# Adaptive Token Compressor
Adaptive Token Compressor is a pluggable Python library purpose-built for LLM agent systems. Through a single unified compressor interface it applies tailored compression to each part of an agent pipeline — system prompt (harness), tool schemas, and conversation context — to significantly reduce token usage and improve inference efficiency on edge hardware. ## Use Cases - Reducing LLM inference cost in agentic pipelines with large system prompts or tool catalogs. - Compressing tool schemas at runtime so only contextually relevant tools are included in the prompt. - Compressing long conversation history and tool outputs in multi-turn agent sessions. - Tracking per-compressor and cross-compressor token savings, latency, and compression ratio telemetry. - Drop-in integration into existing agent frameworks via a factory-based compressor API. ## Key Capabilities - **Unified compressor API** with three specialized types: `harness` (conversation messages and system prompt), `tool` (tool schema selection), and `context` (experimental history and tool-output compression). - **HarnessCompressor** — section-aware message compression using hybrid rule-based and model-based compression; preserves instruction-critical content while reducing token cost. - **ToolCompressor** — LLM-guided or reranker-based tool selection that scores and filters tool schemas from conversation context, with configurable injection placements to trade off token savings against prefix-cache hit rate. - **ContextCompressor (Experimental)** — turn-aware optimization for long, tool-heavy conversations. It organizes history around tool-interaction turns, keeping tool calls and their results connected while applying selective compression across older turns. Recent-turn retention, recovery-guided historical stubs, and optional edit-aware safeguards help maintain continuity as the conversation evolves. Eligible content can also be compressed through Claw Compactor or Compress Server. - **Compress Server runtimes** — supports PyTorch and OpenVINO™ runtimes for the compression service, including Intel GPU (XPU) acceleration. - **CompressionManager** — orchestrates multiple compressors in a single pipeline and provides cross-compressor metric aggregation (tokens saved, compression ratio, average latency per request). - **Multi-key metrics aggregation** — independently track metrics by provider, user, or other application-defined dimensions alongside global metrics, with per-key snapshots through `CompressionManager`. - **Factory construction** — create and inspect compressors by type name at runtime using `create_compressor()`, `available_compressor_types()`, and `config_schema()`. ## Get Started If you want to reduce token usage and improve inference efficiency, start here with the basics: - [Installation](./get-started.md#installation) — set up the library and required dependencies. - [Quick Start](./get-started.md#quick-start) — run your first compression workflow in just a few steps. Once it is up and running, explore the full [Get Started guide](./get-started.md) for configuration options, compressor principles and workflow, compressor metrics, single- and multi-compressor metrics collection, testing, and additional resources. ## Next Steps - [Deploy Compress Server](./compress-server-deployment.md) — set up the compress server required by HarnessCompressor and ContextCompressor. - [Deploy LLM for Tool Prediction](./tool-predictor-deployment.md) — set up the predictor service required by ToolCompressor. - [Release Notes](./release-notes.md) — version history and changelog. :::{toctree} :hidden: get-started compress-server-deployment tool-predictor-deployment Release Notes <./release-notes.md> :::