Skip to main content

conduit-llm

Lightweight AI driver for OpenAI-compatible, Ollama, Anthropic, and Gemini — transport and normalization only, no framework. Python import remains conduit.

Install

pip install conduit-llm

Requires Python 3.10+. Zero runtime dependencies (stdlib http.client).

Ollama Quick Start

No endpoint or API key needed — talks to http://localhost:11434 by default.

from conduit import connect

model = connect(driver="ollama", model="qwen3:8b")
print(model.generate("Hello").text)

for event in model.stream("Hello"):
    if event["type"] == "text_delta":
        print(event["text"], end="")

OpenAI-compatible

from conduit import connect

model = connect(driver="openai-compatible", endpoint="http://localhost:1234/v1", model="my-model")
print(model.generate("Hello").text)

Supported drivers

openai-compatible · ollama (/api/chat) · anthropic (/v1/messages) · gemini (/v1beta/models/...:generateContent)

Full API, spec, and conformance: github.com/krazybean/Conduit

Release files for conduit-llm 0.2.0

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

Source distribution (sdist)

Source distribution for conduit-llm 0.2.0
File Size Uploaded
conduit_llm-0.2.0.tar.gz 44.4 kB Details

Built distribution (wheel)

Table of built distributions (wheels) for conduit-llm 0.2.0
File Interpreter ABI Platform
conduit_llm-0.2.0-py3-none-any.whl Python 3 none any Details

Total release size: 71.9 kB

Release files / conduit_llm-0.2.0.tar.gz

Download URL conduit_llm-0.2.0.tar.gz
Size 44.4 kB
Tags Source
SHA-256 checksum
How to use checksums
8dce878c2bcab2561c79806379edcf9f24663a9c2aa716ce0f8b6179e5d1575a
BLAKE2b-256 checksum
How to use checksums
55e2c1eaf06d0a5759ee0a068a2a9d026f5514ca45ea8712f9e9f2a20c0d8716
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/7.0.0 CPython/3.14.6

Release files / conduit_llm-0.2.0-py3-none-any.whl

Download URL conduit_llm-0.2.0-py3-none-any.whl
Size 27.5 kB
Tags Python 3
SHA-256 checksum
How to use checksums
7988e1b2a5ed335eb82fe7d4f61fb60133a82a9f2cad645df22f140efe82492e
BLAKE2b-256 checksum
How to use checksums
fb5b6b4085f89865e93228a9baa9cf84ec793791d7adbcdf416275c617526611
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/7.0.0 CPython/3.14.6

Release history Release notifications | RSS feed

This release

0.2.0 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