Skip to main content

Agentic State Machine

1. What ASM is

ASM stands for Agentic State Machine. This is a low-level library for pluggable agents orchestration using state diagrams and manifests:

  • a state diagram — using mermaid diagram syntax
  • a manifest — enable pluggable state

Why?

Because when the work is long, branchy, and needs to be inspected as it runs, a pile of nested if statements stops being readable.

ASM is designed for workflows requiring a mix of deterministic and non-deterministic routes through a complex maze of conditions running in a stateless environment.

If your problem is a straight line of five function calls, you do not need ASM. Write the five function calls.

Release files for gai-harness-asm 0.0.1

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

Source distribution (sdist)

Source distribution for gai-harness-asm 0.0.1
File Size Uploaded
gai_harness_asm-0.0.1.tar.gz 262.7 kB Details

Built distribution (wheel)

Table of built distributions (wheels) for gai-harness-asm 0.0.1
File Interpreter ABI Platform
gai_harness_asm-0.0.1-py3-none-any.whl Python 3 none any Details

Total release size: 295.1 kB

Release files / gai_harness_asm-0.0.1.tar.gz

Download URL gai_harness_asm-0.0.1.tar.gz
Size 262.7 kB
Tags Source
SHA-256 checksum
How to use checksums
e32780143d4c3c42c9c048449bee8df186270f564e530726cf25cb3364791ff0
BLAKE2b-256 checksum
How to use checksums
27e6b12cd98421a7d7f507b82511e59c90fdb51c500bfb2049859985995840eb
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/7.0.0 CPython/3.12.13

Release files / gai_harness_asm-0.0.1-py3-none-any.whl

Download URL gai_harness_asm-0.0.1-py3-none-any.whl
Size 32.4 kB
Tags Python 3
SHA-256 checksum
How to use checksums
5b378b56ae067698dcd1993e2de12f8b1f9d3e6fee7ead4eab70c0f9edd18f5c
BLAKE2b-256 checksum
How to use checksums
4082af0531c6a1e869a7b3065d0d267bbf6ecfadb24f7df854c4970062722270
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/7.0.0 CPython/3.12.13

Release history Release notifications | RSS feed

This release

0.0.1 This release

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