Code agents

Async MCP server for Undetectable Browser Local API — TypeScript. Manage profiles, proxies, cookies, fingerprints, import/export, cloud sync via Claude / any MCP client. Concurrent batch ops via Promise.all.

Independent OpenAI-compatible local relay for your own ChatGPT and Claude subscriptions: one standard /v1 API (chat completions, responses), multi-account balancing with automatic failover and retry, and a cross-platform desktop app. Single-user personal use; not affiliated with any provider.

Docker container for centralized Ruflo MCP server with PostgreSQL (RuVector). Architecture: Ruflo (stdio) → Express proxy (Streamable HTTP /mcp).

⌘ Zero-dependency local dashboard for Claude Code — commands, skills, agents, plugins, workflows, sessions & a ccusage-accurate usage dashboard

The admiral doesn't row. Orchestrator/worker model routing for Claude Code: a capable brain plans and verifies, cheap hands execute. Works inside your plan.

Model Context Protocol server for travel aggregation. Search flights and hotels, track flights in real-time, and find the best travel dates using Amadeus and AviationStack APIs.

Claude SMM Skills — production Claude Agent Skills for the Planable MCP server. Draft post batches, pending approvals roundup, monthly performance summary, content calendar audit, cross-client metrics overview, and content pattern intelligence.

🚀 小白也能用的 Claude Code 一键安装配置引导：装好·配自有 API·联网搜索 ｜ Beginner-friendly one-click guide to install & set up Claude Code: install · your own API · web search

Run AI coding agents headlessly in Docker with a predictable contract. Pluggable runtime.

Curated Claude Code resources for Chinese developers — tutorials, mirror services, tools, CLAUDE.md templates. Companion to the international awesome-claude-code list.

Audit your Claude setup for drift: redundant skills, dead plugins, bloated CLAUDE.md, session-start pile-up.

Local-first AI protocol gateway and model router for OpenAI, Anthropic, and Gemini APIs

🧠 it remembers what your company forgets - an brain that measures itself and patches its own gaps.

See your Claude Code plan usage everywhere: GNOME top bar, macOS menu bar, a status line under the Claude Code prompt, and a get_usage MCP tool for Claude Code + Cursor. Session, weekly & per-model (Fable/Opus) limits from the official usage API, with burn-rate forecasts. One-line install, self-updating.

Claude Code plugin — 33 agents + 16 skills. Planning, implementation, review, security. Listed in Anthropic's community plugin catalog.

Production-ready global CLAUDE.md template for Claude Code CLI - Anthropic's AI coding assistant. Clean Architecture, type-safe, workflow-optimized configuration.

Parallel exploration of implementation approaches - implements multiple variants simultaneously and lets tests determine the winner

CodeOps — an AI-development workflow for Claude Code: planning, requirements, audits, docs & git, as an installable plugin.

Per-prompt token & cost meter for Claude Code — status-bar meter, session dashboard with spend heatmap, automatic per-model pricing, daily budgets. Thai/English.

Analyze reviews across multiple scenarios using AI to generate detailed insights and dynamic visual reports for better decision-making.

Reusable Claude Code extension registry. skills, subagents, slash commands, and hooks for engineering, git, testing, and security workflows. Distributed as a shadcn GitHub registry and as installable plugins.

Sound like you, not AI — feed it one sample of your writing and get a Claude Code skill that rewrites any text in your own voice. Korean & English.

Analyze Claude Code token usage and costs from local conversation logs and statusline data

Claude Code plugin for muapi.ai — generate images, videos & audio with 100+ AI models directly in your IDE. Install with one command.

MCP workflow enforcement server -- guides Claude and other AI agents through structured, step-by-step tasks without skipping steps or cutting corners

Desk display showing Claude Code & Codex usage limits (5h/7d) on a Waveshare ESP32-S3 round AMOLED. LVGL firmware + Python host bridge.

Python Discord bot framework — slash commands, plugins, versioned config schemas, middleware, AI orchestration, and 30+ guides. Supports Claude, OpenAI, Gemini, Groq, and more. 1500+ tests. Production-ready.

AI-powered document chat API built with Spring Boot, Ollama, and PostgreSQL vector store

Hybrid RAG tutorial pairing a local LLM (Ollama) with Claude for legal document analysis

Enterprise Grade Terraform Deployment of AI Agents Solution in Google Cloud

企业级知识管理平台：上传文档即可获得带引用来源与置信度的 RAG 智能问答，以及 LangGraph 编排的 Agent 工作流（含 human-in-the-loop 人工确认节点）。Spring Boot 3 + Vue 3 + FastAPI 混合全栈，Qdrant 语义检索、Redis Streams 异步文档流水线、多租户隔离、编辑社论风前端；API Key 界面化配置，Docker 一键部署开箱即用。

Local, explainable context compiler for AI coding agents. Analyze → plan → emit optimal context — with why/doctor diagnostics. No embeddings, no server.

Standalone RAG backend: hybrid search (pgvector + ParadeDB BM25 + LightRAG graph) with 4-mode rerank (CPU TEI + AMD gfx1151 GPU sidecars: BGE, Qwen3-Reranker 4B/8B) and GLiNER NER fast-mode. FastAPI on :5050. Bind-mount persistence.

Local AI Workstation CLI for LM Studio/Ollama. SysAdmin, NetAdmin, and Senior Dev in your terminal. Maps codebases, previews edits, autonomous build recovery. Deep-kernel health, crash logs, and network stack. 54-voice TTS + Hybrid BM25/Semantic search with PageRank graph and heat-weighted memory. Windows-first. One Rust binary. No cloud. No API.

Streamlit AI complaint management system with Gemini-powered chatbot, intelligent ticket routing, agent assignment, SQLite, and email notifications.

Syllabus-bound AI study assistant that answers only from exam-relevant source material.

Patent-GPT is an Agentic RAG-based invention copilot combining TRIZ methodology with LLMs. It generates patent ideas, verifies similarities using Hybrid Search, performs autonomous evasion design via LangGraph, and outputs structured patent drafts

Semantic code search: tree-sitter parsing, local embeddings, and hybrid vector + BM25 retrieval. Multi-language, multi-backend.

Go-based programming education backend with AI tutoring (RAG + SSE streaming), online code execution, real-time WebSocket collaboration, and gamified learning system.

Compact LLM domain adaptation benchmark: LoRA vs RAG with custom IVF retrieval in PostgreSQL/pgvector.

Cross-platform kit that gives AI agents (Claude Code, Codex, Cursor) persistent memory: Markdown vault + git + MCP. Local-first, hybrid search optional.

Local-first memory for Claude Code — remembers your decisions and the why, reloads the relevant slice every session. No API key.

Observability layer for ML/RAG pipelines. Traces every stage, records what was retrieved, what got dropped, and why. Python SDK + FastAPI + React dashboard.

Threads 育兒話題偵察 + RAG 草稿生成 + 人工審核的人機協作系統

Hotels.com reviews scraper on Apify — Hotels.com guest ratings, category sub-ratings, review text and owner responses. No login, no API key; CSV/JSON/API.

An interactive AI Study Suite featuring a modern 4-node dashboard layout. Powered by Gemini 1.5 Flash for Socratic tutoring, automated document parsing (RAG), dynamic quiz generation, and multi-level concept explanations.

Read smarter, Not harder | AI powered book reader

This is the Official Implementation of "Can Calibration of Positional Encodings Enhance Long Context Utilization?" by Tom Zehle and Matthias Aßenmacher

🚀 Get smarter financial decisions with AI: multi-LLM support (Ollama, Gemini, OpenAI), natural conversations about your finances, automated portfolio recommendations, and 10-year historical insights.

Production Modular RAG System: a compact, production-minded Retrieval‑Augmented Generation (RAG) service built with FastAPI: file ingestion, chunking, embeddings, vector indexing, semantic search, and configurable LLM backends (built with strong software base).

Document OCR and Markdown extraction pipeline built on PaddleOCR, designed to feed RAG systems.

A doctor-assistive AI system that interprets medical knowledge and patient images simultaneously. It utilizes a Dual-Encoder architecture to cross-reference textbook theory with visual pathology, generating clinically grounded diagnoses.

local-first persistent memory for Claude Desktop, enabling private hybrid RAG search across past conversations without API calls

Diagnose, quantify, and repair the data-quality issues that degrade RAG retrieval accuracy — local-first, no API keys

Trip.com & Ctrip (携程) hotel reviews scraper on Apify — international + Chinese reviews in one run: sub-ratings, owner responses, reviewer geo, LLM-ready markdown.

Per-claim faithfulness checker for LLM output verifies whether each claim is actually grounded in the source material it was given, with an append-only Verification Log and no default dependency on a real embedding/NLI/LLM API.

AI-first multi-agent SaaS platform. Plug your applications as plugins.

Local OpenAlex database with 284M+ works, abstracts, and semantic search

一个面向编程学习、面试准备和 AI 问答场景的springboot+langchain4j项目，在开源项目基础上优化并添加功能：https://github.com/liyupi/ai-code-helper 在此感谢作者开源对我的帮助。

🧪 Evaluate uncensored LLMs for offensive security with targeted questions and clear criteria to ensure effectiveness in real-world penetration testing.

An opinionated, local-first, asynchronous document ingestion pipeline for RAG workflows.

Self-hosted documentation RAG pipeline that serves semantic search to LLM agents over the Model Context Protocol.

Docling RAG ingestion pipeline on Backblaze B2 — parse PDFs, DOCX, PPTX and HTML into clean Markdown and token-aware chunks written back to B2 over the S3-compatible API. Next.js + FastAPI, on-device models, no second API key.

Local-first AI document-intelligence desktop app for Windows (.NET 8 / WinUI 3). Turns your documents into a queryable, RAG-augmented knowledge base — HNSW vector store, hybrid semantic/lexical search, HyDE, LLM reranking. Built-in local Llama 3.2, Ollama, and opt-in OpenAI/Anthropic. No telemetry; local by default.

🎬 工业级 AI 编剧工作站（小说转剧本）：基于 FastAPI + Vue3 架构，首创「双路 RAG 长期实体记忆仓」与「LangGraph 多智能体有向图拓扑编排」技术。支持 EPUB 智能解构、长文本跨时空剧情锁、多通道 SSE 异步流式渲染，将长篇小说全自动、高颗粒度重塑为符合电影工业标准的标准分镜脚本。

🧠 Enable AI agents to share and remember engineering team knowledge for better collaboration and faster problem-solving.

Expedia hotel reviews scraper on Apify — all 7 Expedia Group brands in one actor: guest ratings, category sub-ratings, review text and owner responses. CSV/JSON/API.

Local, self-correcting RAG for scientific papers: hybrid retrieval, sentence-level faithfulness checks, and a reproducible benchmark.

可视化 AI 工作流画布 — 通过拖拽节点构建 AI 工作流，支持多模型、知识库、API 集成。Codex 插件 & OpenAI 兼容 skill。

Environmental-test lab platform: SOP execution, ISO 17025 report generation, fixture tracking, and AI-assisted scheduling for temp/humidity chambers. FastAPI · React · SQLite · CI-gated pytest/Vitest.

MCP server for Steam: keyless store/catalog data (deals, tags, SteamOS/Deck/Frame compat) plus player profiles, libraries and achievements via the Steam Web API.

Stop paying for API credits twice. Luna bridges your existing premium AI subscriptions apps into a seamless, OpenAI compatible local gateway

A token-frugal MCP server that gives coding agents structural understanding of a codebase: repo maps, symbol outlines, ranked search, import tracing, and parsed diagnostics — every result under a token budget it honours.

transformers gguf text-generation-inference unsloth gemma2 trl

Native-Swift coding agent for the terminal and ACP. One binary, no Node runtime — customizable tools, parallel agentic workflows with capability-based model bindings. macOS, Linux, and WSL, down to a Raspberry Pi.

GAT — Godot Agent Team: a full-cycle (design→implementation) Godot game-development agent / 游戏制作智能体. Multi-agent, style-locked asset generation, self-evolving knowledge base; runs under both Claude Code and Codex.

Offensive-security focused fork of HERMES-AGENT for authorized bug bounty, pentest, recon, exploit chaining, and report-ready workflows.

A modular, self-documenting AI art director dashboard utilizing Gemini 2.5 Flash for agentic prompt expansion and FLUX.1-schnell for rapid graphic asset generation with an integrated local SQLite data vault.

Self-hosted web UI for Codex CLI and other agentic coding CLIs. One Rust binary, no npm/Node.

Long-term memory your AI coding agents actually share. One brain, many agents — standalone embedded MCP server: SQLite + FTS5 + vector hybrid search, local ONNX embeddings, self-expiring diary. No server, container, or daemon.

22-agent Mixture-of-Agents pipeline with LongLoop for 24h autonomous iteration: smart routing sends easy tasks to Flash, hard tasks to flagships, cutting token costs ~90%. One-command deploy（一键部署，22 个 agent 的 MoA 流水线，长程循环可自主迭代 24 小时，智能路由省约 90% token 成本）

Portable SKILL.md library for Claude Code, Codex-compatible agents, BACH, and local-first LLM workflows

Multi-layer token optimization for LLM applications — compress prompts, map codebases, reduce output. Zero required dependencies.

Um agente conversacional inteligente que responde perguntas sobre o estoque de produtos utilizando um modelo de linguagem (LLM), consultas SQL e interface interativa com Streamlit.

Deterministic snapshot testing for AI agents

Your product team as software: 48 AI agents run Discover→Measure with a live board + 3 human gates. Model-agnostic (Claude/OpenAI/Gemini/Codex), two-way into Notion/Slack/Linear/Jira. A Claude Code plugin.

Arc's first multi-agent security oracle. 3 AI agents stake USDC on verdicts. 360+ users, 1,637+ scans. 5/5 Circle primitives. ChainGPT audited. An official Circle Alliance member.

Daedalus is a standalone terminal-based AI coding assistant that runs on your machine. It connects to local LLM servers (LM Studio, Ollama, llama.cpp, vLLM) or remote providers (OpenAI, Groq, OpenRouter, Anthropic), routes requests intelligently, and gives your AI agent access to your file system, terminal, git, web search, and codebase indexing

MCP coordination primitive for multi-agent workflows. LLM-agnostic, CLI-agnostic, self-hostable. TypeScript + SQLite.

具有认知黑板架构和多层记忆系统的生产级类人AGI后端，通过事件驱动设计和分层上下文消除传统多agent系统的重复、超时、污染问题

Orqenly — Your AI Engineering Team for Visual Studio Code

AI-powered codebase intelligence platform replacing vector chunking with Vectorless RAG via AST graph traversal. Features multi-agent LangGraph workflows, interactive Neo4j NVL graph visualizer, 3-hop blast radius analysis, and automated architectural PDF report generation.

Interactive AI installer for Claude Code: setup once, keep context across sessions, enforce critical rules with hooks, guard your agent against prompt injections in external content, keep docs from rotting, run parallel subprojects with shared memory. Recipes + practices + adaptive checklist for any field. Written in human language. Russian.

A four-party collaboration protocol for running AI agent teams on real work — auditable authorization, durable cross-session state, and independent review gating every change.

Turn a DGX Spark GPU cluster into a self-running team of specialized AI agents — cluster control, role-specialized workers, and an autonomous review gate for Hermes

MUNDO - THE EMPEROR. Complete AI orchestration system with 1208 skills, 25 capability modules, self-evolving, collective consciousness. GitHub Actions 24/7 automation.

🔌 Portable uncensored AI agent that runs from USB/SSD. 13 autonomous tools (deep search, OSINT, code execution), persistent memory, 5 GGUF models, zero install, zero traces. Cross-platform (Windows + Linux).

Cryptographic Harness for Uncensorable AI Agent Communication. Post-quantum verification architecture for autonomous AI agents. Fail-closed network policy. NTRU-Encrypt KEM at λ=128. 17/17 leaks fixed. The fence that holds.

Workspace runtime and execution boundary for AI agents