DAILY DROP · OCT 21, 2026

Today's drop: 3 new tools, 2 listing updates

The directory now lists 104 hand-checked tools. AI for IT & Cybersecurity grows to 28 tools with ServiceNow ITSM, the service desk platform you'll see in a huge share of IT job posts, and GhidraMCP, which lets an AI assistant work Ghidra for malware analysis practice. Kyutai's Pocket TTS joins Voice & Audio with voice cloning that runs on a plain CPU. Plus: Devin's plans and DeepSeek's open-source inference engine. Pricing only where the official page states it.

Previous drop: Oct 20, 2026 →

Get the weekly dropThe best new AI tools, one email a week. Free.

New in the directory 3

Browse all 104
Tool
Category
Price
Status
Link
ServiceNow ITSM (Now Assist)ServiceNow's IT service management platform (incident, problem, change and request management) with Now Assist AI that summarizes incidents, suggests fixes and drafts responses, plus AI agents on higher tiers. Shows up in a huge share of help desk and IT job posts. Anyone can get a free Personal Developer Instance with admin access to learn the platform.
Price Quote-based packages (Foundation, Advanced, Prime); free Personal Developer Instance for learning
checked 10/21
GhidraMCPOpen-source MCP server and plugin that lets an AI assistant drive Ghidra, the NSA's free reverse-engineering suite: decompile binaries, list functions, imports and exports, and rename methods and data as it works. About 11,400 GitHub stars; v2.0 shipped Oct 10, 2026 for Ghidra 12.1.4. Analyze malware samples only inside an isolated VM.
Price Open source (Apache-2.0); Ghidra is free; model usage billed by your AI provider
FREEchecked 10/21
Pocket TTS (Kyutai)Kyutai's open-source text-to-speech that runs on a plain CPU, no GPU needed, with voice cloning from a short audio clip and streaming output. Version 4.0 (Oct 20, 2026) adds small English models of 18.2M, 6.9M and 1.9M parameters (the 1.9M ones are experimental) plus standalone binaries that don't need Python. About 10,000 GitHub stars. Only clone voices you have permission to use.
Price Open source (MIT code; CC-BY-4.0 weights); voice cloning weights need a free Hugging Face terms click-through
FREEchecked 10/21

Why these three

  • ServiceNow ITSM calls itself the world's #1 IT service management software, and it's the ticketing system behind a large share of help desk and service desk job posts at bigger employers. Its Now Assist AI summarizes incidents, suggests solutions and drafts responses, and the Advanced and Prime packages add AI agents. Pricing is quote-only, but ServiceNow's Developer Program gives every member one free Personal Developer Instance with admin access, which is yours to keep as long as you keep using it. Log a few incidents, build a catalog item and write a knowledge article, and you'll have something concrete to talk about in an interview.
  • GhidraMCP connects an AI assistant to Ghidra, the NSA's free reverse-engineering suite, through MCP. The assistant can decompile functions, list imports and exports and rename things as it figures them out, which makes it a patient tutor for malware analysis practice. It has about 11,400 GitHub stars, and v2.0 shipped Oct 10 for Ghidra 12.1.4. Only open samples inside an isolated VM, and check what the AI tells you against the disassembly.
  • Pocket TTS from Kyutai is open-source text-to-speech that runs on an ordinary CPU and clones a voice from a short clip. Version 4.0, out Oct 20, adds English models of 18.2M, 6.9M and 1.9M parameters (Kyutai marks the 1.9M ones experimental) and ready-made binaries, so you don't need Python. The code is MIT and the weights are CC-BY-4.0, though the voice cloning weights sit behind a free Hugging Face terms click-through. About 10,000 GitHub stars. Only clone voices you have permission to use.

Listing updates

Checked on Oct 21, 2026 against official pages and announcements.

  • Devin: devin.ai/pricing still returns a 404, but Devin's billing docs list a Free plan, Pro at $20 a month, Max at $200 a month and Teams from $80 a month (full seats $40 each). The listing now shows the full lineup.
  • DeepSeek open-sourced DeepInfer (Apache-2.0), the inference framework behind its own DeepSeek V4.1 Flash service. It's built for data-center hardware (NVIDIA SM100 GPUs and Huawei Ascend 950 NPUs) and ships offline inference only, so it's for infrastructure teams rather than home labs. It passed 16,000 GitHub stars in its first days.

Category changes

  • AI for IT & Cybersecurity grows from 26 to 28 tools. The Breaking into IT guide adds the free ServiceNow Personal Developer Instance to the help desk step and GhidraMCP to the malware practice step.
  • Voice & Audio grows to 6 tools with Pocket TTS.

Checked, not listed

  • Phonon (Gradium): on-device TTS released Oct 20. The English 31M model is Apache-2.0; the 40M models are CC BY-NC (non-commercial). Promising, but its runtime repo is brand new, so we'll watch it.
  • MiniMax M3.1 Flash: still API-only. Open weights were reported for Oct 23 and hadn't appeared on Hugging Face as of this morning.
  • Cursory, VoiceManager and Write the F**king Manual: small new side projects. We couldn't confirm Cursory's token-savings claim and will revisit them once they have real traction.