The Continuous-Improvement Stack for Agents
Detect failures, triage root causes, and ship fixes backed by production data.
Overview
Judgeval is an open-source Python SDK for agent improvement. It provides tracing and agent-judge evaluation for LLM-powered applications — so you can detect failures, understand what went wrong, and validate fixes against real production cases before shipping.
To get started, dive into the docs.
Why Judgeval
OpenTelemetry-based tracing -- Instrument any function with @Tracer.observe(). Automatically captures inputs, outputs, and LLM token usage. Built on OpenTelemetry for full compatibility with existing observability stacks.
Agent judges -- Define prompt-based scorers to evaluate agent behaviors at scale. Judges produce structured behaviors — scored, labeled outputs that describe how your agent acted — which accumulate into a searchable record of agent behavior over time. Run judges against live production traffic or replay them on historical traces to validate fixes before shipping.
Online monitoring -- Automatically score live production traffic server-side with no latency impact. Detected behaviors surface as structured signals — configure Slack alerts so regressions and recurrences never go unnoticed.
Broad integrations -- Auto-instrumentation for OpenAI, Anthropic, Google GenAI, and Together AI. Framework support for LangGraph, OpenLit, and Claude Agent SDK.
Quickstart
Install the SDK:
pip install judgeval
Set your credentials:
export JUDGMENT_API_KEY=...
export JUDGMENT_ORG_ID=...
Add observability to your agent with two lines of setup:
from judgeval import Tracer, wrap
from openai import OpenAI
Tracer.init(project_name="my-project")
client = wrap(OpenAI())
@Tracer.observe(span_type="tool")
def search(query: str) -> str:
results = vector_db.search(query)
return results
@Tracer.observe(span_type="agent")
def run_agent(question: str) -> str:
context = search(question)
response = client.chat.completions.create(
model="gpt-4o-mini",
messages=[{"role": "user", "content": f"{context}\n\n{question}"}],
)
return response.choices[0].message.content
run_agent("What is the capital of the United States?")
JQL
JQL queries use the same API key, organization, and project configuration as the rest of Judgeval. Tenant identifiers are not part of the query payload.
from judgeval import Judgeval
from judgeval.jql import spans
client = Judgeval(project_name="my-project")
result = client.query(spans().rows(), trace_ids=["trace-123"])
trace_ids and session_ids are mutually exclusive options outside the JQL
query object. Trace IDs narrow the query directly. Judgment resolves session IDs
within the authenticated organization and project, then narrows every part of
the query to their traces. If no session resolves, the request fails instead of
falling back to the whole project. Both options work with present() and
discover().
Use offline_traces() or offline_spans() to query traces captured by an
offline test:
from judgeval.jql import offline_traces
offline_result = client.query(offline_traces().rows())
Integrations
Supports OpenAI, Anthropic, Google GenAI, Together AI, LangGraph, OpenLit, and Claude Agent SDK. See the full integrations docs.
CLI
Manage agents, traces, judges, behaviors, and evaluations from the terminal. Query trace history, deploy judges, inspect detected behaviors, and run evals against production data — all without leaving your shell. See the CLI repo and docs.
MCP Server
Connect Judgment to any MCP-compatible AI tool. Query agent traces, invoke judges, browse detected behaviors, and surface failures directly inside your AI assistant or IDE. See the docs.
Links
Judgeval is created and maintained by Judgment Labs.
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 judgeval-1.3.2.tar.gz.
File metadata
- Download URL: judgeval-1.3.2.tar.gz
- Upload date:
- Size: 117.3 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via:
twine/7.0.0 CPython/3.11.16
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
dd3b7044fdadd054e462d1515fe09d940aea4e8463ea64c9ceed777bfe75b7ec
|
|
| MD5 |
b8dbd6e2ab3cd5bcf0e52d3702ae5bd5
|
|
| BLAKE2b-256 |
ca2d1da99b5384351c03b0d028ed4924d92cfa5c0895f50ae64df0999683156a
|
File details
Details for the file judgeval-1.3.2-py3-none-any.whl.
File metadata
- Download URL: judgeval-1.3.2-py3-none-any.whl
- Upload date:
- Size: 203.0 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via:
twine/7.0.0 CPython/3.11.16
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
f864304e3eb467633f1afc7c0aa29a8ad1b561bacf24886e796e04085b68d0c5
|
|
| MD5 |
bc9d9a86dada22ddb454896214c7f48f
|
|
| BLAKE2b-256 |
e32e0160557335935e9e3754527e07c87ee1946d07be58d5ea37571ba6a52497
|
