Skip to main content

pytest for AI agents — trace, debug and catch regressions in LLM swarms

Project description

Tracely

Open-source AI observability framework. Trace, debug and detect regressions in LLM apps with one decorator.

Install

pip install tracely

Usage

from tracely import observe

@observe def my_agent(question): return llm.chat(question)

Features

  • One decorator, zero config
  • Latency tracking
  • Error capture
  • AI-powered regression detection
  • CLI: tracely view
  • Works with any LLM

Why Not LangSmith?

LangSmith Tracely
Open Source No Yes
Any Framework No Yes
Self-hosted No Yes
Regression Detection No Yes
Setup Complex One decorator

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

swarmtrace-0.1.0.tar.gz (5.7 kB view details)

Uploaded Source

Built Distribution

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

swarmtrace-0.1.0-py3-none-any.whl (7.1 kB view details)

Uploaded Python 3

File details

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

File metadata

  • Download URL: swarmtrace-0.1.0.tar.gz
  • Upload date:
  • Size: 5.7 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.12.11

File hashes

Hashes for swarmtrace-0.1.0.tar.gz
Algorithm Hash digest
SHA256 76a9215cd884f3d6d72cf0a6ae03bbc711fcba2781fba937ea9b95e06ab3c02e
MD5 674b36030439f8c15913631665f9ce1a
BLAKE2b-256 dcb9d3da717ec44b8956bc8b3ac9093a73ac66b84399671eb1091ef7814e8f11

See more details on using hashes here.

File details

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

File metadata

  • Download URL: swarmtrace-0.1.0-py3-none-any.whl
  • Upload date:
  • Size: 7.1 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.12.11

File hashes

Hashes for swarmtrace-0.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 18839f00ed73bef1dde36ea05af290805ed04e746eb4371012c5250a9e70bff6
MD5 eadcf69079c2d966f16f044e218adc0f
BLAKE2b-256 11122f19ad5f960fcecc9d5deae529a2f1e5bfc2aa51821b9ee73f48f3ffb739

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