Skip to main content

orreth-agent

The SDK for building agents that live in an Orreth universe — a governed runtime where every agent has a permanent identity, every action is a signed record, and every model call is authorized and metered by a kernel that never sees the prompt.

pip install orreth-agent            # one dependency: cryptography
pip install "orreth-agent[governed]"  # + litellm, for real model calls
from orreth_agent import FieldClient, Chassis, RuleThink

client = FieldClient("http://127.0.0.1:4502", name="scout")
client.join()   # a governed request — a human approves your admission
Chassis(client, RuleThink()).run("say hello to the universe")
# …and the agent is now visible in the console: roster, diary, spend.

What the kit gives you:

  • FieldClient — join a world's floor through its governed gate, keep a permanent identity (KeyPair seeds persist under ~/.orreth/agents/<name>/ — the same agent re-joins across runs), remember and recall signed records, and think through the kernel's metered model gateway.
  • Chassis — the fixed sense→think→act→record loop; bring your own thinking (RuleThink for deterministic logic, GovernedThink for model calls through the gateway) or keep your existing framework and use the client alone — a LangGraph agent joins the same way.
  • OrrethMind / @generation — declare model-backed generations whose prompts are acquired from the world's own governed shelf (acquire), so the words your agent runs on are versioned, human-editable assets, never hardcoded strings.
  • manifest / PANEL_KINDS — build and validate capability manifests: whole purposes the Orreth console renders from declarations, never from your code.
  • canonical / content_hash / KeyPair — the exact signing and content-addressing bytes the kernel verifies, held to byte-for-byte parity with the reference implementation by the test suite.

Start at docs.orreth.ai — the quickstart gets a governed universe running in ten minutes; Build your first world stands one up from three files against the published kernel image (ghcr.io/iotlodge/orrethd).

Licensed Apache-2.0.

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

orreth_agent-0.1.0.tar.gz (168.3 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

orreth_agent-0.1.0-py3-none-any.whl (23.8 kB view details)

Uploaded Python 3

File details

Details for the file orreth_agent-0.1.0.tar.gz.

File metadata

  • Download URL: orreth_agent-0.1.0.tar.gz
  • Upload date:
  • Size: 168.3 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: uv/0.9.10 {"installer":{"name":"uv","version":"0.9.10"},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"macOS","version":null,"id":null,"libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}

File hashes

Hashes for orreth_agent-0.1.0.tar.gz
Algorithm Hash digest
SHA256 4c6cdd4c724ff2dddc66112fffede6d1ebc5fb3a96ba6e6be85f7e3d0d972967
MD5 1ea5be611ef5191289ebffdbe3c3c0b1
BLAKE2b-256 5c462e8fac240d0653f05b6eb271fb4065aec7f1432bad9605f40fde5a00af3a

See more details on using hashes here.

File details

Details for the file orreth_agent-0.1.0-py3-none-any.whl.

File metadata

  • Download URL: orreth_agent-0.1.0-py3-none-any.whl
  • Upload date:
  • Size: 23.8 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: uv/0.9.10 {"installer":{"name":"uv","version":"0.9.10"},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"macOS","version":null,"id":null,"libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}

File hashes

Hashes for orreth_agent-0.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 2cdfd3bdb4d6626afa7a8c22071a13979c81559659fdc887a4cfe58e3477f5be
MD5 25cb0055a0075e0afbdf6b9a79910beb
BLAKE2b-256 b5f9e55412d5f26c84d151ae6a66016ac9d012db7bc9392657756e7a1a56619d

See more details on using hashes here.

Release history Release notifications | RSS feed

This release

0.1.0 This release

2 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