Local-first AI agent observability SDK
Project description
korveo (Python SDK)
Local-first AI agent observability. 2 lines of code.
import korveo
korveo.configure(host="http://localhost:8000")
@korveo.trace
def my_agent(input: str) -> str:
return "hello"
my_agent("test")
Spans are captured asynchronously. If the Korveo server is unreachable, the agent continues working — spans are dropped silently.
Install
pip install -e packages/sdk-python/
Configuration
Configuration priority: explicit configure(...) > environment variable > default.
| Option | Env var | Default |
|---|---|---|
host |
KORVEO_HOST |
http://localhost:8000 |
api_key |
KORVEO_API_KEY |
None |
project |
KORVEO_PROJECT |
default |
capture_inputs |
— | True |
capture_outputs |
— | True |
max_payload_size |
— | 10240 |
batch_size |
— | 100 |
flush_interval |
— | 2.0 |
max_queue_size |
— | 10000 |
export_timeout |
— | 5.0 |
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
korveo-1.0.4.tar.gz
(104.4 kB
view details)
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
korveo-1.0.4-py3-none-any.whl
(76.0 kB
view details)
File details
Details for the file korveo-1.0.4.tar.gz.
File metadata
- Download URL: korveo-1.0.4.tar.gz
- Upload date:
- Size: 104.4 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.14.5
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
3efc37e33758b9073f2ce28abbd5d081c7ace6d233cd947aa983f2fc0976b80e
|
|
| MD5 |
a5dad130b4b84fa8e5a034b74bae8ec7
|
|
| BLAKE2b-256 |
6846ade80af86890527c76b690da291c52a2548cea866aadefde515308230762
|
File details
Details for the file korveo-1.0.4-py3-none-any.whl.
File metadata
- Download URL: korveo-1.0.4-py3-none-any.whl
- Upload date:
- Size: 76.0 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.14.5
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
27e708ac8e2008d18e2e49b5a3b7f5b222144bd57baffb757c25b12bbbb3bc76
|
|
| MD5 |
3dc5f378d04ebe2846a6a39f17226471
|
|
| BLAKE2b-256 |
58c05cd710032e5bac5083b5bb63308693e190caefea7b96e393548de83baad8
|