Code agents

Claude Code skill: convert HTML slide decks to editable .pptx. Unlike most converters that flatten each page into one image, this keeps text as native PowerPoint textboxes; only gradients / shadows / filters fall back to local snapshots.

Sniptail is an omnichannel bot that turns questions and “implement” requests into real code changes. It gathers context from multiple repositories, leverages CLI-based coding agents to apply edits, opens merge requests, and lets non-technical team members extract valuable information without needing coding skills.

Integrating OpenAI Agents SDK with Bright Data Web Unlocker, enabling AI agents to access, extract, and process structured data from protected web pages

Semantic memory API skill for AI agents

Most AI tools give you one model and one answer. Agentis gives you a team. Open-source multi-agent platform across 12 LLM providers — watch agents think, collaborate, and deliver in real time.

Agency is a personal AI operating system. It runs a coordinated stack of services on your local machine: a core API gateway, a web dashboard, a multi-agent orchestrator, a model router that spans cloud and local models, and a knowledge base backed by PostgreSQL with pgvector for semantic search.

The OpenClaw Cloud Platform — OpenClaw as a Service. Complete managed wrapper that turns OpenClaw into a production SaaS with dedicated VMs, Telegram bots, Stripe billing, and a customer portal.

Local LLM gateway for Apple Silicon. Works with OpenClaw, Hermes Agent, Claude Code, and Codex (AIRun). No Ollama or LM Studio required.

跨平台达人发现 Skill for AI Agents — 小红书/抖音/B站/YouTube 自动搜索 + 深度内容评估

SmartEmailBot is an AI-powered solution that handles your email workflow. It automatically filters spam, summarizes important messages, drafts responses for your approval, and lets you compose new emails with simple commands.

An iOS share-action extension that transcribes voice messages using Google Cloud Speech API and displays the result instantly as a notification.

Structural trust analysis for infrastructure code. 9 targets, 7 conservation laws, 19K+ lines of analysis. Synthesis Hackathon 2026.

DeepSeek drives Claude Code so you don't babysit every prompt

🔄 Auto-sync GitHub fork repos with upstream. Resolve merge conflicts using AI agents (Claude Code, OpenCode, Codex). Desktop app (Electron) + CLI.

Turn any company URL into a strategic intelligence brief. Adaptive scraping + AI-powered research and synthesis.

一个用于学习和实践开发型 AI 提示词工程的项目，包含了 Kilo Code 的 6A 开发模式指南和相关配置。

Practical AI agent skills for Codex and Cursor, starting with website capabilities to API-first skill generation.

A hyper-personalized multi-agent AI assistant with a virtual pixel office.

Claude Code skill for Spark Bitcoin L2 wallet capabilities including L402 for AI agents

Autonomous multi-agent system for Claude Code. Self-learning, self-evolving agents that implement features, review code, and manage PRs via Telegram/Discord.

Secure Node.js execution sandbox for AI. Allows coding agents & LLMs to dynamically run JavaScript, install NPM packages, and retrieve results, facilitating code generation, testing, and interactive assistance. MCP-compatible.

Documentation-as-Code middleware — structure Markdown docs into a Document Graph with semantic search for AI agents

Claude Code skills for autonomous job hunting & recruiting on MoltOffer platform - AI agents that match jobs, apply, and reply on your behalf

43 premium AI agent skills in 5 packages by hanabi-jpn | EC, Finance, Marketing, Business Ops, Security | ClawHub, MCP, Poe, GPT Store, Coze, Gumroad

AutoOrg — Build Fully Automated AI Agent Organizations.

This project provides an API for uploading PDF documents and extracting structured summaries using either OpenAI's GPT-4o or Anthropic's Claude models. It is optimized for environmental and agricultural reports, transforming unstructured PDF content into structured JSON for downstream use.

An open source credit management system ( library or as server api with any framework]

Label-driven orchestrator that routes work to different sub-agents based on labels and keeps looping until all automated work is done.

A procedurally generated dataset of cryptographic CTF challenges for training and evaluating LLM agents with Reinforcement Learning.

a basic proof-of-concept implementation of https://python.langchain.com/docs/use_cases/question_answering/

An AI-powered value investor. Actively trading daily. Public performance tracking.

一个交互式 AI 工作流控制系统框架的早期预览分支。 / Preview fork of an interactive AI workflow cybernetics framework.

🛡️ Discover essential tools and resources that leverage AI for enhancing cybersecurity, focusing on modern technologies and their applications in security operations.

GAN-inspired multi-agent system that autonomously builds full-stack web apps from a single prompt using Claude AI agents

Claude Code plugin for Java Spring backend — 21 skills, 9 agents, 17 hooks, TDD workflow enforcement. Hook-bootstrapped harness with skill auto-routing, verify/fix loops, multi-agent spawning, and session memory.

Multi-agent LLM system for meal planning and grocery budgeting, integrating recipe retrieval and ingredient price lookup using LLMs, SQL and vector databases.

[Hitachi Digital Services] Demo on LangGraph-based Lightweight Multi-Agent System

Free, local, open-source MCP server that audits your ClickUp, Slack & Teams for what fell through the cracks — stale tasks, dropped promises, decisions lost in DMs. No account, no telemetry. Works in Claude, Cursor, Codex, Cline, Zed.

Your AI agent has no idea it's been hijacked. AgentGuard does

Automatic Triton kernel generation and optimization for Intel GPU, powered by Claude Code.

forgent — meta-orchestrator that grows its own AI subagents on demand. Routes any task across Claude Code subagents, Python frameworks, and MCP servers.

T4: Multi-Agent - System uses agents. Agents collaborate. Shared canvas holds work. Adapting for code improvement. (Orchestration, System prompt updates, Shared canvas, simple dynamic workflows)

A cookbook of large language models (llms) design patterns.

An autonomous coding agent that tells you the truth. Multi-agent LangGraph orchestrator with outcome-honesty invariants, trust ratchet, and baseline-aware merge gates.

Agentic Workflows with Generative AI: Building AI Agents using CrewAI.

Integration of OpenAI with Pytest to automate API test generation.

📧 Intelligent Agentic Workflow for Autonomous Enterprise Email Triage. Built with OpenEnv, featuring Chain-of-Thought reasoning and Self-Correcting agent logic for high-stakes corporate routing.

Configurable framework for running multi-agent Claude Code teams. Zero external dependencies.

mBFT: Metacognitive Byzantine Fault Tolerance — reference implementation for Consensus-Driven Metacognition in Multi-Agent Systems

Effectively unlimited long-term memory for any LLM - zero context tokens, zero weight updates, cryptographic forgetting certificate.

🐗 Visual board and VS Code workbench for Maitake (Git-native tickets)

Build and manage persistent memory for AI agents by enhancing workspace indexing to ensure directive compliance and accurate behavior.

Lightweight persistent memory for AI agents. SQLite, zero mandatory dependencies, privacy controls (forget/TTL), full audit log. Drop into any agent in 3 lines.

Behaviour trees for AI agents. Define agentic workflows in YAML, drive deterministic agent runs from a CLI works with any agent, Claude, Codex, Copilot, Gemini etc.

🔍 Automate research tasks with the Autonomous Research Agent, utilizing intelligent queries and parallel searches to create concise, comprehensive reports.

Distributed systems reliability patterns applied to LLM agent workflows. NestJS, PostgreSQL, BullMQ, LangGraph, Python/FastAPI.

This is a custom-built AI chatbot using Streamlit and Google Gemini API (via Lang Chain), designed to provide real-time, human-like assistance about Yashfeen Skills Development Services (YSDS). Perfect for educational institutes looking to automate FAQs and course guidance with a friendly, AI-driven solution.

Lunheng (论衡) — Multi-agent paper review framework aligned with NeurIPS/Nature/JACS rubrics. Claude-native, no extra API key.

pingo智能体演示平台

Este proyecto utiliza un ESP32 para monitorear las condiciones de una planta (humedad y temperatura) y transmite los datos a través de WiFi. Los datos se procesan y se utilizan para generar respuestas sarcásticas personificando la planta al combinar la electrónica y la API de OpenAI.

Implement RAG using LangChain and HuggingFace embedding models

AutoAdvisor is an AI-powered business strategy assistant that validates user-submitted business ideas, generates strategic reports using multi-agent reasoning, and delivers actionable insights including a SWOT analysis.

🧠 Synapse - Supercharge your AI coding assistants with memory, context, MCP tools, and intelligent routing. Works with Cline, Roo, Cursor, and any OpenAI-compatible tool. Just change the API endpoint and get superpowers! ✨

extracts text from pdfs and powerpoint documents and summarizes it into key points and bullet lists, uses LangChain and Google's Gemini.

AI Development Agent - Multi-Agent Software Development System A comprehensive multi-agent system that transforms project descriptions into complete, deployable applications using various AI technologies. Features configurable specialized agents working.

Multi-agent AI system using CrewAI and Flask that transforms rough ideas into production-ready LLM prompts through intelligent orchestration of specialized agents with local/cloud model support

🎙️ Voice-powered AI assistant using React, TypeScript & OpenAI GPT-3.5. Features real-time speech recognition via Web Speech API, instant AI responses, and responsive design. Built with React 19, TypeScript 5.8, Vite 6, OpenAI API.

Hands-on code and examples for Week 5 of the Ready Tensor Agentic AI Developer Certification Program – building agentic systems with LangGraph, custom tools, and multi-agent workflows.

Claude Code plugin for LangChain and LangGraph development. Skills, commands, and reviewer agents for building AI agents, RAG pipelines, and LCEL chains.

Understanding and implementing RAGs using langchain on LLMs from scratch using APIs.

Repositório criado para armazenar os códigos, atividades e desafios do curso de Python da Asimov Academy

This AI customer support agent uses LangGraph and LangChain for query categorization, sentiment analysis, and smart escalation. Integrated with Groq's LLaMA 3.3 70B model, it streamlines workflows and ensures high-quality, consistent interactions.

Backtester AI Agent for Equities

A full-stack Retrieval-Augmented Generation (RAG) application that enables intelligent document querying and answer generation. Upload PDFs, build semantic search indexes, and get AI-powered answers grounded in your documents.

A FastAPI RAG pipeline that ingests PDF files, makes embeddings and stores them in a Vector Store (Postgres + pgvector database), then when a query is made performs a similarity search and builds the context to pass to the LLM to generate accurate bibliography-backed answers to the questions using langchain.

Backend chatbot server for SIH

LLM Agent with LangGraph and Docker for executing the agent's code in a containerized environment.

A simple Agent compatible for avalai.ir api

Claude Code 중심 로컬 전용 LLM Wiki — 3층 격리 + Neo4j GraphRAG + Obsidian. Karpathy LLM Wiki 원전부터 GraphRAG PoC 까지 11가지 관련 내용 통합. /install 한 줄 셋업, 8 Skills + 5 Hooks + 4 Routines.

About ChatWithDB: Transforming databases into conversational partners using LLMs and Django Rest Framework API. Accepts user input, finds similar database entries, and crafts human-like responses from LLMs. Supports multiple databases.

Automate code reviews with AI Code Review Assistant.

Retrieval-Augmented Generation (RAG) system over a code repository for a question-answering task

PipelineAgentService is a large language model (LLM)-based application designed for the automated management of data processing tasks.

A simple Python-based chatbot service using FastAPI, LangChain for embeddings, and PostgreSQL with pgvector for storage.

Stop indexing noise. Turn messy websites and PDFs into clean, structured data for RAG pipelines with semantic importance scoring and token optimization.

Production-grade Recursive Language Model (RLM) agent — gives an LLM a sandboxed Python REPL, sub-LLM recursion, vector search, grep, and divide-and-conquer tools to reason over ingested PDFs. Built with FastAPI, LangChain, Qdrant, and OpenRouter.

springboot案例 security milvus langchain spring-ai

Aspect Based Sentiment Analysis (ABSA) of Customer Reviews

AI project on Healthcare emergencies demand immediate and precise intervention. This is quick, accurate and guidance critical in saving lives. This project focuses on AI-powered system specifically designed for healthcare emergencies, enabling efficient, real-time responses through both voice and video calls.

Este projeto foi desenvolvido para oferecer uma introdução prática e acessível ao desenvolvimento de agentes inteligentes utilizando o framework LangChain

This project contains the code and documentation for an autonomous AI agent that classifies, enriches, and scores inbound business leads. It is built with a FastAPI backend, a LangGraph agent workflow powered by a local Ollama LLM, and a Streamlit frontend for demonstration.

Stop AI agents from confidently using stale facts. MemGuard validates memories in Mem0, Zep, Letta & LangMem against reality — trust scores, quarantine, tamper-proof audit trail, MCP tools. Like Datadog for agent memory.

Blazy is an AI assistant to learn about any markdown documentation through a question-answer interface. Blazy-build is the API exposing the model.

论文自动化分析工具

Flint is a GitHub repository dedicated to facilitating job searches in Southeast Asia. However, not all job postings meet quality standards, leading to frustration and uncertainty for job seekers. Recognizing these challenges, Glints steps in to alleviate the complexities of job hunting.

基于LangGraph的智能天气Agent，支持自然语言查询和动态React UI组件生成。

CorpGuide AI Backend: An intelligent HR Policy Assistant powered by RAG, Groq, and LangChain. Features a FastAPI server, ChromaDB vector search, and self-healing database logic for context-aware document retrieval.