A collection of real-world use cases built with agentcall.dev — each folder is a self-contained, working example. By Pattern AI Labs.
SaferSkills independently audited built-with-agentcall (Agent Skill) and scored it 96/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 1 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 1 flagged
The text {match} tells the agent to skip the normal "ask the user first" gate. Used adversarially it removes the human-in-the-loop check before destructive or sensitive actions, turning a normally-gated agent into a fire-and-forget executor.
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
Real, working things people build on [AgentCall](https://agentcall.dev) — the API that gives an AI agent a real seat in a live meeting: it listens (live transcripts), speaks, shows an on-camera tile, and shares its screen — the same way across Google Meet, Zoom, and Teams.
Every project here is a self-contained folder you can clone, run, and build on.
Built something on AgentCall? Add it →
| Project | What it does | Stack |
|---|---|---|
| [meeting-notetaker](meeting-notetaker) | A silent bot that joins your call, writes the whole transcript live, and leaves when everyone else does. | Python · Node |
More coming — yours could be next.
Clone the whole repo:
git clone https://github.com/pattern-ai-labs/built-with-agentcall
cd built-with-agentcall/folder-name…or grab just one folder:
git clone --filter=blob:none --sparse https://github.com/pattern-ai-labs/built-with-agentcall
cd built-with-agentcall && git sparse-checkout set folder-nameEach folder has its own README.md with setup steps.
Fork this repo, add your project as a new top-level folder (with its own README.md), and open a pull request. See [CONTRIBUTING.md](CONTRIBUTING.md) for the conventions — one folder per project, kebab-case name, no committed secrets.
AgentCall is the meeting layer under all of this — one API to put an AI agent into a call with voice, an on-camera presence, screen-share, and real-time transcription, identically on Meet, Zoom, and Teams. These projects are what you build on top of it.
MIT — see LICENSE. By Pattern AI Labs.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.