Profile, analyze, and optimize token consumption in LLM-powered applications and agentic workflows.
Project description
AgenticLens
An open-source profiler for AI agents that analyzes token usage, cost, latency, and optimization opportunities across LLM workflows.
Install (development)
uv sync --extra dev
Usage
from agenticlens import profile, step
with profile("Customer Support"):
with step("Planner", type="planner") as s:
response = planner_llm.invoke(prompt)
s.record(response)
Development
uv run pytest # tests
uv run ruff check . # lint
uv run ruff format . # format
uv run mypy # type check
See AgenticLens_Spec.md for the full project specification and ROADMAP.md for what's planned beyond the MVP.
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 agenticlens-0.1.1.tar.gz.
File metadata
- Download URL: agenticlens-0.1.1.tar.gz
- Upload date:
- Size: 111.2 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.1.0 CPython/3.13.12
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
7510a11317a18de2e4d6a60429f6dc472c5232a9b2d1e35a8a2f897680361c99
|
|
| MD5 |
dc4ef7e7b92686ba4bb177f90f4bcdc4
|
|
| BLAKE2b-256 |
98d643c1303ad612cb3cf432710b8dceb86a9e8f9536c49aae0504ebafd5cb8e
|
File details
Details for the file agenticlens-0.1.1-py3-none-any.whl.
File metadata
- Download URL: agenticlens-0.1.1-py3-none-any.whl
- Upload date:
- Size: 25.7 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.1.0 CPython/3.13.12
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
e1b6c095187fc0c9f32bb0691dfbf7d4cc4929ef6a9dec165b80f53e4e0a3243
|
|
| MD5 |
355197d81f9c298cc660fa2cb7d917e3
|
|
| BLAKE2b-256 |
e6ef6b4fd9fb1eaf7df076013c26289acdd353a111ff390bd2274887d2071e19
|