Skip to main content

A lightweight, zero-dependency, provider-agnostic LLM agent with tool-calling support for Anthropic, OpenAI, Gemini, and Ollama.

Project description

llmadapt

A small, zero-dependency, provider-agnostic agent for chatting with LLMs and giving them tools. Works with Anthropic, OpenAI, Gemini, and Ollama using only the Python standard library for HTTP — no requests, no provider SDKs. v0.1.0

Install

From source (until published to PyPI):

git clone https://github.com/Shyam-Parikh-2025/llmadapt.git
cd llmadapt
pip install -e .

Once published:

pip install llmadapt

Quick start

from llmadapt import Agent

agent = Agent(
    provider="anthropic",
    model="claude-sonnet-4-6",
    api_key="sk-ant-...",  # or set ANTHROPIC_API_KEY in your environment
    system_instruction="You are a helpful assistant.",
)

print(agent.chat("What's 12 * 7?"))

Giving the agent tools

def get_weather(city: str) -> dict:
    """Look up the current weather for a city."""
    return {"city": city, "tempF": 72, "condition": "sunny"}

agent.add_tool(get_weather)
print(agent.chat("What's the weather in NYC?"))

A JSON schema is auto-generated from the function's type hints, default values, and docstring. Tool outputs are JSON-serialized automatically (plain strings pass through untouched).

Switching providers

agent.switch_api(provider="openai", model="gpt-4o", api_key="sk-...")

Limiting tool-call loops

agent.set_max_tool_iterations(20)  # default is 10

If the model gets stuck calling tools repeatedly without producing a final answer, chat() raises a RuntimeError instead of looping forever.

Supported providers

provider env var for API key notes
anthropic ANTHROPIC_API_KEY Messages API
openai OPENAI_API_KEY Chat Completions API
gemini GEMINI_API_KEY generateContent endpoint
ollama (none — local) defaults to localhost:11434
custom (none — pass directly) requires base_url + a custom_format_func you supply to chat()

Running tests

python tests/test_agent.py

Tests run entirely offline against scripted fake HTTP responses — no API key or network access required.

License

MIT

Project details


Download files

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

Source Distribution

llmadapt-0.1.0.tar.gz (14.6 kB view details)

Uploaded Source

Built Distribution

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

llmadapt-0.1.0-py3-none-any.whl (9.6 kB view details)

Uploaded Python 3

File details

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

File metadata

  • Download URL: llmadapt-0.1.0.tar.gz
  • Upload date:
  • Size: 14.6 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.13.11

File hashes

Hashes for llmadapt-0.1.0.tar.gz
Algorithm Hash digest
SHA256 221501214a9c5caca6364ecaa1caf0d4eaaacc06c7415b42e388d993c21a2fbc
MD5 b6fe7cdf793af64941503f768fbcbdbd
BLAKE2b-256 d126ce85e31d23d0f74bac94673fbced68884e8788d96c77250f55e8de7194be

See more details on using hashes here.

File details

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

File metadata

  • Download URL: llmadapt-0.1.0-py3-none-any.whl
  • Upload date:
  • Size: 9.6 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.13.11

File hashes

Hashes for llmadapt-0.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 03da48d7c3a40eb2d3b8370002ccd8093ee29d05362c8d63f9acc5ac9df0dbfa
MD5 64f09e1d96fd9df72eaea48d95fdaa7f
BLAKE2b-256 6919ec57373878908c2d8771ee63e1866cea13598851c8b9f1b658489aad65de

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page