Skip to main content

Attestable LLM → This package is now `aiir`. Install: pip install aiir

Project description

attestable-llm

This package has been consolidated into aiir.

Install the real package

pip install aiir

What is AIIR?

AI Integrity Receipts — lightweight cryptographic commitment records generated during AI inference that bind model identity, sampling configuration, and output tokens into a tamper-evident hash chain.

  • Zero external dependencies (Python stdlib only)
  • Receipt generation in < 100 µs
  • SHA-256 hash chains with O(1) amortized cost
  • Works with any model format (GGUF, ONNX, cloud APIs)
  • MCP server for Claude / Copilot / ChatGPT integration

Links


This package (attestable-llm) exists to redirect users to the canonical aiir package. Installing it will automatically install aiir as a dependency.

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

attestable_llm-0.0.1.tar.gz (1.7 kB view details)

Uploaded Source

Built Distribution

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

attestable_llm-0.0.1-py3-none-any.whl (2.2 kB view details)

Uploaded Python 3

File details

Details for the file attestable_llm-0.0.1.tar.gz.

File metadata

  • Download URL: attestable_llm-0.0.1.tar.gz
  • Upload date:
  • Size: 1.7 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.11.0rc1

File hashes

Hashes for attestable_llm-0.0.1.tar.gz
Algorithm Hash digest
SHA256 ac7edcc8a6fa1c34b4dc449d6b61ee4f11ad9953ac403dcfa004809aa7c48bcc
MD5 c5569cb1035572c3a1eb93ae8b1d9ca6
BLAKE2b-256 58ba03f16715ed1c252e5832665464db0d55e234508003c499767667d7f36391

See more details on using hashes here.

File details

Details for the file attestable_llm-0.0.1-py3-none-any.whl.

File metadata

  • Download URL: attestable_llm-0.0.1-py3-none-any.whl
  • Upload date:
  • Size: 2.2 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.11.0rc1

File hashes

Hashes for attestable_llm-0.0.1-py3-none-any.whl
Algorithm Hash digest
SHA256 ff90c255e5bcde2e75438c90e0e1087f5b9cb2a4e04a0bf267ab68637323f153
MD5 3ebe6227e4c6d8352c68786f8e9beb66
BLAKE2b-256 e5bdfc02ee1bc4dd93d17810cd173485b665492fe9a0c4d351727cff2753a702

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