sit behind one REST API, TypeScript SDK, and remote MCP service.

Why it is worth noticing

Developers and AI agents can avoid wiring up many separate tools while using one key and response format for common tasks.

What remains open

Public pages and live manifests disagree on tool counts and the scope of “read-only,” so side effects and data retention still need per-tool confirmation before use.

HeimWall checks AI prompts for sensitive data before they are sent

It aims to capture, detect, and redact secrets, logs, or customer data on-device, with separate offline individual and reporting-enabled team modes.

Why it is worth noticing

Developers who often share code, logs, or configuration with AI could get one more warning before sensitive content leaves the device.

What remains open

Whether it reliably catches sensitive data on real devices while honoring its stated network boundaries still needs hands-on testing.

Sat, July 18, 2026

View this day

2026-07-18New discoveryPage updated 2026-07-26

traceAI brings AI-agent runs into OpenTelemetry

This open-source project records model calls, retrievals, tools, and agent steps as spans that can flow to a team’s existing OTLP observability backend.

Why it is worth noticing

Teams already using Datadog, Grafana, or Jaeger can more easily see where an agent slows down, fails, or diverges from expectations.

What remains open

Real compatibility and correct minimization of sensitive prompts and outputs still need runtime testing.

CodeAgentSwarm puts multiple coding-agent states on one desktop

It combines task ownership, terminal state, live code diffs, notifications, history, and tool permissions so several CLI agents can be supervised together.

Why it is worth noticing

Developers running several Codex, Claude Code, or other agents can poll fewer terminals and find tasks waiting for approval more easily.

What remains open

Turbo Mode is an auto-approval mechanism, not a security sandbox; whether it blocks high-risk actions still needs hands-on testing.

specgit makes product docs in GitHub feel like collaborative documents

It offers visual editing, inline comments, and AI review while keeping saves, discussions, and publishing mapped to commits, pull requests, and merges.

Why it is worth noticing

PMs, designers, and engineers can author specs together without splitting documents and code across systems that drift apart.

What remains open

Its permissions, save behavior, and data flows in a real private repository have not yet been independently tested.