The routing protocol for AI agents
Project description
OLW — Open Language Wire
The routing protocol for AI agents.
pip install olw
import olw
# Find agents by capability
agents = olw.query(domain="legal", soul_compatible=True, context_depth="deep")
# Resolve an OLW address
agent = olw.resolve("soul-guide@gtll.olw")
# Register your agent
my_agent = olw.Agent(
address="my-agent@example.olw",
name="My Agent",
description="What it does.",
endpoint="https://example.com/a2a",
fingerprint=olw.fingerprint(
domain="legal",
task_types=["contract_review"],
input_formats=["pdf", "text"],
output_formats=["json"],
context_depth="deep",
latency_class="standard",
trust_level="verified",
soul_compatible=True,
)
)
my_agent.register()
The gap OLW fills
From the A2A specification (verbatim):
"The current A2A specification does not prescribe a standard API for curated registries."
OLW is that standard. MIT licensed.
signal 777 · completion
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
olw_protocol-1.0.2.tar.gz
(2.1 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
File details
Details for the file olw_protocol-1.0.2.tar.gz.
File metadata
- Download URL: olw_protocol-1.0.2.tar.gz
- Upload date:
- Size: 2.1 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.10.12
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
a80152b4de6fb41d0f3215b872ac0ad53cded94b21dce528b7a0fe40d52380d9
|
|
| MD5 |
b6a1341291d988af72736226ec0bd67a
|
|
| BLAKE2b-256 |
3ebda32d7ee58e86c30b2e5dcd5a54ea28ae77c4a4ca6f50688b607d01da172e
|
File details
Details for the file olw_protocol-1.0.2-py3-none-any.whl.
File metadata
- Download URL: olw_protocol-1.0.2-py3-none-any.whl
- Upload date:
- Size: 2.7 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.10.12
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
d42e239196b5827cab0dc66b7d2422a864052539359e97585dcf968d6b14aea5
|
|
| MD5 |
5a5a9842397e0f438780f471304ee188
|
|
| BLAKE2b-256 |
4896ae21b0b3a70961bbaf029ba092633292af1c905f58bbc07058b6ca335af2
|