headroom-ai 0.3.7

The Context Optimization Layer for LLM Applications - Cut costs by 50-90%

Headroom

The Context Optimization Layer for LLM Applications

Tool outputs are 70-95% redundant boilerplate. Headroom compresses that away.

---

Demo

---

Quick Start

pip install "headroom-ai[all]"

Simplest: Proxy (zero code changes)

headroom proxy --port 8787

# Claude Code — just set the base URL
ANTHROPIC_BASE_URL=http://localhost:8787 claude

# Cursor, Continue, any OpenAI-compatible tool
OPENAI_BASE_URL=http://localhost:8787/v1 cursor

Works with any language, any tool, any framework. One env var. Proxy docs

Python: One function

from headroom import compress

result = compress(messages, model="claude-sonnet-4-5-20250929")
response = client.messages.create(model="claude-sonnet-4-5-20250929", messages=result.messages)
print(f"Saved {result.tokens_saved} tokens ({result.compression_ratio:.0%})")

Works with any Python LLM client — Anthropic, OpenAI, LiteLLM, httpx, anything.

Already have a proxy or gateway?

You don't need to replace it. Drop Headroom into your existing stack:

Your setup	Add Headroom	One-liner
LiteLLM	Callback	litellm.callbacks = [HeadroomCallback()]
Any Python proxy	ASGI Middleware	app.add_middleware(CompressionMiddleware)
Any Python app	compress()	result = compress(messages, model="gpt-4o")
Agno agents	Wrap model	HeadroomAgnoModel(your_model)
LangChain	Wrap model	HeadroomChatModel(your_llm) (experimental)

Full Integration Guide — detailed setup for LiteLLM, ASGI middleware, compress(), and every framework.

---

Does It Actually Work?

100 production log entries. One critical error buried at position 67.

	Baseline	Headroom
Input tokens	10,144	1,260
Correct answers	4/4	4/4

Both responses: "payment-gateway, error PG-5523, fix: Increase max_connections to 500, 1,847 transactions affected."

87.6% fewer tokens. Same answer. Run it: python examples/needle_in_haystack_test.py

What Headroom kept

From 100 log entries, SmartCrusher kept 6: first 3 (boundary), the FATAL error at position 67 (anomaly detection), and last 2 (recency). The error was automatically preserved — not by keyword matching, but by statistical analysis of field variance.

Accuracy Benchmarks

Benchmark	Metric	Result	Compression
Scrapinghub Extraction	Recall	98.2%	94.9%
Multi-Tool Agent (4 tools)	Accuracy	100%	76.3%
SmartCrusher (JSON)	Accuracy	100%	87.6%

Full methodology: Benchmarks | Run yourself: python -m headroom.evals quick

---

How It Works

flowchart LR
  App["Your App"] --> H["Headroom"] --> LLM["LLM Provider"]
  LLM --> Resp["Response"]

Inside Headroom

flowchart TB
  subgraph Pipeline["Transform Pipeline"]
    CA["1. CacheAligner\nStabilizes prefix for KV cache"]
    CR["2. ContentRouter\nDetects content type, picks compressor"]
    IC["3. IntelligentContext\nScore-based token fitting"]
    QE["4. Query Echo\nRe-injects user question"]
    CA --> CR --> IC --> QE
  end

  subgraph Compressors["ContentRouter dispatches to"]
    SC["SmartCrusher\nJSON arrays"]
    CC["CodeCompressor\nAST-aware code"]
    LL["LLMLingua\nML-based text"]
  end

  subgraph CCR["CCR: Compress-Cache-Retrieve"]
    Store[("Compressed\nStore")]
    Tool["headroom_retrieve"]
    Tool <--> Store
  end

  CR --> Compressors
  SC -. "stores originals +\nsummary of what's omitted" .-> Store
  QE --> LLM["LLM Provider"]
  LLM -. "retrieves when\nit needs more" .-> Tool

Headroom never throws data away. It compresses aggressively and retrieves precisely. When it compresses 500 items to 20, it tells the LLM what was omitted ("87 passed, 2 failed, 1 error") so the LLM knows when to ask for more.

Verified on Real Workloads

Scenario	Before	After	Savings
Code search (100 results)	17,765	1,408	92%
SRE incident debugging	65,694	5,118	92%
Codebase exploration	78,502	41,254	47%
GitHub issue triage	54,174	14,761	73%

Overhead: 1-5ms compression latency.

---

Integrations

Integration	Status	Docs
compress() — one function	Stable	Integration Guide
LiteLLM callback	Stable	Integration Guide
ASGI middleware	Stable	Integration Guide
Proxy server	Stable	Proxy Docs
Agno	Stable	Agno Guide
MCP (Claude Code)	Stable	MCP Guide
Strands	Stable	Strands Guide
LangChain	Experimental	LangChain Guide

---

Features

Feature	What it does
Content Router	Auto-detects content type, routes to optimal compressor
SmartCrusher	Statistically compresses JSON arrays — preserves errors, anomalies, boundaries
CodeCompressor	AST-aware compression for Python, JS, Go, Rust, Java, C++
LLMLingua-2	ML-based 20x text compression
CCR	Reversible compression — LLM retrieves originals when needed
Compression Summaries	Tells the LLM what was omitted ("3 errors, 12 failures")
Query Echo	Re-injects user question after compressed data for better attention
CacheAligner	Stabilizes prefixes for provider KV cache hits
IntelligentContext	Score-based context management with learned importance
Image Compression	40-90% token reduction via trained ML router
Memory	Persistent memory across conversations
Compression Hooks	Customize compression with pre/post hooks
Query Echo	Re-injects user question after compressed data for better attention

---

Cloud Providers

headroom proxy --backend bedrock --region us-east-1     # AWS Bedrock
headroom proxy --backend vertex_ai --region us-central1 # Google Vertex
headroom proxy --backend azure                          # Azure OpenAI
headroom proxy --backend openrouter                     # OpenRouter (400+ models)

---

Installation

pip install headroom-ai                # Core library
pip install "headroom-ai[all]"         # Everything (recommended)
pip install "headroom-ai[proxy]"       # Proxy server
pip install "headroom-ai[mcp]"         # MCP for Claude Code
pip install "headroom-ai[agno]"        # Agno integration
pip install "headroom-ai[langchain]"   # LangChain (experimental)
pip install "headroom-ai[evals]"       # Evaluation framework

Python 3.10+

---

Documentation

Integration Guide	LiteLLM, ASGI, compress(), proxy
Proxy Docs	Proxy server configuration
Architecture	How the pipeline works
CCR Guide	Reversible compression
Benchmarks	Accuracy validation
Evals Framework	Prove compression preserves accuracy
Memory	Persistent memory
Agno	Agno agent framework
MCP	Claude Code subscriptions
Configuration	All options

---

Contributing

git clone https://github.com/chopratejas/headroom.git && cd headroom
pip install -e ".[dev]" && pytest

---

License

Apache License 2.0 — see LICENSE.