Skip to main content

OpenSymbolicAI Core

Build LLM-powered systems as typed, testable Python software — not prompt strings.

The LLM plans once over your primitive signatures; execution is deterministic Python with no model in the loop. Inputs and outputs are typed variables.

Install

pip install opensymbolicai-core

Example

from opensymbolicai import PlanExecute, primitive, decomposition

class Calculator(PlanExecute):
    @primitive(read_only=True)
    def add(self, a: float, b: float) -> float:
        """Add two numbers."""
        return a + b

    @decomposition(intent="What is 2 + 3?")
    def _example(self) -> float:
        return self.add(a=2, b=3)

Documentation

Full docs, examples, benchmarks, and architecture: https://github.com/OpenSymbolicAI/core-py

License

MIT

Metadata

Release files for opensymbolicai-core 0.8.0

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

Source distribution (sdist)

Source distribution for opensymbolicai-core 0.8.0
File Size Uploaded
opensymbolicai_core-0.8.0.tar.gz 105.4 kB Details

Built distribution (wheel)

Table of built distributions (wheels) for opensymbolicai-core 0.8.0
File Interpreter ABI Platform
opensymbolicai_core-0.8.0-py3-none-any.whl Python 3 none any Details

Total release size: 173.2 kB

Release files / opensymbolicai_core-0.8.0.tar.gz

Download URL opensymbolicai_core-0.8.0.tar.gz
Size 105.4 kB
Tags Source
SHA-256 checksum
How to use checksums
f0f74a25ef2930e9542ec5df7b94709a95f172cafcd1c465f9648986d9a627f0
BLAKE2b-256 checksum
How to use checksums
9bc250760c5436cfd21f7a21daaaeb87423208fedeef45979566d96d5dbac924
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/6.2.0 CPython/3.14.2

Release files / opensymbolicai_core-0.8.0-py3-none-any.whl

Download URL opensymbolicai_core-0.8.0-py3-none-any.whl
Size 67.8 kB
Tags Python 3
SHA-256 checksum
How to use checksums
2460c1439561265c5bf193fe9e0009d7dd1fa021424d48d188507eadcf6c1a30
BLAKE2b-256 checksum
How to use checksums
80e7ae09a15bfeb9124c07510ee0123e25a3a71218888a4a743a837a02525a31
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/6.2.0 CPython/3.14.2

Release history Release notifications | RSS feed

This release

0.8.0 This release

2 release files

0.7.1

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