Business agents

Elegant, modern and asynchronous Telegram MTProto API framework in Python for users and bots (Navy Fork)

KGraphRAG

Anthropic API client library for kiarina namespace

Autonomous OSS-repo health for solo maintainers (Python port of @p-vbordei/agent-fleet)

한국투자증권 OpenAPI Python Wrapper - Korea Investment & Securities Trading API Client

KISS Agent Framework - A simple and portable agent framework for building and evolving AI agents

A LiteLLM plugin for intelligent model routing and request tracking with Kloom

Local-first Knowledge GraphRAG MCP server

Python SDK for the Kraken Agent API

LLM infrastructure layer with multi-provider fallback, health monitoring, speed probing, and alerting.

KyberShield security integration for Claude and Anthropic SDK

Building applications with LLMs through composability

Expose LangChain and LangGraph agents through ACP Kit.

Building applications with LLMs through composability

Integration package connecting Claude (Anthropic) APIs and LangChain

Intelligent cache management for LangChain Anthropic models with advanced optimization strategies

Building applications with LLMs through composability

An integration package connecting Chroma and LangChain.

Building applications with LLMs through composability

LangChain integration for CoordiNode — GraphStore backed by graph + vector + full-text

Building applications with LLMs through composability

Building applications with LLMs through composability

Building applications with LLMs through composability

LangChain integration for Ferro Labs AI Gateway — chat, streaming, embeddings, and tool calling across 30+ LLM providers via a single OpenAI-compatible endpoint

This repo walks through connecting to the Google Calendar API.

Implementation of GraphRAG (https://arxiv.org/pdf/2404.16130)

Use GridGain as a Vector Store, Document Loader, LLM Cache, Key-Value Store and Chat Memory within LangChain, and as a LangGraph checkpointer and cross-thread memory store.

LangChain tools for hreflang SEO analysis using hreflang.org API

Building applications with LLMs through composability

The first autonomous routing system for AI agents. Routes to the optimal execution path to prevent failures, degradations, and cost spikes before they impact users.

Stream and print responses from LangChain's language models asynchronously.

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

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

LangChain-compatible MCP client with OAuth 2.0 Client Credentials (M2M) flow support

A library for managing multiple LangChain model configurations with validation and automatic agent creation

Langchain-Nexus is a Python library enabling easy integration with diverse language models like ChatGPT and GLM through a unified interface.

LangChain agent middleware that routes model calls through the NoPII PII-tokenization proxy

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

63 deterministic quant calculators + 10 composite workflows for LangChain agents. x402 USDC payments on Base or Solana.

An integration package connecting Salesforce and LangChain

Anthropic Agent Skills implementation for LangChain

LangChain tools for SystematicMind Signal Intelligence — real-time BTC & equity market signals for AI agents.

Building applications with LLMs through composability

Building applications with LLMs through composability

Building applications with LLMs through composability

LangExtract provider plugin for Anthropic Claude

Anthropic Claude provider plugin for LangExtract

A SurrealDB Checkpointer for Langgraph with both synchronous and asynchronous support.

TTL-based thread retention for LangGraph checkpointers

An integration package connecting Synapse memory and LangGraph. Privacy-first checkpointing and cross-thread memory store.

anthropic integration for lavague

Send Mastodon threads from Flat OpenDocument files.

Legal document processor with grounded retrieval and learning from edits.

legalsops for retriever and reader

A lightweight LLM API proxy framework with network connectivity and usage analysis

A module for using GPT-3/4 for free (Needs Chrome or Chromium browser for GPT-3)

A lightweight LLM agent framework supporting async OpenAI and Anthropic APIs with ReAct agents, TODO-based agents, and built-in tools

The unified LLM runtime — local inference, API proxy, and monitoring. A powerful alternative to Ollama + LiteLLM, built in Rust.

Add your description here

Lightweight Anthropic Messages API proxy with LiteLLM-style config — load your middleware from any project

A lightweight Python library for tracking LLM API costs via litellm's callback system

MCP server giving AI agents access to 100+ LLMs through LiteLLM

Universal LLM API client with Rust-powered polyglot bindings.

Auto-synchronized Python bindings for llama.cpp using CFFI ABI mode

llama-index llms anthropic integration

LlamaIndex LLM integration for Ferro Labs AI Gateway — route LlamaIndex workloads across 30+ LLM providers via a single OpenAI-compatible endpoint

llama-index multi-modal-llms anthropic integration

llama-index packs chroma_autoretrieval integration

llama-index packs implementation of a hierarchical agent for finance chat.

llama-index postprocessor FlashRank rerank integration

llama-index readers airbyte_salesforce integration

llama-index readers chroma integration

llama-index readers earnings_call_transcript integration

llama-index readers sec_filings integration

LlamaIndex integration for BuyWhere — search products, discover deals, and browse categories through the BuyWhere product catalog API

llama-index finance-tools integration

OSINT intelligence platform integration for LlamaIndex — 15-category intelligence reports, domain recon, and social media lookup

llama-index tools salesforce integration

llama-index tools yahoo_finance integration

llama-index vector_stores chroma integration

Unified interface for multiple LLM providers with advanced features (routing, privacy, logging).

llama-optimus is a lightweight Python tool to automatically optimize llama.cpp performance flags for maximum tg & pp token/s throughput. Powered by Bayesian optimization with Optuna

Asynchronous Fortnite API wrapper.

CLI utility and Python library for interacting with Large Language Models from organizations like OpenAI, Anthropic and Gemini plus local models installed on your own machine.

LLM actor: pool, circuit breaker, retries, metrics

LLM access to models by Anthropic, including the Claude series

A flexible gateway for connecting and managing multiple LLM providers

Lightweight, pluggable adapter for multiple LLM APIs (OpenAI, Anthropic, Google)

Runs a throughput benchmark for LLM APIs, measuring generation throughput, prompt throughput, and Time To First Token (TTFT) under various concurrency levels.

Multi-LLM Provider Library

Azure AI Foundry plugin for LLM - access Anthropic, Llama, Mistral and more via Azure

LLM plugin for Anthropic's Claude on AWS Bedrock

Behavioral testing for LLM applications. pytest plugin with semantic assertions, multi-turn conversation testing, and drift detection. No LLM judge needed.

CLI tool for comparing LLM API pricing, ranked by cost-effectiveness against LMSYS Arena scores

Benchmark any LLM provider against your actual prompts — latency, cost, quality

Unified Python library for LLM APIs (OpenAI, Anthropic, Gemini, xAI, Groq, custom)

LLM-Blender, an innovative ensembling framework to attain consistently superior performance by leveraging the diverse strengths and weaknesses of multiple open-source large language models (LLMs). LLM-Blender cut the weaknesses through ranking and integrate the strengths through fusing generation to enhance the capability of LLMs.

Pre-flight LLM cost estimation and budget enforcement

Prevent LLM cache poisoning with Confidence Gap Analysis — intent-aware thresholds, zero false serves

Agent Cache Runtime for building cache-aware LLM applications.