agentregistry is the registry for your agent fleet — discover, version, and deploy production AI agents. Like PyPI, but for agents.
Install
pip install agentregistry-py
pip install "agentregistry-py[http]" # health checks
pip install "agentregistry-py[sqlite]" # persistent store
Quickstart
from agentregistry import AgentRegistry, AgentManifest
registry = AgentRegistry()
registry.publish(AgentManifest(
id="acme.billing-agent",
version="1.2.0",
description="Handles billing for enterprise tenants",
capabilities=["charge_card", "refund", "read_balance"],
framework="langgraph",
tags={"domain": "finance", "env": "prod"},
policies=["acme.billing.v2"],
))
# Discover
agent = registry.get("acme.billing-agent")
results = registry.search(capability="charge_card")
results = registry.search(framework="langgraph", tags={"domain": "finance"})
# Version lifecycle
registry.deprecate("acme.billing-agent", "1.1.0")
registry.yank("acme.old-agent")
versions = registry.versions("acme.billing-agent")
AgentManifest
| Field | Type | Description |
|---|---|---|
id |
str | Unique agent identifier |
version |
str | Semver version |
capabilities |
list[str] | What the agent can do |
framework |
str | langgraph / crewai / autogen / openai / custom |
policies |
list[str] | Required agentplane policy IDs |
tags |
dict | Arbitrary k/v for filtering |
health_check |
str | HTTP endpoint for health checks |
Stack
agentplane → control plane (runtime policy, versioning, escalation)
agentregistry → registry (discover, version, deploy agents) ← you are here
agentobserve → observability (unified view across all layers)
agenteval → testing (golden paths, adversarial, policy tests)
Apache 2.0 · Built for production enterprise agents
1 maintainer
Metadata
1 maintainer
Release files for agentregistry-py 0.1.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| agentregistry_py-0.1.0.tar.gz | 10.0 kB | Without provenance | Details for agentregistry_py-0.1.0.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| agentregistry_py-0.1.0-py3-none-any.whl | Python 3 | none | any | Details for agentregistry_py-0.1.0-py3-none-any.whl |
Total release size: 18.1 kB
Release files / agentregistry_py-0.1.0.tar.gz
| Download URL | agentregistry_py-0.1.0.tar.gz |
|---|---|
| Size | 10.0 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
c33b42cd3783f1e94febde6d7ed9489965ae3fe557b5be27d98aab9e43d93b53
|
|
BLAKE2b-256 checksum How to use checksums |
74ae9f913c371f9cecddadb4a8a51ffab6db3074a10baa00a7b23888fbd4dc5c
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.1.0 CPython/3.13.12
|
Release files / agentregistry_py-0.1.0-py3-none-any.whl
| Download URL | agentregistry_py-0.1.0-py3-none-any.whl |
|---|---|
| Size | 8.1 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
6c8507a1fca144ea7f092dd8bbfbde01179299ed9cb061e7dedc87a555943f8a
|
|
BLAKE2b-256 checksum How to use checksums |
5e58e4ffacf27f0c2c275cb7c97d5a8959ac2b748d4d01e35c92612e10e771a9
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.1.0 CPython/3.13.12
|
Security for agentregistry-py 0.1.0
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.
