Business agents

Pass text through a chain of 20 LLM translations and watch the meaning drift

Deterministic testing framework for LLM-powered apps — record/replay cassettes, eval scoring, regression testing

Token-bucket rate limiter for LLM API calls with per-model limits

Pre-call cost estimation, tracking, and budgets for OpenAI, Gemini, and Claude

Token cost control and auto-optimization for LLM apps — compress prompts, estimate costs, enforce budgets, route to cheap models, and cut LLM spend by up to 60%

Cut your LLM API bill by 30-70% with zero accuracy loss

A lightweight Python library for tracking OpenAI and Anthropic SDK costs with budget alerts

Lightweight drop-in Python decorator to track costs, monitor token usage, and enforce budget/rate limits for LLM API calls

OpenTelemetry instrumentation for Anthropic.

Auto-capture OpenAI and Anthropic LLM calls for warehousing and observability

LLM-powered markdown knowledge base CLI — knowledge synthesized at ingest time, not query time.

Unified Python client for OpenAI, Azure OpenAI, Vertex AI, Anthropic, Gemini, DeepSeek, OpenRouter, Cerebras, Fireworks, Together AI, LM Studio, Bedrock, LiteLLM, and ChatGPT.

A zero‑dependency wrapper that turns any OpenAI‑compatible endpoint into a hackable one‑liner.

Lightweight LLM API Orchestrator - A fast, multi-provider LLM client with rate limiting and key rotation

The new package transforms a user’s plain‑text search phrase into a structured, BM25‑ranked list of PostgreSQL search results. It takes the query text as input, forwards it to an LLM that rewrites the

Unified Python interface for OpenAI, Anthropic, Google, and Ollama LLMs with optional model registry and usage tracking - deprecated

A framework-agnostic browser tool for AI agents. Works with Anthropic, OpenAI, LangChain, and any agent framework.

Real-time LLM spend enforcement — CLI and tray app

A professional CLI tool for interacting with OpenAI and Anthropic LLMs with cost tracking

Cycle through multiple LLM providers with smart fallback, load balancing, and unified API with real-time FastAPI dashboard, resilient streaming failover, Pydantic structured output, prompt caching, token budgets, and local/cloud key rotation.

Read through cache for OpenAI's API.

Secure LLM Mesh over MCP — multi-LLM swarm + industrial IoT + privacy gateway

A lightweight, cross-platform latency and throughput profiler for LLMs

In-process LLM client faker that patches OpenAI, Anthropic, LiteLLM, and LangChain for fast, deterministic testing without network calls

Lightweight, provider-agnostic LLM calling library — OpenAI, Gemini, Anthropic, Groq, Mistral, Cohere, Azure, Bedrock, Ollama

LLMGovernor — anomaly engine for LLM apps (core SDK with optional LiteLLM bundle)

Open-source LLM evaluation framework — 50+ metrics for RAG, agents, safety, async eval, regression tracking, custom benchmarks, and exportable reports

Plug-and-play LLM connector via YAML config

Your Personal AI Cloud -- intelligent proxy, router, and cache for LLMs

LLM execution engine — multi-provider streaming, MCP tools, and budget management

Production-grade LLM client for Python - 100+ providers, 11,000+ models. Rust-powered.

AI API gateway SDK with cost tracking, budget enforcement, and multi-provider routing for LLM applications

Unified LLM testing lab - test, compare, and interact with multiple AI providers through a single UI

Chaos engineering for LLM apps: mock OpenAI, Anthropic, Gemini and more, break them on demand, and get a verdict on your client's resilience.

Reduce LLM costs by 90% - AI recommendations with NO API keys needed!

A unified framework for interacting with various LLM providers through a consistent interface with batch processing, templating, and rate limiting.

A lightweight set of tools to use several llm and embeddings apis

Unified Python interface for OpenAI, Anthropic, Google, and Ollama LLMs

A lightweight CLI tool and OpenAI-compatible server for querying multiple Large Language Model (LLM) providers

Command-line tool to use Large Language Models in your shell,including OpenAI, Anthropic, PalM, Mistral, Cohere, and more.

Know where your AI money goes. Track LLM API costs per feature, per model, per user.

A provider-agnostic LLM toolkit with tool calling, skills, and parallel execution.

Anthropic provider for llmtest

Production-quality performance validation and regression testing for LLM inference systems

Lightweight structured tracing for LLM applications

Lightweight LLM observability. SQLite-based tracing with zero infrastructure.

Automatically find cheaper LLM alternatives while maintaining performance

Automatically find cheaper LLM alternatives while maintaining performance

Record and replay LLM API responses for fast, free, deterministic tests

Lightweight multi-provider LLM client for Python

Lightweight Python SDK for the LLMWise multi-model API (chat, compare, blend, judge, failover).

Lightweight, extensible LLM toolkit: chat, embeddings, vector stores (Chroma, Milvus Lite).

Anthropic provider for lmux

A flask server for a chrome extension that querys llm models

A lightweight proxy server that converts Anthropic Messages API to OpenAI API

Claude (Anthropic) API emulator – LocalStack extension

Enterprise-grade AI security SDK with prompt injection detection for Python

Lyrie Agent SDK — embed the Lyrie Shield, Attack-Surface Mapper, Stages A–F validator, and pentest scanners in any Python project. Lyrie.ai by OTT Cybersecurity LLC.

Drop-in Anthropic client with MADB causal memory. One import, every turn persisted.

Unified Python interface for multiple LLM providers with cost tracking

MatrixLLM: OpenAI-compatible multi-provider LLM router (OpenRouter-style) with optional relay nodes

Synap memory integration for Anthropic's Claude Agent SDK

maxllm_gate - Intelligent LLM client with built-in rate limiting. Maximizes throughput and prevents 429 errors.

MCP server for interacting with AI agents through the Agent API

A Python SDK for MCP tool integration with LLM providers

An MCP server for bringing Anthropic's Agent Skills to any MCP-compatible agent.

MCP-Bastion security middleware for Anthropic Claude - prompt injection, PII, and rate-limit protection for AI agents

MCP server for Claude conversation extraction with enhanced export and search

MCP Server for web search via Gemini's grounding API

Python client, based on fastmcp, for connecting to MCP servers through multiple protocols, specifically designed to work with integrated language models.

MCP server for Ollama integration

MCP server for Ollama integration

MCP Server for rapid-rag - Local RAG with semantic search and LLM queries

Anthropic Claude tool use testing helpers for MCP Test Harness

Incremental Markdown translation with LLMs — track blocks in PO files, only retranslate what changed

MCP Server for MediaLLM

A specialized fork of Mem0 optimized for small, local Large Language Models (LLMs) running through Ollama.

3-level LLM cache (exact, semantic, prefix) with real-time token cost tracking

Anthropic Building Blocks for Meshagent

Anthropic (Claude) provider for Metorial

Mi-Claude — Chat with Claude AI from your terminal. No API key needed.

A flexible framework for building and deploying LLM-powered agents with multiple provider support, inspired by the mihrab that guides prayer in a mosque

A lightweight Python SDK for building AI agents with unified LLM providers, ReAct orchestration, and tool calling

A tool for OCR using Mistral. Ensure your MISTRAL_API_KEY is exported or in ~/.zshrc or ~/.bashrc

A firewall for LLMs — block prompt injection, jailbreaks, and PII exfiltration in real time.

A mock server that mimics OpenAI and Anthropic API formats for testing

Moda Anthropic instrumentation for LLM observability

Run Claude Agent SDK agents in Modal sandboxes

A unified framework for accessing multiple LLM providers with comprehensive CLI and machine interface

MOSS cryptographic signing integration for Anthropic Claude

MRI-Swarm - TGSC

A free, specialized MCP server for financial analysis and quantitative trading. Provides one-click setup for local financial MCP services with department-based architecture simulating financial company operations. Supports traditional indicators, price action analysis, economic calendar, fundamental analysis, and news integration for seamless LLM interaction and algorithmic trading.

Make Anthropic Model Context Protocol (MCP) tools compatible with LangChain and LangGraph agents.

GraphRAG-based MCP server: builds a repository knowledge graph (Tree-sitter + LightRAG) for Q&A and change planning.

多 Agent 协作运行时——脚手架 + 运行时观察台（spec v6 真协作 / 多 LLM provider / GSAP 仪表盘）

Achieve consensus across multiple LLMs through an AI judge coordinator

AI CLI Background Music Player - Plays work music in loop and done music when finished

A lightweight, dependency-free LLM agent framework with direct HTTP-based provider integration

A simple, easy-to-hack GraphRAG implementation

Python package to allow easy integration to Neo4j's GraphRAG features