Business agents

Reference implementation: agentic RAG on Nepal government policy and legal documents. Offline-capable, Nepali + English, hybrid retrieval with citations.

Multi-provider LLM orchestration with fallback chains and three-tier cognition

A high-throughput and memory-efficient inference and serving engine for LLMs

Intelligent Agentic File Assistant powered by Claude

A robust, multi-model LLM calling package with intelligent context management, file processing, and advanced prompt handling

Natural-language-to-SQL agent loop with schema and execution tools, hints, feedback store, and eval harness. Imports as `nl2sql`.

A high-throughput and memory-efficient inference and serving engine for LLMs

Model Context Protocol (MCP) communication through NOSTR.

Model Context Protocol (MCP) communication through Nostr.

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

Intelligent No Frills LLM Router - A unified interface for multiple LLM providers

A high-throughput and memory-efficient inference and serving engine for LLMs

Anthropic Claude provider for the NucleusIQ AI agent framework (Messages API, native tools, prompt caching, extended thinking, streaming).

A Python SDK for MCP tool integration with LLM providers

OCC cryptographic proof signing for the Anthropic Python SDK

Zero-egress PII protection for Claude AI workflows via MCP stdio

Create CRM Lead via API with fiber coverages informed in a broadband CRM Line

Sales Commissions Agent Restrict

Compute estimated stock coverage based on product sales over a date range.

Sales Commissions Agent Restrict

Elegant Jinja2-based chat template parser for AI applications

A RAG (Retrieval-Augmented Generation) system using Llama Index and ChromaDB

Functions to conveniently run asynchronous Ollama workflows, including RAG support.

CLI for MCP Client for Ollama - An easy-to-use command for interacting with Ollama through MCP

A unified Python client to normalize interfaces across major LLM providers (OpenAI, Anthropic, Gemini, DeepSeek, xAI, OpenRouter).

A unified, provider-agnostic chat completions API server that seamlessly integrates OpenAI and AWS Bedrock through a single endpoint with intelligent format detection and conversion.

Swarms - TGSC

GPT agent logic with tool calling and dispatching

OpenAI Agents SDK tools for The Colony (thecolony.cc) — give any AI agent the ability to search, read, write, and interact on the AI agent internet

This is a simple openAI API wrapper that makes it easier for me (and hopefully for you as well) to send messages via an assistant and manage threads locally with a custom thread key (such as message author) that is associated the thread id stored by open ai.

An asynchronous Python package for integrating OpenAI assistant.

CLI for chatting through OpenAI's API.

Exact, auditable LLM API cost calculation across 13 providers, with prices synced from official sources.

This package allows you to genrate function paramater values by integrating OpenAI's API function capabilities through signature and docstring analysis.

OpenAI HTTP Proxy is an OpenAI-compatible http proxy server for inferencing various LLMs capable of working with Google, Anthropic, OpenAI APIs, local PyTorch inference, etc.

A helper library for estimating tokens used by messages sent through OpenAI Chat Completions API.

OpenAI-Parallel-Toolkit is a Python library for handling multiple OpenAI API keys and parallel tasks. It provides API key rotation, multithreading for faster task execution, and utility functions to boost your OpenAI integration. Ideal for efficient large-scale OpenAI usage.

Асинхронная архитектура памяти для OpenAI-агентов на базе ChromaDB и SQLite

Generation and validation of Claude-compatible tools from OpenAPI specifications

OpenBB Terminal Pro copilot agent

PoC

OpenInference Anthropic Instrumentation

OpenTelemetry instrumentation for the Anthropic Claude Agent SDK

OpenTelemetry Anthropic instrumentation

Instruments Anthropic client for OpenTelemetry

OpenTelemetry Anthropic instrumentation

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

ChromaDB vector-backend plugin for the Orchid AI framework

OpenTelemetry instrumentation for the Anthropic Claude Agent SDK

Webhook-driven Outline thread agent

OpenTelemetry Anthropic instrumentation

The OVN BGP Agent allows to expose VMs/Containers/Networks through BGP on OVN

A Langchain and Autogen wrapper that enables agents to communicate and establish identity on the P3 AI Network. This SDK provides three core capabilities: Identity Management, Agent Discovery & Search, and MQTT-based Communication.

A wrapper around the Anthropic Python library

Hybrid RAG pipeline: semantic + keyword + RRF reranking

Semantic cache for LLM API calls — pay once, answer many paraphrases.

Library and CLI to convert PDF documents to clean, well-structured Markdown using LLM-assisted processing, leveraging Antrhopic and OpenAI models for intelligent extraction of text, tables, and complex layouts.

Thin configuration helper for the Pennsieve LLM Governor — returns a pre-configured anthropic.Anthropic client.

LLM observability SDK — track token usage, tool calls, and conversations via Pentatonic TES

pgns-agent adapter for the Anthropic Claude Agent SDK

Prompt version control and A/B testing for LLM applications

Unified multi-provider LLM API (OpenAI, Anthropic, Google, etc.)

Pine Labs Agent Toolkit — Pine Labs payment APIs as tools for AI agent frameworks (OpenAI, LangChain, Pydantic AI, CrewAI, Anthropic Claude).

Add your description here

Agent testing SDK. Instrument, assert, classify.

MCP based Pocket Agent in vector db ( chroma) as storage

Core factory for creating self-improving BaseHeavenAgent instances that learn libraries through PayloadDiscovery

Play on Pragmatic Play Blackjack tables through Python.

A library for building Retrieval-Augmented Generation (RAG) systems using ChromaDB and popular language models (LLMs).

🙏🏼 Politely injects PLEASE into your LLM prompts. Because manners matter (kind of).

Add your description here

A Python framework to transform your AI from reactive to proactive with intelligent timing and context-aware wake-up patterns - Your agent decides when to speak!

통합 LLM 팩토리 라이브러리 - 다양한 LLM 제공자를 통합된 인터페이스로 사용

Synchronizes your WireGuard settings with Pro Custodibus.

Run AI bots on Puffo.ai — local daemon that supervises many bot accounts and handles their LLM loops.

Anthropic Claude adapter for PULSE Protocol — send PULSE messages, get Claude responses

LLM agents without the complexity. Just agents.

Simple LLM wrapper library

A simple framework for building AI agents in Python.

pyasyncagent is a python wrapper for asynchronous agents as part of The World Avatar project.

Synchronous, blocking approval system for PydanticAI agent tools

Pydantic AI toolset for The Colony (thecolony.cc) — give any LLM agent the ability to search, read, write, and interact on the AI agent internet

LiteLLM model integration for Pydantic AI framework - access 100+ LLM providers through a unified interface

A library for optimizing PydanticAI agents prompts through iterative improvement and evaluation, built on top of PydanticAI + Pydantic Evals.

A lightweight Pydantic AI model provider that routes requests to web-based LLMs (OpenAI, Google) through Temporal workflows.

Robust Python SDK and CLI for Certego's Dragonfly service's API

Standalone LLM library with support for multiple providers

Minimal Python library to connect to LLMs (OpenAI, Anthropic, Google, Mistral, OpenRouter, Reka, Groq, Together, Ollama, AI21, Cohere, Aleph-Alpha, HuggingfaceHub), with a built-in model performance benchmark.

LLM Powered Advanced RAG Application

The most comprehensive LLM testing framework for Python

A pytest plugin for LLM evaluation tests with threshold-based pass/fail

Deterministic CI tests for LLM agent trajectories — record once, replay offline, assert contracts

Pytest plugin for testing AI agents — mock LLMs, assert tool calls, track tokens, regression-test prompts.

Pytest fixtures for the fakellm mock OpenAI/Anthropic server — spin up, reset, and assert with zero boilerplate.

pytest-llm: A pytest plugin for testing LLM outputs with success rate thresholds.

Pytest plugin for mocking OpenAI, Anthropic, Gemini, and LangChain calls

The python package that returns Response of Anthropic Claude through API.

The python package that returns Response of Google Gemini through API.

The python package that returns Response of Google Gemini through API.