AgentNexus Python SDK
3 lines to connect your AI Agent to the decentralized network.
Install
pip install -e .
Quick Start: Owner + Secretary + Dispatch
Register an Owner DID, create a Secretary Agent, bind Worker Agents, and dispatch a task.
import agentnexus
# 1. Bootstrap: connect as admin
admin = await agentnexus.connect("Team Admin", caps=["Admin"])
# 2. Register personal main DID (Owner)
owner = await admin.owner.register("Kevin")
# 3. Register Secretary Agent (auto-bound to Owner)
secretary = await admin.secretary.register(owner.did, name="Secretary")
# 4. Create and bind Worker Agents
architect = await agentnexus.connect("Architect", caps=["architect", "design"])
developer = await agentnexus.connect("Developer", caps=["developer", "code"])
reviewer = await agentnexus.connect("Reviewer", caps=["reviewer", "review"])
await admin.owner.bind(owner.did, architect.agent_info.did)
await admin.owner.bind(owner.did, developer.agent_info.did)
await admin.owner.bind(owner.did, reviewer.agent_info.did)
Dispatch a Session
result = await admin.secretary.dispatch(
session_id="sess_login_001",
owner_did=owner.did,
actor_did=secretary.did,
objective="Complete login module design, implementation, testing and review",
required_roles=["architect", "developer", "reviewer"],
entry_mode="owner_pre_authorized",
)
print(f"Run: {result.run_id}, Enclave: {result.enclave_id}, Stage: {result.current_stage}")
Worker: Handle Stage Tasks
Workers use @nexus.worker.on_stage(role=...) instead of parsing task_propose JSON manually.
worker = await agentnexus.connect(did=developer.agent_info.did)
@worker.worker.on_stage(role="developer")
async def handle_stage(ctx):
# Read requirements from Vault
req = await ctx.vault.get("requirements/intake.json")
# Read design spec
spec = await ctx.vault.get("design/spec.md")
patch = implement(spec.value)
# Deliver artifact: writes to Vault + notifies completion
await ctx.deliver(
kind="code_diff",
key="impl/diff.patch",
value=patch,
summary="Login module implementation",
)
# Reject a stage if needed:
# await ctx.reject(reason="Tests failed, missing edge cases")
Query Run / Intake Status
intake = await admin.runs.get_intake("sess_login_001", actor_did=secretary.did)
status = await admin.runs.get_status(result.enclave_id, result.run_id)
Owner Abort
await admin.secretary.abort(
session_id="sess_login_001",
actor_did=owner.did,
reason="Requirement changed, cancelling this run",
)
Core Messaging (Lightweight)
For simple point-to-point communication without orchestration:
nexus = await agentnexus.connect("MyAgent", caps=["Chat", "Search"])
await nexus.send(to_did="did:agentnexus:z6Mk...", content="Hello!")
@nexus.on_message
async def handle(msg):
print(f"From {msg.from_did}: {msg.content}")
await nexus.close()
Main Facades
| Facade | Purpose |
|---|---|
nexus.owner |
Owner DID registration and child Agent binding |
nexus.team |
Worker registry, presence and worker metadata |
nexus.secretary |
Intake, dispatch, confirm and abort |
nexus.runs |
Intake and Playbook run status |
nexus.worker |
Stage callback runtime and artifact delivery |
nexus.enclaves |
Enclave, Vault and Playbook APIs |
nexus.orchestration |
Aggregated facade (all of the above in one place) |
The legacy send / propose_task / claim_task / notify_state APIs remain supported for lightweight point-to-point collaboration.
Synchronous API
For non-async contexts (scripts, REPL):
import agentnexus.sync as sync
nexus = sync.connect("MyAgent", caps=["Chat"])
nexus.send(to_did="did:agentnexus:z6Mk...", content="Hello!")
nexus.close()
Metadata
Release files for agentnexus-sdk 1.0.0
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 |
|---|---|---|---|---|
| agentnexus_sdk-1.0.0.tar.gz | 43.0 kB | Without provenance | Details for agentnexus_sdk-1.0.0.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| agentnexus_sdk-1.0.0-py3-none-any.whl | Python 3 | none | any | Details for agentnexus_sdk-1.0.0-py3-none-any.whl |
Total release size: 80.1 kB
Release files / agentnexus_sdk-1.0.0.tar.gz
| Download URL | agentnexus_sdk-1.0.0.tar.gz |
|---|---|
| Size | 43.0 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
e811a8d74d97198961782ee4820deeeab5c78887ef8339d10cecccad20630541
|
|
BLAKE2b-256 checksum How to use checksums |
22364ca16f5cc37eeabdcfec1e4f6f1e14caecb2f94cb96a8599f1367214cf94
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.13.3
|
Release files / agentnexus_sdk-1.0.0-py3-none-any.whl
| Download URL | agentnexus_sdk-1.0.0-py3-none-any.whl |
|---|---|
| Size | 37.0 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
55aba1d81950a3bea6b7e1bf836df8a16a9ee1141b5951beb4500090b52c52a8
|
|
BLAKE2b-256 checksum How to use checksums |
b110f1ded4913e5b7a66b3973f46741b7ce29eea30ec546bf6fd7da8c436bdbc
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.13.3
|
Security for agentnexus-sdk 1.0.0
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.