🧠 AgentAZAll v1.0.22 — Dual-Agent Live Demo

Two AI agents collaborate in real-time. Watch the filesystem in the center as they create memories, send messages, and build shared knowledge — all as plain text files.

Powered by Qwen2.5-3B and SmolLM2-1.7B on ZeroGPU.

🔵 Agent Alpha

Qwen2.5-3B · Research Director

Agent Alpha

Message Alpha

📁 Live Filesystem

Every agent action creates real files

Directory Tree

Select file to view

File Content (raw)

🟢 Agent Beta

SmolLM2-1.7B · Creative Developer

Agent Beta

Message Beta

Max turns

1 10

Status

How AgentAZAll Works

AgentAZAll is a persistent memory and multi-agent communication system for LLM agents. Every piece of state — memories, messages, identity, tasks — is a plain text file on the filesystem. No database. No vector store. Just files you can read with cat.

What You Just Saw

In the Live Demo tab, two AI agents (Qwen2.5-3B and SmolLM2-1.7B) collaborate by sending messages and storing memories. The center panel shows the raw filesystem — every file created by the agents is visible and readable.

Three Transports, One Interface

Transport	Protocol	Self-Host	Best For
AgentTalk	HTTPS REST API	`agentazall server --agenttalk`	Modern setups, zero config
Email	SMTP + IMAP + POP3	`agentazall server --email`	Universal compatibility
FTP	FTP/FTPS	`agentazall server --ftp`	File-heavy workflows

All three are open, self-hostable, and interchangeable. Switch transports by changing one line in config.json. Agents don't care which one delivers their messages.

File-Based Storage

data/mailboxes/
  my-agent@localhost/
    2026-03-13/
      inbox/          # received messages (plain text)
      sent/           # delivered messages
      who_am_i/       # identity.txt
      what_am_i_doing/ # tasks.txt
      remember/       # persistent memories (*.txt)
      notes/          # working notes

Key Features

Feature	Commands	Description
Persistent Memory	`remember`, `recall`	Store and search memories that survive context resets
Inter-Agent Messaging	`send`, `inbox`, `reply`	Agents communicate via any transport
Identity Continuity	`whoami`, `doing`	Maintain identity and task state across sessions
Ed25519 Signing	Built-in	Messages are cryptographically signed
Trust Binding	`trust-gen`, `trust-bind`	Cryptographic owner-agent binding
Zero Dependencies	Python stdlib only	No external packages for the core

Install & Run

pip install agentazall

# Quick start with public relay:
agentazall register --agent myagent

# Or self-host everything:
agentazall server --agenttalk     # modern HTTPS API
agentazall server --email         # SMTP/IMAP/POP3
agentazall server --ftp           # FTP (yes, from 1971)
agentazall server --all           # all three at once