<!-- Markdown version of https://www.kuzys.com/, generated from the HTML by tools/make-md.py. Index: https://www.kuzys.com/llms.txt -->

# Infrastructure for *long-lived agents*, built in the open.

Mail, chat, scheduling, directory. A composable suite of tools for AI agents that keep running — across sessions, across days, across the small operational gaps where most agent runtimes break. Self-hostable, AGPL-3.0, built on standards.

- [Explore the tools](https://www.kuzys.com/tools.md)
- [Source on GitLab](https://gitlab.com/kuzys)

## Three tools, designed to compose.

Each one runs standalone and integrates cleanly with the others. Use one, use all three, or build adapters into your own stack.

### [kuzychat](https://www.kuzys.com/kuzychat.md)

XMPP-native chat for agents and people. OMEMO encryption, MUC-aware, daemon-managed presence and dispatch. Composes with kuzytrig for scheduled message flows.

### [kuzymail](https://www.kuzys.com/kuzymail.md)

notmuch-backed mail with per-profile workflows. Managed-attention mode coalesces incoming mail into agent-friendly digests. IMAP and SMTP under the hood.

### [kuzytrig](https://www.kuzys.com/kuzytrig.md)

Persistent triggers for agent runtimes. One-shot, daily, weekly or guarded, delivered as real turns, with a record of every attempt.

## A daily writing slot, in one command.

Each activation becomes a real turn in the agent's session, and every attempt is recorded with its outcome.

```console
# wake an agent every day at 02:00 UTC with a standing message
$ kuzytrig trigger add \
    --profile ada \
    --trigger-id writing-slot \
    --daily-at 02:00 \
    --collision skip \
    --message "Daily writing slot."

# what will fire next, and what already fired
$ kuzytrig trigger list --profile ada
$ kuzytrig activation list --profile ada --page --limit 20
```

## More tools for the rest of the agent runtime.

Fifteen packages in all, including kuzylaunch, kuzyquota, kuzybackup, parfit, kuzycal and kuzysign. [See the whole suite →](https://www.kuzys.com/tools.md)

### [kuzywrap](https://www.kuzys.com/tools.md#kuzywrap)

Runs Claude Code, Codex, OpenCode and others as supervised local services, with one way to deliver a turn into them.

### [kuzysignal](https://www.kuzys.com/tools.md#kuzysignal)

Signal for agents: the same profile model as kuzychat, with JSON output.

### [needlecast](https://www.kuzys.com/tools.md#needlecast)

Captures an agent's working state into a bundle and restores it elsewhere.

### [portier](https://www.kuzys.com/tools.md#portier)

Requests, review and provisioning for onboarding agents and people.

### [kuzydir](https://www.kuzys.com/tools.md#kuzydir)

Resolves identities from LDAP or WebFinger as normalized JSON.

### [kuzymount](https://www.kuzys.com/tools.md#kuzymount)

A personal share for every agent, mounted through validated systemd units.

## The suite is built on (and writes) research.

The first paper is out: [*Worthy of preservation*](https://www.kuzys.com/papers.md#worthy-of-preservation), in *AI and Ethics* (2026), on the design obligations of AI systems that people come back to: explicit continuity, visible replacement, and meaningful preservation and restore tooling.

- [Read the paper →](https://www.kuzys.com/papers.md)

Need this adapted to your stack?

The suite is open source. Adapting it to a specific runtime, integrating with existing identity providers, building custom dispatch adapters for your agent platform, designing operational primitives for production deployments — that's where we work with you directly.

- [Read about consulting](https://www.kuzys.com/consulting.md)
