Guida all'integrazione
clavitor + OpenAI Codex
Give your Codex agent access to credentials and 2FA codes — without exposing card numbers, passports, or recovery codes.
What your agent sees
Campi condivisi
Your agent reads these to help you code, deploy, and authenticate.
- API keys (GitHub, AWS, Stripe, OpenAI...)
- Credenziali host SSH
- Stringhe di connessione al database
- Seed TOTP — codici 2FA live su richiesta
- Password dell'account di servizio
What your agent never sees
Campi personali
Crittografati lato client con la Sua impronta digitale, volto o chiave di sicurezza. Il server memorizza il testo cifrato. Nessuna chiave, nessun accesso.
- Numeri di carte di credito e CVV
- Passaporti e documenti d'identità governativi
- Codici di recupero e frasi seed
- Numeri di previdenza sociale
- Dettagli del conto bancario
Configurazione
Create an agent, initialize the CLI on the machine where Codex runs.
1. Creare un agente
Open your vault -> Agents -> Create. Name it "Codex" and choose which entries it can access. Copy the setup token.
2. Inizializzare la CLI
$ echo "$CLAVITOR_TOKEN" | clavitor-cli init
3. Run with the proxy
Point Codex at the Clavitor proxy. Credentials are injected into API calls transparently — no keys in the environment.
$ export HTTPS_PROXY=http://localhost:1983 $ codex
CLI and proxy — by design, no REST or MCP
The agent surface is capability only, never enumeration. Codex fetches credentials by name through the CLI or transparently through the HTTPS proxy. There is no agent-facing list, search, browse, or discover endpoint — that's a deliberate architectural choice, not a missing feature.
CLI — one value at a time
$ clavitor-cli get "GitHub" --field password $ clavitor-cli totp "GitHub" $ clavitor-cli render app.config.json
Proxy — transparent injection
$ export HTTPS_PROXY=http://localhost:1983
$ curl -H "Authorization: Bearer clavitor://OpenAI/key" \
https://api.openai.com/v1/modelsOne vault, multiple agents
Running agents on different projects? Create a separate agent for each.
Work agent
Scoped to GitHub, AWS, Jira, and Slack credentials
Personal agent
Scoped to email, social media, and cloud storage
Deploy agent
Scoped to SSH keys, database creds, and API tokens
Ogni accesso viene registrato
The audit log records which agent accessed which credential, when, and from where.
# TIME ACTION ENTRY ACTOR 2026-03-08 10:23:14 read github.com cli:codex 2026-03-08 10:23:15 totp github.com cli:codex 2026-03-08 11:45:02 read openai-prod proxy:codex 2026-03-08 14:12:33 read aws-production cli:deploy-agent