{
  "markdown": "<div align=\"center\">\n  <img src=\"https://actvt.io/actvt-glass-logo-96.png\" width=\"96\" height=\"96\" alt=\"Actvt\">\n  <h1>Actvt</h1>\n  <p><strong>A macOS app that monitors your Mac and your AI coding agents in one place.</strong></p>\n  <p>\n    <a href=\"https://actvt.io\">Website</a> ·\n    <a href=\"https://actvt.io/docs\">Docs</a> ·\n    <a href=\"https://actvt.io/changelog\">Changelog</a> ·\n    <a href=\"https://actvt.io/roadmap\">Roadmap</a>\n  </p>\n</div>\n\n<img src=\"https://actvt.io/actvt-desktop-light.webp\" alt=\"Actvt showing CPU, GPU, memory and network cards alongside recent Claude Code sessions\">\n\nActvt shows live CPU, GPU, memory and network for your Mac. It also reads the Claude Code and\nCodex session transcripts already sitting on your disk, so you can search them, see what they\nactually cost, and pick one back up where you left it.\n\nIt ships an embedded **MCP server**, so your agents can query the machine they are running on.\n\n## Download\n\n**[Download for Apple Silicon](https://actvt.io)**. Requires macOS 15.5 or later.\n\nThe current release is **1.1.6**. Updates are delivered in-app through the Sparkle appcast in\nthis repository.\n\n## What it does\n\n**System monitoring.** CPU, GPU, memory and network with live graphs, usage breakdowns and\ntemperatures. History is persisted across restarts.\n\n**Agent sessions.** One browser for every Claude Code, Codex and Claude Desktop session. Full\ntranscripts with thinking blocks and tool calls, outline navigation, search across everything,\nand one-click resume back into your terminal. Sessions are tagged by where they started, so a\nrun in Ghostty is distinguishable from one in Cursor.\n\n**Cost and usage analytics.** Total spend, token counts, cache hit ratio, spend by project,\ntool usage, and a daily activity heatmap. Plan usage bars show how much of your Claude and\nCodex quota is left and when it resets.\n\n> Spend is calculated at **API token pricing**. On a flat-rate plan that figure is not your\n> bill. It is what those tokens would have cost at API rates, which is a useful read on what\n> you are getting out of the plan.\n\n**Remote sessions.** Reach over SSH to other Macs and headless Linux boxes and fold their\nsessions into the same timeline. Tailscale peers are discovered automatically. Install the\nhelper on each host with one command, no sudo required.\n\n```sh\ncurl -fsSL https://actvt.io/install-cli.sh | sh\n```\n\n**Notifications.** Get told when a session is waiting on your input, finishes, errors, runs\nlong, or crosses a cost threshold. Clicking a notification raises the exact terminal or editor\nwindow that session lives in.\n\n**Sensitive data detection.** Transcripts are scanned for emails, credentials, payment cards,\nIDs and other sensitive spans. Every scan runs **on-device and offline**. Values are masked by\ndefault.\n\n**Port manager.** List every listening TCP port with the process behind it, and reclaim one\nwithout leaving the app.\n\n## MCP server\n\nActvt embeds a Model Context Protocol server. One click connects it to your installed Claude\nCode and Codex CLIs, after which your agents can ask Actvt about the machine they are running\non. The server is local and protected by an auth token.\n\n| Group | What agents can query |\n|---|---|\n| **System** | CPU, GPU, memory, network, thermal pressure, uptime, and persisted history |\n| **Ports** | Every listening port and its owning process. `port_kill` reclaims one. It refuses protected, system and AI-agent processes, and re-verifies the target before acting |\n| **Agent sessions** | Cost and token roll-ups, full-text transcript search, error-pattern triage, and resume cues. Remote-aware, so sessions on your other machines are visible too |\n\nA practical use is diagnosis. An agent can ask whether a slow session was the model thinking or\nthe Mac thermal-throttling, and get an answer grounded in what actually happened.\n\nRaw transcripts stay behind an explicit opt-in, and detected sensitive data is masked.\n\n## Privacy\n\nActvt reads session files that are already on your machine and scans them locally. Sensitive\ndata detection runs entirely on-device with no network access. Remote sessions travel over your\nown SSH connection, are held in memory while you read them, and are never written to the local\nindex. Plan usage bars read the quota your provider already reports using your CLI's own login,\nand Actvt never modifies those credentials.\n\n## Pricing\n\nActvt is free to use. A 7-day trial unlocks everything.\n\n| | Free | Basic | Premium |\n|---|---|---|---|\n| System monitoring, ports, notifications, shortcuts | ✅ | ✅ | ✅ |\n| Agent session browser and transcripts | Last 72 hours | 30 days | Full history |\n| On-device sensitive data detection | Within window | Within window | ✅ |\n| Remote sessions over SSH (up to 3 hosts) | No | ✅ | ✅ |\n| Custom Lottie menu bar icons | No | ✅ | ✅ |\n| Cost and token Overview, plan usage bars, GPU menu bar | No | No | ✅ |\n| MCP server, system and port tools | ✅ | ✅ | ✅ |\n| MCP server, agent session tools | No | No | ✅ |\n\nBasic is a **$9.99 one-time** purchase. Premium is **$7.99/month** billed annually.\n\n## About this repository\n\nThis repository is the public release channel for Actvt. It hosts the Sparkle `appcast.xml`\nthat drives in-app updates, and `pricing.json`, the model pricing table Actvt uses to compute\nsession costs. **The application itself is closed source** and is not distributed here.\n\nFound a bug or have a request? Open an issue.\n\n---\n\nBuilt by [Oye Collective](https://actvt.io). Localized in English, French and German.\n",
  "bytes": 5529,
  "sha": "da6b8dffc79271bb751b9fe99ec150784ba953565dab76a98383be7a6f1fc7f1",
  "repo_slug": "oye-collective/actvt-macos-releases",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_io_actvt_actvt_d502be4e/readme"
}