pytest for AI agents — trace, debug and catch regressions in LLM swarms
Project description
swarmtrace
pytest for AI agents — trace, debug and catch regressions in LLM swarms
Install
pip install swarmtrace
Quick Start
from tracely import observe
@observe def my_agent(question): return llm.chat(question)
CLI Commands
swarmtrace # view all traces with rich colors swarmtrace-replay # replay any trace swarmtrace-export --format json # export to JSON swarmtrace-export --format csv # export to CSV
Features
- One decorator, zero config
- Multi-agent swarm tracing with parent/child tree
- Async + sync support
- Thread-safe (contextvars)
- Accurate token counting via tiktoken
- Cost tracking per agent
- Regression detection
- Failure replay
- Works with any LLM
Built at AMD Hackathon 2026
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
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file swarmtrace-0.1.2.tar.gz.
File metadata
- Download URL: swarmtrace-0.1.2.tar.gz
- Upload date:
- Size: 7.4 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.12.11
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
982af5a6b40a9d96f5fce2a5f00a0c7e37feb01281b9f199432c7041d9d0ab3f
|
|
| MD5 |
fdf1e51333e1c7e6e0af844465484fef
|
|
| BLAKE2b-256 |
b0f18cd27be1f4305b042733342ab27bea881cd8514ac06dfb54066689b13f4e
|
File details
Details for the file swarmtrace-0.1.2-py3-none-any.whl.
File metadata
- Download URL: swarmtrace-0.1.2-py3-none-any.whl
- Upload date:
- Size: 9.2 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.12.11
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
718413b70e307833829f9da66f0fc3e24d0f7a16056489ee23f3a0fd6b691fce
|
|
| MD5 |
9f1dd2c34d6efac19281952fa745a300
|
|
| BLAKE2b-256 |
b8cc15757496d8e52f66b5f77014beab7d8e0806a39cc534e23d7e3185376d46
|