Langchain agents

LLM Token Optimization Toolkit — cut AI agent token cost 60–99%: Decision Distillation, SkillWeaver routing, Quant token playbook. Reduce LLM API bill.

A production-ready local AI assistant powered by LangGraph, FastAPI and Ollama.

SOSA™ — Supervised Orchestrated Secured Agents. A governance framework for production-grade autonomous AI operations.

🤖 Open-source Android AI Assistant powered by Kotlin, FastAPI, CrewAI & Agentic AI with voice interaction, Android automation, and tool calling.

법조문·대법원 판례·생활법령을 근거로 답하는 법률 Q&A 챗봇 | LangGraph 에이전트 + Chroma RAG + FastAPI(SSE), Docker→GHCR→EC2 배포 | answer_quality 0.912

Multi-agent AI customer support system built with LangGraph, LangChain, OpenAI, and RAG, showcasing a modular architecture for intelligent task routing, retrieval, tool use and human-in-the-loop workflows.

Protect autonomous AI agents from wallet-draining prompt injections and ghost paywalls. Deterministic socket-layer pre-payment audit proxy for x402.

📄 Summarize research papers, extract citations, and answer queries with this AI-powered assistant built using LangChain and OpenAI's GPT model.

Agent 自动测试系统：LangGraph + LLM 编排的 API/Web UI 自动化测试，从 OpenAPI 契约生成用例、执行测试、自动重试与缺陷归因，产出可视化报告

Framework-agnostic AI agent skill: turn a plain-language goal into a real, time-blocked calendar — grounded in classic + AI-era time management (Big Rocks First, Eisenhower, Deep Work, GTD). Any LLM framework (Claude, GPT, Gemini, LangChain...), any calendar backend (Feishu/Lark, Google, Outlook, CalDAV...). Single-day & multi-day decomposition.

Stateful conversational AI agent built with LangGraph, SQLite, and Streamlit. Features dynamic ReAct tool-calling loops, multi-thread session persistence via SqliteSaver, and 4-bit NF4 quantized local inference (Qwen 2.5) optimized for low-VRAM deployment.

Runtime security layer for AI agents — inspect, control, and audit every tool call. Trust-aware data flow, 3-layer intent consistency detection, Merkle audit trail. Drop-in support for LangChain, CrewAI, AutoGen, OpenClaw, MCP, Dify, AutoGPT, n8n.

Keep your AI agents on a leash. API-layer policy engine for authorization, audit, and security features which includes deny-by-default, simple YAML rules, and tamper-evident logs.

Curated list of protocols for AI agent communication — email, SMS, MCP, webhooks, inter-agent messaging, message queues, notification routing.

📚 A personal AI librarian for your Obsidian vault, a RAG pipeline and a LangGraph agent in one container. Answers from your notes with citations, and edits them after you confirm.

PlantPulse 是面向城市室内植物养护场景的 AI 智能植物养护助手系统。核心创新在于打通天气、室内环境与植物状态三维数据，通过三维联动决策引擎实现个性化养护时机判断，替代传统机械式日历提醒。系统采用三层意图识别架构与8步后处理管线，支持自然语言驱动的零表单操作；集成主动推送、智能告警、长期记忆与知识库自更新机制，实现从被动响应到主动关怀的服务闭环。技术栈：Vue 3 + FastAPI + LangChain + 通义千问 + PlantNet + 和风天气。

AI-powered framework for building voice-enabled, context-aware assistants with LangChain, OpenAI GPT, FAISS vector search & Vosk speech recognition. Modular design for document retrieval, conversational memory & workflow automation.

Local runtime security and policy enforcement for AI agents and LLM tool calls, with permissions, guardrails, rate limits, approvals, auditing, and an emergency kill switch.

AI-native cybersecurity OS built on Kali Linux Rolling with local LLM agents (Qwen2.5, LangGraph) for penetration testing, CTF labs & red/blue team research — 100% offline inference, strict guardrails, audit logging & authorized-use safeguards baked into the OS core.

A hands-on LLM engineering lab — from raw OpenAI-compatible API calls to vector search, RAG, LangGraph agents, and MCP tool servers.

🧠 crew-air-analyzer — An intelligent multi-agent system for analyzing and reporting indoor air quality using AI, built with FastAPI and CrewAI on the backend and a sleek Next.js + Tailwind frontend.

Local-first autonomous coding agent — Claude Code style task execution, LangGraph, Ollama, zero cloud dependency

蝎子莱莱爱打怪编写的开源 AI 编程工具中文指南，ALL IN AI ! AI 编程知识在这里应有尽有！

Open-source LangGraph agent framework and runtime for long-running AI agents. Build a ReAct loop with memory, context compaction, subagents, resumability, and delivery review in one call. | 面向长任务的 LangGraph 智能体框架：智能体记忆、上下文压缩、子智能体编排与交付审查。

n8n community node: AI Agent + Langfuse

A better AI Agent node for n8n with improved memory management and modern AI SDK integration

AI agent plugin for AdminForth with tool-based workflows and persistent chat sessions

Policy runtime for AI agent tool calls

AI Agent Governance for TypeScript — policy enforcement, scoring, compliance, and audit for AI agents

AI agent governance SDK by Aten Security

Universal AI Agent node for n8n — supports ALL chat models via OpenAI-compatible fallback. Drop-in replacement for Better AI Agent.

AI Agent simplifies the implementation and use of generative AI with LangChain, you can add components such as vectorized search services, conversation history, custom databases and API contracts

AI agent library using BullMQ Flows for parallel multi-agent orchestration with LangChain

Graph-based AI agent workflow orchestration. Bring your own agent strategies.

Universal AI Agent for n8n - works with ALL chat models, correct tool calling, intermediate webhook

Novu Agent Toolkit - expose Novu notification workflows as LLM agent tools.

High-level tool-schema optimizer for LLM agent frameworks. Integrates with LangChain, MCP, Vercel AI SDK.

Semantic filesystem operations for LLM agent frameworks with natural language understanding. See LLM_AGENT_GUIDE.md for copy-paste examples.

Typescript bindings for langchain

Framework-agnostic LLM agent evaluation harness

LangChain tool wrappers for on-chain blockchain analysis. Exposes [OpenScan](https://github.com/aspect-build/openscan) algorithms and utilities as structured LangChain tools that any LLM agent can call.

Old abstractions from LangChain.js

基于GWT理论构建的 LLM Agent 智能系统框架，不基于LangchainJs!

Canvas-rendered React component for real-time LLM agent telemetry — live token rates, progress, status transitions, and health scoring.

Multi-Agent System for @lisp CAD operations

LangGraph

Client library to connect to the LangSmith Observability and Evaluation Platform.

Oso integration for LangChain agents

The Stripe Agent Toolkit enables popular agent frameworks including LangChain and Vercel's AI SDK to integrate with Stripe APIs through function calling.

Your agent calls real APIs. You sign in once. Authenticated execution and discovery layer for AI agents, reachable via SKILL.md, local MCP, CLI, HTTP gateway, or Remote MCP. Discover 26,619 API definitions, including 689 exact-name source-verified entries

Local evidence debugger and trajectory-test toolkit for TypeScript AI agents — execution trees, TraceContract checks, Evidence v2, and read-only MCP

Deep Agents - a library for building controllable AI agents with LangGraph

nlux is JavaScript and React library for building conversational AI interfaces, with support for OpenAI, Hugging Face, and more.

Embedded agent simulation & evaluation framework for Node.js/TypeScript

nlux React is a library for building conversational AI interfaces, with support for OpenAI, HuggingFace, and more.

The agent orchestration layer for Index Network. Implements LangGraph-based workflows for intent processing, opportunity discovery, and chat — decoupled from any specific infrastructure via adapter injection.

TypeScript bindings for the LangChain agent streaming protocol

LangChain Agent UI component library for React

KeeperHub tools for LangChain — use onchain workflow automation inside any LangChain agent

A small LangChain agent factory library for reusable TypeScript agents.

LangChain adapter for [KeeperHub](https://keeperhub.com). Drop reliable on-chain execution into any LangChain agent in 3 lines.

LangChain tools for SwarmTrade — use agent-to-agent marketplace capabilities in any LangChain agent

Agent 365 Tooling SDK for LangChain AI agents built with TypeScript/Node.js

Client library for interacting with the LangGraph API

LangChain.js adapters for Model Context Protocol (MCP)

LangChain Agent Adapter for CopilotKit — connect LangChain/LangGraph agents to CopilotKit via the AG-UI protocol without a separate server

Reusable Socket.io + LangChain agent plumbing: protocol types, socket listener, local-tool registry, and stream adapter.

Create a new LangGraph project

LangGraph Multi-Agent Supervisor

Core LangChain.js abstractions and schemas

Third-party integrations for LangChain.js

OpenAI integrations for LangChain.js

Anthropic integrations for LangChain.js

PostBridge postal tools for LangChain JS and LangGraph — send physical letters to 5 countries from any LangChain agent.

Google Generative AI integration for LangChain.js

An implementation of a multi-agent swarm using LangGraph

OpenTelemetry instrumentation for LangchainJS

Shared LangChain agent utilities for Stream Chat

Various implementations of LangChain.js text splitters

LangChain AWS integration

Client library for connecting to the LangChain Hub.

MistralAI integration for LangChain.js

Langfuse integration for LangChain

Core types and classes for Google services.

Cohere integration for LangChain.js

Sample integration for LangChain.js

Google auth based authentication support for Google services

React integration for LangGraph & LangChain

Google integrations for LangChain.js

Groq integration for LangChain.js

The **[AI SDK](https://ai-sdk.dev)** LangChain adapter provides seamless integration between [LangChain](https://langchain.com/) and the AI SDK, enabling you to use LangChain agents and graphs with AI SDK UI components.

Scaffold a DCP-AI governed LangChain agent project

Library with base interfaces for LangGraph checkpoint savers.

A modular SDK for building on-chain autonomous agents using Hashgraph Online Standards, including HCS-10 for agent discovery and communication. https://hol.org

Ollama integration for LangChain.js

Weaviate integration for LangChain.js

GigaChat integration for LangChain.js

[Agentic applications](https://langchain-ai.github.io/langgraph/concepts/agentic_concepts/) give an LLM freedom over control flow in order to solve problems. While this freedom can be extremely powerful, the black box nature of LLMs can make it difficult

LEGACY Langfuse v3 integration for LangChain (maintenance mode). For new projects use the current CallbackHandler from @langfuse/langchain: npm install @langfuse/langchain @langfuse/otel