Skip to main content

🤖 IOI Swarm SDK (ioi-swarm)

The Official Python Framework for the Internet of Intelligence (IOI) Protocol.

ioi-swarm is a high-performance library for building sovereign, autonomous agents that run on the IOI Network. Unlike standard agent frameworks, IOI agents are cryptographically tied to The Substrate (Sovereign Context Substrate), ensuring that every observation, decision, and action is verifiable and tamper-proof.

PyPI version License: BBSL


🚀 Key Features

  • Sovereign Context Substrate (SCS): Direct integration with the IOI Substrate for intent-constrained memory and provenance proofs.
  • Distributed Inference Mesh (DIM): Seamlessly burst agent reasoning to a decentralized network of GPU providers.
  • Verifiable Agency: Every tool call generates a cryptographic receipt, providing an immutable audit trail of agent behavior.
  • Ghost Mode: Record agent traces locally to synthesize security policies for the IOI Semantic Firewall.
  • Post-Quantum Secure: Built-in support for hybrid classical/PQ cryptographic identities.

📦 Installation

pip install ioi-swarm

Note: Requires a running IOI Node (ioi-local) for full verification and settlement capabilities.

🛠 Quickstart

from ioi_swarm import Agent, tool, ActionTarget

# 1. Initialize your Sovereign Agent
agent = Agent(name="Autopilot", policy_id="finance-restricted")

# 2. Define a Verifiable Tool
@tool(name="get_balance", target=ActionTarget.FS_READ)
def check_vault_balance(vault_id: str):
    """Checks the balance of a specific on-chain vault."""
    # Logic intercepted by the IOI Kernel for policy enforcement
    return 100.0

# 3. Register and Run
agent.register_tool(check_vault_balance)
agent.run("Check my vault balance and alert me if it's below 50")

🧠 The Triad of Agency

IOI agents operate within a strict architectural boundary:

  1. Drivers: Native hardware capabilities (Eyes & Hands).
  2. Tools: Extensible WASM-based instruments (Utility).
  3. Skills: Procedural memory stored in the Substrate (Know-How).

📄 Documentation

For full protocol specifications, whitepaper details, and advanced swarming patterns, visit docs.ioi.network.

🛡 Security

The ioi-swarm SDK is designed to be "Secure by Default." All outbound requests are gated by the IOI Agency Firewall, which performs real-time PII scrubbing and intent validation.


© 2026 IOI Foundation. Built for the Internet of Intelligence.

Release files for ioi-swarm 0.1.2

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for ioi-swarm 0.1.2
File Size Uploaded
ioi_swarm-0.1.2.tar.gz 14.2 kB Details

Built distribution (wheel)

Table of built distributions (wheels) for ioi-swarm 0.1.2
File Interpreter ABI Platform
ioi_swarm-0.1.2-py3-none-any.whl Python 3 none any Details

Total release size: 31.8 kB

Release files / ioi_swarm-0.1.2.tar.gz

Download URL ioi_swarm-0.1.2.tar.gz
Size 14.2 kB
Tags Source
SHA-256 checksum
How to use checksums
51ceb5fa1bb7160c2aab19c80bd83367c4b7ab9b01be4abb75fcfaa615a73d72
BLAKE2b-256 checksum
How to use checksums
c167344cd18cbb6e70a3dd1dd2fdb7c30ed96a114dee7e3402165c298107a50a
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/6.1.0 CPython/3.13.7

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.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Jan 9, 2026.

Transparency log

Release files / ioi_swarm-0.1.2-py3-none-any.whl

Download URL ioi_swarm-0.1.2-py3-none-any.whl
Size 17.6 kB
Tags Python 3
SHA-256 checksum
How to use checksums
9282a1cfadb472a8eda19cdd27b60757a408f7a01a3652f5a88394e3ced1c6e2
BLAKE2b-256 checksum
How to use checksums
6e0ce6c98b6fe6b16dd49f12a160b28a7166dd969844a58bbe1a3811e5b9d28b
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/6.1.0 CPython/3.13.7

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.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Jan 9, 2026.

Transparency log

Release history Release notifications | RSS feed

This release

0.1.2 This release

2 release files

0.1.0

2 release files

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page