Skip to main content

No project description provided

Project description

Build Status Coverage

llmbroker

Route LLM calls over a pool of free LLMs with automatic round-robin and cooldown.

No LangChain, no heavy deps.

import llmbroker

llms = llmbroker.Broker("llms.toml")
print(llms.ask("Summarize this receipt").text)

llms.toml is a plain list of [[llms]] entries (base_url, model, api_key_ref). Grab the freetier preset from this repo to start with a maintained list of free LLM endpoints.

That one-liner is the whole API for a script — but the same Broker scales up too. Run it inside a server or across a cluster with cooldown state shared between instances, and back it with common databases (connectors for SQLite, Redis, and Postgres covering registry, telemetry, secrets, and state). The calling code stays the same — you just pass a backend.

Why llmbroker:

  • Round-robin with automatic failover — 429/503 cools an endpoint and tries the next; the caller never sees a rate-limit error unless every endpoint fails.
  • No heavy deps — stdlib-only core; optional backends (sqlite, redis, postgres) are submodules you import only when you need them.
  • Dead-simple to start — a TOML file and env vars, one constructor line, done.
  • Fully customisable — swap registry, secrets, and telemetry backends independently: any DB, any secrets manager (AWS, Vault, …), any storage.
  • Cluster-ready — add state_store=llmbroker.redis.StateStore(...) to sync cooldown state across instances; omit for single-process.
  • Sync and asyncllmbroker.Broker for scripts; llmbroker.AsyncBroker for FastAPI, agents, and async workers.

Documentation

llmbroker

Developers

Do not forget to run . ./activate.sh.

For work it need uv installed.

Use pre-commit hooks for code quality:

pre-commit install

Allure test report

Scripts

Install invoke preferably with uv tool:

uv tool install invoke

For a list of available scripts run:

invoke --list

For more information about a script run:

invoke <script> --help

Coverage report

Created with cookiecutter using template

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

llmbroker-0.0.10.tar.gz (104.4 kB view details)

Uploaded Source

Built Distribution

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

llmbroker-0.0.10-py3-none-any.whl (37.0 kB view details)

Uploaded Python 3

File details

Details for the file llmbroker-0.0.10.tar.gz.

File metadata

  • Download URL: llmbroker-0.0.10.tar.gz
  • Upload date:
  • Size: 104.4 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.13.12

File hashes

Hashes for llmbroker-0.0.10.tar.gz
Algorithm Hash digest
SHA256 e553c1d6d15dc09e6f8f16191698cee8fe3550d3ddf7b7eaff07db86a1b521b7
MD5 a7430ef46b9d5b0162f3d4f7268bc89f
BLAKE2b-256 36215c78284457c8fa99f65cfde848fa70b87d66227646c56554d15de83d0153

See more details on using hashes here.

File details

Details for the file llmbroker-0.0.10-py3-none-any.whl.

File metadata

  • Download URL: llmbroker-0.0.10-py3-none-any.whl
  • Upload date:
  • Size: 37.0 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.13.12

File hashes

Hashes for llmbroker-0.0.10-py3-none-any.whl
Algorithm Hash digest
SHA256 507bc6af7ac3b820749887009e32d7421a2f462abfccba53ad1c9449ceba051f
MD5 42fc0b1f4512b3416734624aeb8eba39
BLAKE2b-256 2ec1a44802b0a90281135e287334325b5ab39f123217b3ed0a26df913c7fece1

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