Skip to main content

Visceral Python SDK — runtime optimization layer for AI agents

Reason this release was yanked:

had a bug

Project description

Visceral Python SDK

visceral — runtime optimization layer for AI agents. Wrap your LLM client and Visceral observes traffic, finds wasted work, and proves a cheaper call is safe before making it. Fails open: if Visceral is unreachable, your agent runs exactly as before.

Install

pip install "visceral-ai[openai]"   # or [anthropic], [google], [all-providers]

Distribution name is visceral-ai; the import package is visceral. Requires Python 3.10+.

Usage

from openai import OpenAI
from visceral import wrap

client = wrap(OpenAI(), agent_id="my-agent")   # same client back, now instrumented

Set VISCERAL_API_KEY (and VISCERAL_BASE_URL if self-hosting).

Prompt and response text never leaves your process unencrypted: content is stripped or AES-256-GCM-encrypted with your per-workspace key before export, and spans that cannot be redacted are dropped, never sent.

Develop

pip install -e ".[dev]"
ruff check src/ tests/
pytest

License

Apache-2.0 — see LICENSE.

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

visceral_ai-0.1.0.tar.gz (36.7 kB view details)

Uploaded Source

Built Distribution

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

visceral_ai-0.1.0-py3-none-any.whl (25.2 kB view details)

Uploaded Python 3

File details

Details for the file visceral_ai-0.1.0.tar.gz.

File metadata

  • Download URL: visceral_ai-0.1.0.tar.gz
  • Upload date:
  • Size: 36.7 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.12

File hashes

Hashes for visceral_ai-0.1.0.tar.gz
Algorithm Hash digest
SHA256 ab944dcf5004ede68492cd716a7146379b437f1a583d2eb309b623c2d6bdd19a
MD5 5abf6449629f9db5065373af7c1daf6d
BLAKE2b-256 02e48751638a6edfe706747e6e49cdbc25c42ffe0eeee40d8ea8604309105e92

See more details on using hashes here.

Provenance

The following attestation bundles were made for visceral_ai-0.1.0.tar.gz:

Publisher: publish.yml on visceral-ai/visceral-py

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file visceral_ai-0.1.0-py3-none-any.whl.

File metadata

  • Download URL: visceral_ai-0.1.0-py3-none-any.whl
  • Upload date:
  • Size: 25.2 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.12

File hashes

Hashes for visceral_ai-0.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 7fbada0f3d6d4d3fb0ae9a57c2ff2346fdd490b180b1106762d1872311afda38
MD5 a9adbd3e251b3b9d92a8c0915b2e2777
BLAKE2b-256 1f23e545c2a566355c4e45ec2f3e6f6b4b742ab088defa395f7189e2c63df300

See more details on using hashes here.

Provenance

The following attestation bundles were made for visceral_ai-0.1.0-py3-none-any.whl:

Publisher: publish.yml on visceral-ai/visceral-py

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

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