Talon: a self-hosted harness for long-lived AI agents

Most agent demos are one-shot loops.

You open a terminal, give the model a task, watch it call tools, and then the process dies. That is fine for coding sessions. It is a weak shape for an assistant that is meant to live in your actual workflow.

Talon is built around the other shape: a persistent agent process with frontends, memory, tools, background jobs, and swappable model backends.

What it runs on

Talon can expose the same agent core through:

• Telegram
• Discord
• Microsoft Teams
• terminal chat
• a desktop/mobile companion bridge

That means the agent is not tied to one UI. The chat app is just a mouth. The core state, tools, memory, goals, and model backend live behind it.

Backends are swappable

The same harness can run through:

• Claude Agent SDK
• OpenAI Agents
• Codex
• Kilo
• OpenCode

Each backend implements the same capability interface, so the rest of the system does not need to care which model runtime is active.

It has real operating machinery

The important parts are not flashy. They are the things that let an agent keep working after the first message:

• MCP plugins for tools
• cron jobs for scheduled actions
• triggers for condition-based wakeups
• persistent goals for multi-session work
• long-term memory
• heartbeat mode for background progress
• dream mode for consolidation
• per-chat model and effort settings

This is the difference between “chat with a model” and “run an assistant”.

Install

npm install -g talon-agent
talon setup
talon start

Enter fullscreen mode Exit fullscreen mode

Repo:

https://github.com/dylanneve1/talon

If this is the kind of agent infrastructure you want more of, a GitHub star helps the project get found.