Skip to main content

specialists

A small, typed foundation for defining and organizing domain-specific AI agents.

Installation

This package requires Python 3.10 or higher.

pip install specialists

Usage

from specialists import Specialist, SpecialistRegistry

legal = Specialist(
    name="Lex",
    domain="contract law",
    instructions="Review contracts and identify ambiguous clauses.",
)

registry = SpecialistRegistry()
registry.register(legal)

print(registry.get("Lex").system_prompt())

specialists intentionally does not select an LLM provider or agent runtime. Its definitions can be adapted to the framework used by an application.

Development

pip install -e ".[dev]"
pytest
ruff check --fix --select I
ruff format

License

MIT

Metadata

Release files for specialists 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 specialists 0.0.1
File Size Uploaded
specialists-0.0.1.tar.gz 34.2 kB Details

Built distribution (wheel)

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

Total release size: 37.6 kB

Release files / specialists-0.0.1.tar.gz

Download URL specialists-0.0.1.tar.gz
Size 34.2 kB
Tags Source
SHA-256 checksum
How to use checksums
d782d5ca9617f12406b0401c9e97149db6f7ea723d5a1ed8439bd1daac561666
BLAKE2b-256 checksum
How to use checksums
a50fac49a107a63136cae66c618eb5a2612407ee9fbaa05021e7073e5622fe81
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/6.2.0 CPython/3.14.0

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

Download URL specialists-0.0.1-py3-none-any.whl
Size 3.4 kB
Tags Python 3
SHA-256 checksum
How to use checksums
51d675f872abbb030d3416cbe970b8123920e62133fca0d93d42a1224f1a96a4
BLAKE2b-256 checksum
How to use checksums
818fa267fb02223100534bf691b954142ebe42035325847f341c80ff73c0648a
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/6.2.0 CPython/3.14.0

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