Code agents

Streaming PII proxy for LLM chat. Pluggable detector, per-session vault, and cryptographic provenance-anchored reversal (PASP) that closes the false-attribution attack every other streaming library silently has.

Flooky is a privacy-focused AI assistant designed for natural, intelligent conversations. Powered by Anthropic, it offers context-aware responses, memory features, and a clean, user-friendly interface.

Patina - High-performance terminal client for Claude API

Slash commands for Claude Code that analyze, validate, and optimize your AI agents. Rate across 8 pillars, find issues, auto-fix problems.

🤖 Production-grade autonomous customer support agent using Claude AI & MCP achieving 100% first-contact resolution. Built for Claude Architect Certification (Scenario 1) - demonstrates agentic architecture, tool design, and reliability patterns.

Your personal open-source talent agent — an AI pipeline that analyzes your GitHub history and recommends active OSS projects where your skills fit best, with a concrete first contribution for each.

A macOS-first CLI for managing Anthropic/Claude Code environment profiles with one-command switching, Keychain-backed token storage, and zero-friction setup.

Slack-ClaudeCode Vanguard

Skim: A MCP server for Claude Code — skim large outputs, return only schema. Save context, save tokens.

AWS Summit 2024 Jakarta --- ObservabilityAI: Memanfaatkan Amazon Bedrock Untuk Memantau Kinerja RESTful API Golang

Real-time Claude.ai/Codex subscription awareness for AI coding assistants. Surfaces your live Session 5hr and Weekly 7day utilization, forecasts when you'll hit the limit, gates expensive operations before they run, and measures real per-task cost — all without leaving your machine.

Personally curated and maintained collection of Claude Code plugins

🧠 AI Memory Proxy: LLM with persistent user memory using PostgreSQL + pgvector. AI-driven fact extraction, semantic search, single API call optimization.

This is a comprehensive large model service platform designed to facilitate rapid deployment and application of large model services in small and medium-sized enterprises. The platform mainly includes large model service and application modules, data management modules, and development documentation modules.

Use LLM/AI agent for Web scraping (collection data) and analysis data with deep research

This is standard mini–RAG Application from scratch

An AI-driven Hacker News aggregator providing automated Chinese translations, structured summaries, and RAG-based Q&A to help users efficiently access technical insights.

DSCode is a free, comprehensive learning platform for mastering Data Science, AI, and Machine Learning. With 445+ curated problems across 16 topics including Python, ML, Deep Learning, NLP, Computer Vision, Gen AI, RAG, and AI Agents, DSCode helps you build job-ready skills through hands-on practice.

Demonstrates the core aspects of RAG, built using NextJS and Supabase

Open source AI inference server with Model Marketplace, Document RAG, and OpenAI-compatible API

RAG-Based Research Assistant

AI-powered debate assistant using Groq, Gemini APIs, and SearchXNG for intelligent argumentation. Built with RAG (Retrieval-Augmented Generation) architecture to source academic research and data. Features real-time web search integration and upcoming Model UN debate simulation mode.

AI-powered Web3 chat that mixes live market and DeFi data (CoinGecko, DeFiLlama) with RAG over a PostgreSQL/pgvector knowledge base; React + Vite frontend and Express backend.

Your screen history, searchable and automated - Windows OCR + REST API + AI + RAG

Java Spring Boot RAG & hybrid search system for graduation projects: Elasticsearch BM25, BGE-M3 vector search, reranker, evidence-grounded QA, book recommendation, Vue 3, offline evaluation.

A tutorial-scale, fully local RAG-based chatbot built with Gemma 3 via Ollama + Bright Data SERP API + Chroma. This researches topics comprehensively and then answers questions using retrieval-augmented generation.

Perplexity-style conversational search — plain-English questions answered from live Google + Bing results, grounded and cited. FastAPI + React + Cloudflare LLaMA 3.1 70B.

A RAG assistant for reviewing your notes

RAGify is a modern chat application that provides accurate, hallucination-free answers by grounding responses in your documents. No more made-up information - if the answer isn't in your knowledge base, RAGify tells you so.

A full-stack knowledge graph-based Retrieval Augmented Generation (RAG) system for Vietnamese tax law documents. Compares vector search vs graph-based retrieval approaches.

me.fyi python backend with core LLM and RAG logic, flask API, Twitter bot

Portable vector database with auto-installing Ollama embeddings. Zero-config semantic search via SQLite.

A Retrieval-Augmented Generation (RAG) application for querying legal documents. It uses PostgreSQL, Elasticsearch, and LLM to provide summaries and suggestions based on user queries. Features data ingestion with Airflow, real-time monitoring with Grafana, and a Streamlit interface.

Source code for the Gilded Age Gourmet, a cooking chat app based on the Boston Cooking-School Cook Book.

🎓 你的 AI 备考搭子：基于 RAG 的智能学习助手。支持 PDF 知识库构建、智能问答、自动出题与错题本管理。技术栈：Spring Boot + LangChain4j + Chroma + Kafka

A flexible Haystack 2.0 pipeline integrating Retrieval-Augmented Generation (RAG) with any OpenAPI service

🧩 Intelligent Chunking Methods for Code Documentation RAG

Create unlimited AI chatbot agents for your website — powered by OpenAI-compatible LLMs, RAG, and MCP.

GitStarRecall is a local-first AI enabled web app that turns your GitHub stars into a searchable memory system on your browser locally.

This project is a Document Retrieval application that utilizes Retrieval-Augmented Generation (RAG) techniques to enable users to interact with uploaded PDF documents. By leveraging a Large Language Model (LLM), users can ask questions about the content of the documents and receive accurate answers based on the information retrieved.

A comprehensive RAG FastAPI service that handles document uploads and retrievals, built with Python. Uses PyMuPDF for document processing, turbopuffer for vector storage, OpenAI for models, and cohere for reranking.

Minimalist Telegram bot for codebase analysis using LLMs and RAG

Production-grade AI coding rules for Cursor and Claude Code. 15 rules + 9 doc templates + skills + agents + MCP setup. Drop into any project.

Official web application for managing, configuring, and testing the Brevia API

Engineer markdown snapshots of your application for promoting LLMs manually.

Self-hosted and local-first application for inference and RAG on consumer grade hardware.

An Abstraction Using a similar API to Pinecone but implemented with pgvector python

A Python project that deploys a Local RAG chatbot using Ollama API. Refines answers with Deep Research from external websites, and uses both Embedding and LLM models.

Practical AI & more workflows for coding, MCP, local AI, productivity, research, media, and ops.

Fastest way to make a RAG for your current website. WIP

Your Family Translator — An AI-powered wellness platform combining emotional companionship, community support, and self-reflection tools in a calming beach-themed experience.

Web crawler for generating RAG knowledge base files

Give your AI a perfect, infinite memory. A local-first, zero-LLM memory system and Model Context Protocol (MCP) server designed to give AI assistants (like Claude, ChatGPT, and custom agents) a searchable, structured "Memory Palace."

A Next.js notes assistant powered by Groq AI, Prisma, and SQLite.

A live, evolving collection of open-source AI agents and real examples showing how businesses can use AI to automate work, save time, and explore new ideas.

DAUT – Documentation Auto Updater - AI-powered documentation generator for your codebase. MCP-Connector

A Retrieval Augmented Generation (RAG) implementation in python using django and streamlit, along with a working authentication system.

"A Retrieval-Augmented Generation (RAG) system for document query and summarization using vector-based search and language models.

High level AI chatbot module, wraps OpenAI GPT Chat API. Examples are given for Slack, Google Chat, and FastAPI

A powerful RAG tool that scrapes YouTube channel videos, extracts transcripts, and enables AI-powered chat interactions using Google's Gemini API.

The #1 AI-native monorepo template — Next.js + Expo + FastAPI + LangGraph + Supabase with 90% code sharing

Official EmbedElite Enterprise Chat

Official Code repository of our approach Fashion-RAG: Multimodal Fashion Image Editing via Retrieval-Augmented Generation

数游AI平台为您聚合了包括OpenAI、Google、Anthropic、Grok、DeepSeek、通义千问在内的众多前沿大模型。无论您面临智能对话、AI绘画还是视频生成的复杂需求，我们都能为您提供全方位、持续进化的智能创作服务。

AI long-form novel writing pipeline with SQLite memory, guard registry, continuity evidence, anti-hallucination checks, and revision loop.

Convert your repositories into PDFs and structured JSON outputs, giving LLMs full context of your codebase

Oshepherd: Ollama instances Orchestration

Weld connected structure toolkit for agent-first repository discovery

Quick Checkpoint is a VS Code extension that helps you use code history as context when working with AI coding assistants. It is useful for using old versions of code as context to help undo when LLMs break your code.

Decantr AI design intelligence layer for AI-generated web applications

AI context engine for Claude Code, Cursor, Windsurf — pack, compress, and optimize any codebase. Save 60-90% tokens. Web dashboard on port 7456.

Trigger-Driven Dynamic Context Loading for Code-Aware LLM Agents

LLM observability for React Native and Expo. Track token usage, cost, latency, and TTFT for Claude, GPT, and Gemini calls on device, with optional remote sync.

This template is an example of an AI-powered task management system

This template is an example of an AI-powered task management system

29 Claude Code Skills + Obsidian Knowledge Base = Full ABA Clinical Supervision Automation | AI驱动的ABA临床督导自动化系统

Automates personalized internship outreach emails using Python, Gmail API & Google Sheets — with smart delays, template rotation, and logging.

即插即用的 AI Agent 技能集合 — 飞书集成 · Mermaid 图表 · Codex 编排 · 前端设计规格

The Toolpack SDK is a unified TypeScript SDK for building AI-powered applications. It provides a single, consistent API to work with multiple AI providers OpenAI, Anthropic, Gemini, and Ollama without vendor lock-in.

Autonomous coding agent — queue tasks, schedule jobs, and let Claude Code execute them in isolated git worktrees while you sleep

Assess and improve your codebase's AI-readiness. Get an AI Readiness Score (0-100).

AI-powered brand monitoring workflow using Bright Data SDK, OpenAI & SendGrid. Automatically scrapes Google News, analyzes sentiment & emails reports.

Zing plans, builds, tests, and ships clean code with AI. Zing keeps you in charge at each step. This is the Zen of Zing.

WebDriver BiDi-first browser harness for AI agents, inspired by browser-use/browser-harness.

Bridge to run Codex CLI as a Claude Code native teammate — multi-model agent orchestration for AI-powered development

Structured document annotations with REST API + MCP. Replace Google Docs commenting with agent-consumable feedback.

🧘 NoWorries (无事) - 开源 AI 桌面助手 | Open-source AI Desktop Agent with Permanent Memory & Safe Mode | Claude Code / Codex / Qoder 平替。基于 OpenClaw / OpenWork / Pi Agent 开发

Instagram Reels Transcript API examples using Apify. Integrations for Python, Node.js, Java, Go, Rust, cURL, batch processing, and MCP workflows for ChatGPT, Claude, and Gemini.

Self-improving AI agents that run 24/7 on Claude Code. Discord, Telegram, Slack. One command setup.

A Model Context Protocol (MCP) server offering professional tools and templates for hierarchical prompting, code hygiene, visualization, memory optimization, and agile planning.

Make your OneNote notebooks survive in the age of AI — CLI with full-text page-level search via Graph API

Write-capable Solana AI agent — swap tokens, send SOL, and manage your wallet through natural language. Experimental: review before trusting with funds.

Custom modes for better planning and executing software development tasks with AI agents.

AI-readable codebase navigation indexes (README_AI.md) via a deterministic CLI — coding agents navigate faster, with fewer tokens. A/B-benchmarked.

Forge Plugin: Zero-dependency governance for Claude Code. 21 commands, 22 agents, 29 skills.

Official Python SDK: Multi-agent payments, x402 Auto-Pay, and Base L2/USDC support.

Chrome DevTools for AI Agents — real-time observability, hallucination detection, session replay, and cost tracking. MIT licensed.

AI Career Mentor is a web application powered by Google's Gemini API that helps users explore and plan their tech career paths based on interests and goals.

Chief Executive Orchestrator - Claude Code plugin coordinating 150+ specialized agents across all domains

Terminal UI harness tool for Salesforce. Orchestrator + 6 persona subagents, jsforce + sf CLI, qmd RAG. Powered by Claude Opus 4.7.