Orqis Agent SDK
One line to stream your AI agent's traces to Orqis — autonomous self-healing ops for AI agents.
Install
pip install orqis-agent-sdk
Use
import orqis
orqis.init(api_key="orqs_your_workspace_key")
That's it. Every OpenAI, Anthropic, and LangChain call in your process is captured and streamed to your Orqis workspace, where incidents are detected and fix PRs are proposed automatically. Nothing else in your code changes.
Get your API key from your workspace Settings -> API keys.
Configuration
| Argument / env var | Default | Purpose |
|---|---|---|
api_key / ORQIS_API_KEY |
- | Routes traces to your workspace |
backend_url / ORQIS_BACKEND_URL |
hosted Orqis | Point at a self-hosted backend |
The SDK never blocks or crashes your agent: events are queued on a background daemon thread and dropped silently if the backend is unreachable. All detection, root-cause analysis, and patch generation happen server-side — none of that logic ships in this package.
License
MIT
1 maintainer
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 orqis_agent_sdk-0.1.4.tar.gz.
File metadata
- Download URL: orqis_agent_sdk-0.1.4.tar.gz
- Upload date:
- Size: 18.5 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via:
twine/6.2.0 CPython/3.9.6
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
7e3decabbfad4fa5980513f44e2d6bbcb27dadcd3bf76025f7e101d1f8de6346
|
|
| MD5 |
50c63268a324e27e5110ccc86f110dc8
|
|
| BLAKE2b-256 |
9b2f22036033e0212597e782059536f237c63ebe6db4373a3ee81bc059b79988
|
File details
Details for the file orqis_agent_sdk-0.1.4-py3-none-any.whl.
File metadata
- Download URL: orqis_agent_sdk-0.1.4-py3-none-any.whl
- Upload date:
- Size: 22.6 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via:
twine/6.2.0 CPython/3.9.6
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
ca51e656fa3bea816d55e5db06727581007a2729bdc2c48c0e0a231eefec8252
|
|
| MD5 |
646f44649fd64cd8f6aefbd490964385
|
|
| BLAKE2b-256 |
aa9f47bac2728f7bde45e3c51f2af3ef26163bb90d9b7e64972bbd8df3b6bd3a
|
