Compress Context.Cut Cost. Improve performance.

Context GatewayGitHub Stars

🎯 Request-Tailored Context for LLMs

Question-specific context compression with our proprietary algorithm.

Outperforms traditional retrieval baselines.
Integration via our SDK in minutes.

Open Source

🤖 Agent Proxy for Context Control

Route agent traffic through a proxy: full control over context.

Compress context before model calls: conversation state, tool traces, retrieved information.
Use for free with a vanilla compressor or upgrade to compresr for best results.

Get started in minutes

Drop-in addition to your current context management workflow.

Get Your API Key

Create an API key from your console.

setup.sh

# Your API key: cmp_...
export COMPRESR_API_KEY="cmp_..."

Install the SDK

Install the official Python library. Works with Python 3.8+.

terminal

pip install compresr

Upload Documents (Under development)

Use a dedicated ingestion client to upload documents into a named collection.

index_docs.py

from compresr import DocumentIngestionClient

ingestion = DocumentIngestionClient(api_key="cmp_...")

upload_result = ingestion.upload_to_collection(
    collection_name="my-meetings",
    files=["./Sam_Nov22.pdf", "./Dario_Feb5.pdf"]
)

Ready to Use

Compress your context and use it with any LLM of your choice.

compression.py

from compresr import CompressionClient

client = CompressionClient(
    api_key="cmp_..."
)

result = client.generate(
    use_collections=["my-meetings"],  # Pre-uploaded context
    context="Your context...",  # In-line context ingestion
    question="User's question...",
    compression_model_name="compresr_v1",
)

print(result.data.compressed_context)