Pack
Deterministically pack context before it goes on the wire — stop re-sending the same boilerplate, file contents, and system prompts.
TokenPak — local LLM proxy
Local. Context-lean. Measurable.
TokenPak is a local proxy that packs your LLM context before it hits the API — fewer repeated tokens on the wire, more reuse opportunities, and savings you can measure per-request.
TokenPak doesn't replace your AI stack.
It adds the missing logistics layer: packing, routing, reusable context, guardrails, orchestration, and per-request records.
Six capabilities
The logistics layer, as a capability grid.
Route
Send each request to the right model, with fallback rules you control.
Reuse
Recall and reuse context from local PAKs instead of rebuilding it every session.
Guard
Spend and safety guardrails run as a side-channel gatehouse across every request.
Dispatch
Coordinate scoped, multi-step and multi-agent work. Preview (alpha) — not yet in a published release.
Record
Every request leaves a local record — what was sent, reused, observed, and charged.
How a request flows
One linear path, packed and recorded locally before it leaves your machine.
- Raw context
- Packing Station
- Route
- Send
- Provider
- Record
Reuse feed: PAKs feed into the Packing Station — recall and reuse context instead of rebuilding it.
Gatehouse (Guard): spend and safety guardrails run as a side-channel overlay before Send.
Where TokenPak fits
TokenPak overlaps with tools you may already run — and adds a layer they don't. Run them together.
-
Your agent
Claude Code
Cursor · Cline
-
TokenPak (local)
pack · measure
guard · record
-
Your gateway
LiteLLM /
OpenRouter / …
-
Model provider
Anthropic · OpenAI
Google Gemini
Dispatch Center dashboard (preview) — orchestration for multi-step and multi-agent work, around the flow.
| Tool type | Overlaps on | TokenPak adds | Together? |
|---|---|---|---|
| Gateways / routers | routing | deterministic context packing + reusable PAKs | Run both. |
| Observability tools | measurement | pre-send packing + per-request context-level attribution | Run both. |
| MCP-based workflows | ecosystem coordination | a semantic contract (TIP) for packing, routing, cost, telemetry | Composes. |
Savings
Reduce the repeated context your agents re-send. Improve cache reuse. Receipt-backed measurement is coming from benchmarked workloads.
Open source & Pro
TokenPak's core is open source (Apache-2.0). Pro adds team dashboards, advanced routing, and enterprise controls.
Pro is delivered as the tokenpak-paid package via a separate index.
Latest release
Refreshed automatically on every release + on a daily safety-net schedule.
latest
### Added - **TokenPak Dispatch graduates from preview to a released feature.** The `tokenpak dispatch` command (intake/routing, Decision Inbox, run-ledger lifecycle, observability) now ships in the released `pip install tokenpak` package — the Dispatch engine, its registry/schema data, and the user guide are included in the wheel. Delivery/receipt remain an explicit post-alpha preview (no live station execution wired yet).
Documentation highlights
Curated entry points sourced from tokenpak/docs.
starter
Getting Started
Install TokenPak and see savings in one command.
starter
Installation
pip install options, OS notes, troubleshooting install failures.
starter
Claude Code guide
Route Claude Code through TokenPak with one environment variable.
starter
OpenAI SDK guide
Point the OpenAI Python SDK at TokenPak with OPENAI_BASE_URL.
starter
Anthropic SDK guide
Point the Anthropic Python SDK at TokenPak with ANTHROPIC_BASE_URL.
starter
Cline guide
Route Cline through TokenPak with a custom compatible base URL.
See savings in one command.
pip install tokenpak && tokenpak setup. No cloud component; credentials stay in your environment and provider flow.