Live agent sessions
View current or recorded AI agent sessions together in one window instead of relying on separate views.
Agent Activity
Agent Activity is a macOS developer tool that shows AI agent sessions, build timelines, and test results for work in Xcode. It is designed for developers who want a local, account-free view of agent-driven development activity.
Overview
Agent Activity is a macOS developer tool for observing AI agent work in Xcode. It brings agent sessions, build timelines, and test results into one window so developers can review how an iteration unfolded—from builds and errors through fixes and a green result.
The app operates without an account and has no server of its own. According to the product page, transcript, message, build-log content, project name, and project path data stay on the Mac. Diagnostic sharing is optional and controlled through an initial prompt and Settings → Diagnostics.
Features
Build timelines
Follow the sequence of builds, errors, fixes, and successful outcomes to understand how an iteration progressed.
Test result tracking
See test results alongside the development activity associated with an agent session.
Local operation
Use the app without creating an account or routing project activity through a LeMax server.
Optional diagnostics sharing
Choose independently whether to send usage events and crash reports, with controls available in Settings → Diagnostics.
Use cases
Debugging an agent iteration
Review an agent-driven coding iteration after it finishes by tracing the build, error, corrective change, and successful test outcome in sequence.
Following active Xcode work
Monitor AI-assisted development activity from a single window while working in Xcode, rather than switching between separate status views.
Validating generated changes
Inspect test results in the context of the agent session that produced them when checking whether an automated change is ready for further review.
Local project oversight
Use the app as an account-free local activity view when project privacy is important and cloud-based session storage is not desired.
Pros and Cons
Pros
- Combines AI agent sessions, build timelines, and test results in one window.
- Provides a local, account-free workflow according to the product page.
- Makes the progression from build errors to fixes and passing tests easier to review.
- Offers independent controls for usage-event and crash-report sharing.
Cons
- The listed requirement is macOS 26 or later; the page does not document older macOS support.
- The product page does not specify supported Xcode versions, agent frameworks, or detailed setup steps.
- Optional diagnostic reports may include limited installation-path and crash-error details described in the privacy notice.
FAQ
What is Agent Activity?
Agent Activity is a macOS app for viewing AI agent sessions, build timelines, and test results related to work in Xcode. The page does not provide detailed setup or workflow instructions beyond the app's local operation.
What operating system does Agent Activity require?
The product page lists macOS 26 or later as the requirement. It does not specify additional Xcode version compatibility or supported agent tools.
Does Agent Activity require an account or send project data to a server?
No account is required. The app has no server of its own, and the product page states that transcript, message, build-log content, project name, and project path data do not leave the Mac.
What diagnostic data can Agent Activity share?
On first launch, the app asks whether to share usage events and crash reports. These choices are independent and can later be managed in Settings → Diagnostics. The page notes limited exceptions for record-type names, the app installation path in crash reports, and crash error messages.
Quick Facts
- Category
- Developer Tools
- Platform
- macOS
- Requirement
- macOS 26 or later
- Primary workflow
- Review AI agent sessions, builds, and test results in Xcode
- Account
- None required
- Product site
- le-max-app.com
Alternative a Agent Activity
ByteAsk
ByteAsk is a terminal-first AI coding agent for C and C++ that edits repositories and verifies changes with the real compiler, debugger, sanitizers, and tests before showing a diff. It offers a free tier plus paid plans, with editor connectors and zero-retention handling described in the source.
Manta AI
Manta AI is an autonomous web app testing tool for teams that want to map application behavior, catch regressions, and generate tests without writing scripts or maintaining selectors. It works from a URL and supports plain-English test flows, run results with screenshots, and scheduled or deployment-triggered checks.
PromptScout
PromptScout tracks how ChatGPT, Gemini, Google AI Overviews, and Perplexity mention your brand or competitors, then pairs those results with source analysis and website audits. It helps teams decide what to fix in content, positioning, or site readiness next.
CreateOS Sandbox
CreateOS Sandbox is an isolated compute environment for running code and agent workloads inside Firecracker micro-VMs. It is designed for workflows that need machine-level isolation, private networking between sandboxes, and programmatic control through SDK, CLI, or MCP.
Sleek Analytics
Sleek Analytics is a privacy-friendly web analytics tool with real-time visitor tracking, Core Web Vitals, and revenue attribution. It helps site owners understand traffic and conversions without cookie banners or a heavy setup.
GitBot
GitBot is a local browser-based workspace for creating reusable coding bots powered by Claude Code, Codex, or OpenCode. It helps developers run those agents across repository folders with persistent threads and configurable permissions.