Current collected state Current
Observed since 20 Oct, 23:11 UTC
No superseded metadata states collected. Unchanged observations do not create new revisions.
Registri framework — build, register, and orchestrate AI agents in minutes
High-level framework for building agents on the Agent Registry — register, discover, and collaborate in minutes.
pip install agent-registry-framework
Build a fully registry-aware agent in ~10 lines:
from agent_registry_framework import AgentServer
agent = AgentServer(
name="my-agent",
capabilities=["text-analysis"],
description="Analyzes text",
)
@agent.on_message
async def handle(message, ctx):
# Discover and talk to other agents
writers = await ctx.discover("content-writing")
draft = await ctx.send_and_wait(writers[0].id, {"topic": "AI"})
return {"draft": draft}
agent.run(port=8080)
send_and_wait() with correlation trackingask_human() for approval workflows/.well-known/agent-card.jsonagent.run(reload=True) for developmentagent.run(tunnel=True) for ngrok tunnelingagent-registry init --template llm to scaffold projects| Variable | Default | Description |
|---|---|---|
AGENT_REGISTRY_URL | https://api.registri.io | Registry API endpoint |
AGENT_REGISTRY_USERNAME | — | Your registry username |
AGENT_REGISTRY_PASSWORD | — | Your registry password |
AGENT_ENDPOINT | Auto-detected | Public URL for webhooks |
AGENT_PRIVATE_KEY | — | Ed25519 private key for signing |
AGENT_PROVIDER_NAME | Double A Labs LLC | Organization name in Agent Cards |
Download counts and popularity will appear here as the collector receives them.
| Version | Published | Direct dependencies | Open version |
|---|---|---|---|
| 0.1.0 | 3 Mar 2026 | 6 |
This describes our collected data; it is not a security assessment.
Observed since 20 Oct, 23:11 UTC
No superseded metadata states collected. Unchanged observations do not create new revisions.
package:60b650a71ac9a002f7fc8fb049b5dc6e5db333cbdce6889b34bc5190da06cf7a