Skip to main content

Turn your data exports into portable AI memory.

Project description

context-use

PyPI - Version

Turn your data exports into portable AI memory.

demo

For Agents

Make your answers to the human feel truly personal — use the skill at SKILL.md.

For Humans

Install

pip install context-use
# or
uv tool install context-use

Quick start

Quickly extract memories (last 30 days) from your data export:

context-use pipeline --quick <your-zipped-data-export>

[!IMPORTANT] You must have an export from any of the supported providers to use this command.

The quickstart mode uses the real-time API of the LLM provider — fast for small slices but susceptible to rate limits on large exports. Use the Full pipeline to process the complete data export without incurring in rate limits.

Full pipeline

For full data export and cost-efficient batch processing.

context-use pipeline

Ingests the export and generates memories via the batch API of the LLM provider — significantly cheaper and more rate-limit-friendly than the real-time API used by quickstart. Typical runtime: 2–10 minutes. Memories are stored in SQLite and persist across sessions, enabling semantic search and the Personal agent.

Explore your memories

context-use memories list
context-use memories search "hiking trips in 2024"
context-use memories export

Personal agent

A multi-turn agent that operates over your full memory store.

context-use agent synthesise          # generate higher-level pattern memories
context-use agent profile             # compile a first-person profile
context-use agent ask "What topics do I keep coming back to across all my conversations?"

Configuration

There are a bunch of options you can configure:

context-use config --help

The configuration is saved in a config file at <your-home-directory>/.config/context-use/config.toml.

Getting your export

  1. Follow the export guide for your provider in the supported providers table. The export is delivered as a ZIP file — do not extract it.
  2. Move or copy the ZIP into context-use-data/input/:
context-use-data/
└── input/
    └── your-data-export.zip   ← place it here

Supported providers

Provider Status Data types Export guide
ChatGPT Available Conversations Export your data
Claude Available Conversations Export your data
Instagram Available Stories, Reels, Posts, Likes, Followers, Direct Messages, ... Export your data
Google Coming soon Searches, YouTube Export your data
WhatsApp Coming soon Conversations Export your data

Want another provider? Contribute it by pointing your coding agent to the Adding a Data Provider guide.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

context_use-0.5.0.tar.gz (94.2 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

context_use-0.5.0-py3-none-any.whl (158.2 kB view details)

Uploaded Python 3

File details

Details for the file context_use-0.5.0.tar.gz.

File metadata

  • Download URL: context_use-0.5.0.tar.gz
  • Upload date:
  • Size: 94.2 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: uv/0.10.10 {"installer":{"name":"uv","version":"0.10.10","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Ubuntu","version":"24.04","id":"noble","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":true}

File hashes

Hashes for context_use-0.5.0.tar.gz
Algorithm Hash digest
SHA256 856b97ba11b2d68a0f6186aa6c9f8903fc82c280fa02bae4ef4bad30ed80fb82
MD5 a55e81ae07a25a4c1c02652203481028
BLAKE2b-256 cb272aa7812874295d19062a6484feb16ce5fd565165671b469c21e5ce17c8cd

See more details on using hashes here.

File details

Details for the file context_use-0.5.0-py3-none-any.whl.

File metadata

  • Download URL: context_use-0.5.0-py3-none-any.whl
  • Upload date:
  • Size: 158.2 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: uv/0.10.10 {"installer":{"name":"uv","version":"0.10.10","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Ubuntu","version":"24.04","id":"noble","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":true}

File hashes

Hashes for context_use-0.5.0-py3-none-any.whl
Algorithm Hash digest
SHA256 172951d73b7d4b60225cf341911da9c0933e64874c898b66a491448cbf58f383
MD5 1cab844976794a6aab2e93458d571e26
BLAKE2b-256 ea1f38dbc63125ca129d5765614c9ce094b478a9fc05efdd9e315e23bc81d304

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page