llm-fallback

LLM budget control and cost governance for AI agents. Python library for token budgets, usage limits and guardrails for OpenAI, Anthropic, LangChain, LangGraph and agentic systems.

AI-powered video auto-clipper that extracts the most compelling moments from long-form videos and turns them into vertical shorts optimized for TikTok, YouTube Shorts, and Instagram Reels. Built with Flask, FFmpeg, and Whisper.

Free LLM API for Python & Node.js: a free-only, lightweight LiteLLM/OpenRouter alternative. One OpenAI-compatible client and local /v1 endpoint over Gemini, Groq, OpenRouter, Cloudflare, Mistral, NIM, Z.ai, Cohere & Kilo, with LLM fallback that races slow providers and key rotation. Works with no API keys.

Cascade a chat completion across every free-tier LLM API you have a key for

TypeScript LLM Abstraction Layer for Multi-Provider AI Systems. Multi-provider routing, fallback chains, USD cost gating, capability factories, tool-use security.

A deterministic, safety-first microservice for parsing free-form bKash customer complaints (English, Bengali, Banglish) into structured triage data. Built with FastAPI, featuring a hybrid rule/LLM engine, local NLP normalization, and deep input/output guardrails.

Ollama + Hermes local fallback kit for when every cloud LLM is down — drill-first, honest about the ceiling

Django REST + React platform that turns pharma SOPs into role-specific quizzes via NVIDIA NIM (Llama 3.1), with a deterministic offline fallback, RBAC-gated endpoints, 21 CFR Part 11-style e-signatures/audit trail, and Leitner+FSRS adaptive retraining.

Pi coding agent extension for seamless API key failover, provider fallback, and rate-limit handling without interrupting your AI coding session.

Enterprise AI Continuity: The Backup QB Strategy | Published on omnithium.ai

Hybrid SAP ticket routing: Rule Engine → TF-IDF → LLM fallback. Three-layer decision system with zero unnecessary API calls.

A production-ready CLI Chatbot featuring an advanced RAG pipeline with Hybrid Search, Cross-Encoder Reranking, and a Multi-Model Fallback Router (Anthropic/Ollama). It includes Smart Memory context compression and a native LLM-as-a-Judge evaluation framework.

Production-oriented customer support ticket classifier using MiniLM, Logistic Regression, FastAPI, Docker, and optional LLM fallback.

Self-hosted multi-agent assistant on Google ADK + Gemini 2.5 — FastAPI backend (agent-as-tool coordinator with ~22 tool specialists), Next.js voice UI, hardened auth, and an LLM fallback + completion-verifier resilience layer.

A lightweight LLM gateway with automatic fallback across providers (Groq, Hugging Face) — built with LangChain and a Streamlit UI.

Textual terminal UI (TUI) sample app for the ai-api-unified Python library: one API across OpenAI, Anthropic Claude, Google Gemini, and AWS Bedrock for LLM completions, tool use, structured output, model fallback, embeddings, image, video, and voice.

A self-hostable, enterprise-grade LLM gateway: routing, cost control, caching, guardrails, access control, and a tamper-evident audit trail.

LLM Gateways

A production-ready, fault-tolerant multi-agent orchestrator built with LangGraph, FastAPI, and React. Features true async parallel task execution and dynamic open-source model fallback chains.