OSS beta — plain-English data-handling summary. This page describes what TokenPak does on your machine today. It is not a substitute for legal advice and has not been reviewed by counsel. TokenPak is a local proxy with no cloud component, so the disclosures here describe local file paths and opt-in escape hatches — not a service operated on your behalf.

Privacy

Last updated: 2026-04-23 (draft).

What runs where

TokenPak is a local proxy. Every compression, routing, caching, and telemetry decision happens on your machine. Your prompts, completions, code, and business data are not sent to any TokenPak-operated infrastructure — there is none to send them to. The one thing that does leave your machine is the LLM request you ask TokenPak to proxy: it travels to the upstream provider you configure, using your own credentials (see What leaves your machine below).

What we collect by default

By default, nothing: zero telemetry, no usage pings, no install counters. The opt-in debug and logging controls described below can expand what is stored locally on your machine when you enable them — they write only to local destinations (file, stdout, or your system's local syslog socket) and do not initiate any outbound network connection for logging purposes.

What TokenPak stores locally on your machine

A SQLite ledger at ~/.tokenpak/monitor.db (or ~/.tpk/monitor.db on fresh installs) with per-request metadata (model, token counts, latency, cost, cache-origin). Default retention: 90 days of rolling history.
Configuration at ~/.tokenpak/config.yaml (or ~/.tpk/config.yaml on fresh installs). Contains profile selection, port, compression knobs. Never contains API keys or prompts.

Optional debug/logging escape hatches — full disclosure

Several opt-in controls will expand what is stored locally if you turn them on. They are off by default. We disclose them here so you know exactly what each knob does before enabling it.

TOKENPAK_DEBUG=1 (env var): Enables verbose debug output on stdout/stderr and debug-level entries in local logs. Debug output may include request headers (never credential values — those are redacted at the logging boundary). Off by default.
TOKENPAK_LOG_ENABLED=1 + TOKENPAK_LOG_DESTINATION (env vars): Enables the structured request logger. Destinations: file (default path), stdout, syslog. Logger records request metadata — not prompt/response bodies unless store_prompts is also enabled. See TOKENPAK_LOG_LEVEL and TOKENPAK_LOG_RETENTION_DAYS for tuning.
telemetry.store_prompts = true (config flag): This flag stores prompt and response bodies to local disk. Off by default. Exists for debugging and benchmarking. When enabled, prompt/response content is written to the same retention store as metadata. Clients with regulated data should leave this off.

What leaves your machine

Only what you ask TokenPak to proxy:

LLM requests — forwarded to the provider you configured (Anthropic, OpenAI, etc.), using your credentials on the way out. TokenPak does not intercept, log to our infrastructure, or mirror the payload.

Third parties

TokenPak OSS has no sub-processors and no TokenPak-operated cloud boundary. Your prompts, completions, and credentials never reach TokenPak; the only network destination for the requests you proxy is the upstream LLM provider you configure (Anthropic, OpenAI, Google, etc.), reached using your own credentials.

Your controls

rm -rf ~/.tokenpak ~/.tpk removes every local artifact TokenPak has ever created (legacy + canonical paths).
Unset any optional escape-hatch env var to disable that source of data collection.
Uninstalling the package (pip uninstall tokenpak) stops all TokenPak execution on your machine.

Contact

Questions: hello@tokenpak.ai.