aidialer — security grade SAFE, quality 70/100

Security audit verdict: SAFE · quality 70/100

Flagged: opens a tunnel service. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →

by akiani · Agent Tool · ★ 163

Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h

🔒 Is aidialer safe to install? View the security audit →

About aidialer

🤖 ☎️ AI Dialer 👉 A blog post explaining the work behind this project. Important Update As of 2025, major changes in Deepgram, ElevenLabs and OpenAI APIs has unfortunately rendered this codebase obsolete. The repo is kept merely as a code reference for handling real-time AI phone calls. Summary A full stack app for interruptible, low-latency and near-human quality AI phone calls built from stitching LLMs, speech understanding tools, text-to-speech models, and Twilio’s phone API Listen to example call Features The following components have been implemented and wrangled together in streaming fashion to achieve the tasks of low-latency and interruptible AI calls: ☎️ Phone Service: makes and receives phone calls through a virtual phone number (Twilio) 🗣️ Speech-to-Text Service: converts the caller’s voice to text (so that it can be passed to LLMs) and understands speech patterns such as when the user is done speaking and interruptions to facilitate interruptibility (Deepgram) 🤖 Text-to-text LLM: understands the phone conversation, can make “function calls” and steers the conversation towards accomplishing specific tasks specified through a “system” message (OpenAI GPT-o or...

aianthropicgenaillmopenaittstwilio

Quick Facts

Stars163
Forks50
LanguagePython
CategoryAgent Tool
LicenseMIT
Quality Score70.1918347945959/100
Last Updated2025-04-25
Created2024-06-18
Platformspython
Est. Tokens~28k

aidialer alternative? Top 6 similar tools

Looking for a aidialer alternative? If you're comparing aidialer with other agent tool tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.

  • agent-builder by strands-agents · ⭐ 424

    An example agent demonstrating streaming, tool use, and interactivity from your terminal. This agent builder c

  • mcp-server by strands-agents · ⭐ 293

    This MCP server provides documentation about Strands Agents to your GenAI tools, so you can use your favorite

  • neurolink by juspay · ⭐ 138

    The pipe layer of an AI nervous system — one interface connecting provider neurons to your application, across

  • sdk-typescript by strands-agents · ⭐ 693

    A model-driven approach to building AI agents in just a few lines of code.

  • giselle by giselles-ai · ⭐ 554

    Giselle: AI App Builder. Open Source.

  • c4-genai-suite by codecentric · ⭐ 173

    c4 GenAI Suite

More Agent Tool Tools

Explore other popular agent tool tools:

View all Agent Tool tools →

Popular Python Agent Tools

Frequently Asked Questions

What is aidialer?

aidialer is A full stack app for interruptible, low-latency and near-human quality AI phone calls built from stitching LLMs, speech understanding tools, text-to-speech models, and Twilio’s phone API.. It is categorized as a Agent Tool with 163 GitHub stars.

What programming language is aidialer written in?

aidialer is primarily written in Python. It covers topics such as ai, anthropic, genai.

How do I install or use aidialer?

You can find installation instructions and usage details in the aidialer GitHub repository at github.com/akiani/aidialer. The project has 163 stars and 50 forks, indicating an active community.

What license does aidialer use?

aidialer is released under the MIT license, making it free to use and modify according to the license terms.

What are the best alternatives to aidialer?

The top alternatives to aidialer on Agent Skills Hub include agent-builder, mcp-server, neurolink. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.

How this security grade is produced

Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.

The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.

Sources & who's responsible:

View on GitHub → Browse Agent Tool tools