Code agents

📚 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.

小语 AI 工作台 - 有记忆/情绪/进化系统的 Web AI 工作伙伴（多模型+文件交付+一键分享）

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。

The complete, safety-first MCP server for TIDAL — 112 tools for catalog, lyrics, recommendations, favorites, playlists, folders, discovery, and approval-gated writes.

Vibecoded custom windows file explorer

🤖 Python MCP server for AI-powered expense tracking. Built with fastmcp & uv. Chat with Claude to manage finances naturally.

https://youtu.be/u8KJYQgUOs8 AI-powered paralegal assistant that extracts, summarizes, and analyzes legal documents. Upload PDF/DOCX contracts to get instant summaries, extract key clauses, and perform intelligent document analysis using OpenAI.

Local AI assistant (Jarvis-like) for desktop automation, file management, and coding tasks using FastAPI and LLMs.

真正具备工程闭环交付与工业审美的本地多智能体协作与自主开发桌面工作站

CLI tool and MCP server for handling sensitive information without exposing values to AI assistants

Chrome extension that orchestrates multiple AI chatbots (ChatGPT, DeepSeek, Gemini, Grok, Claude, Qwen) — send one question to all, collect answers, aggregate via expert AI. No API keys needed.

A stealthy, high-performance AI Chrome Extension that provides instant code analysis, bug detection, and intelligent explanations via NVIDIA's Llama API. Zero DOM injection. Pure productivity.

Open-source MCP server that runs self-hosted WordPress like a senior admin: 150 tools for content, SEO, security audits, Query Monitor-style profiling, theme.json & accessibility, plugin settings as admin, and multi-site fleets. MCP 2026-07-28, Cloudflare Workers or stdio. Free, no usage caps.

🌌 DeepSeek Orbit — The ultimate open-source Chrome extension for DeepSeek AI. Features smart Persian/Arabic RTL alignment, │ custom wallpapers, developer code tools (line numbers, word wrap, fullscreen modal), in-chat keyword search, bookmarks, slash

Practical CLAUDE.md and AGENTS.md patterns that make AI coding agent rules testable and enforceable.

Five production-ready Claude Skill templates: one-pager writer, code reviewer, brand voice keeper, CSV cleaner, decision-doc generator. Each demonstrates a different SKILL.md pattern. Drop into Claude Code or Claude.ai. MIT licensed.

Claude Code wrote `grep` 4,575 times and `rg` zero times across 25,216 Bash calls in one user’s transcripts. weir is the hook that fixes that — tells the model what shell tools you actually have, suggests rewrites for the antipattern cluster, refuses to run the unambiguously-broken ones (`cat FILE | grep`, `which CMD`).

Editorial AI · 直笔 — A Claude Skill for serious writers. Skeleton-first writing, anti-fabrication, diagnosis+prescription, word count discipline. Built for journalists, analysts, PR teams, B2B writers.

Agentic Coding TUI, not the Ruby gem

Your repo has a working product but the README is losing you stars. github-repo-audit runs 5 specialist agents in parallel to audit README, positioning, and discoverability — then drafts a severity-ranked fix list and applies approved changes via Claude Code.

Find the best and newest models for oh-my-openagent (OMO) configurations using Artificial Analysis data

An AI changed your code. RunBoth runs both versions and tells you what actually behaves differently, including the functions nobody touched.

AI Testing Framework using Promptfoo for automated LLM evaluation, red teaming, and CI/CD integration with Jenkins. Supports prompt validation, security testing, custom assertions, API-based model testing, and quality gates for enterprise GenAI applications.

Apple Ads Platform API MCP server. All 99 operations (Apple Search Ads + Apple Maps brand ads) exposed to Claude, Cursor and any MCP client through 4 token-efficient tools.

Codelicious is a headless autonomous developer CLI that transforms markdown specifications into production-ready Pull Requests with zero human intervention. It orchestrates a dual-engine architecture powered by Claude Code and Hugging Face (DeepSeek for reasoning and Qwen for Coding). Specs -> Code -> Tests -> Iterate -> PRs/MRs

Local proxy that keeps your API keys and secrets out of LLM requests. Works with Claude Code, Cursor, Codex and any tool.

OpenCode plugin for recall and analysis of past OpenCode sessions: search, grep, and cost/usage insights across your session history via 18 LLM tools over the SQLite database.

Méthode et garde-fous pour travailler avec un agent de code sur un projet qui dure. Extrait de trois projets réels et de leurs incidents.

Give AI agents a memory that outlives the session: local-first SQLite per project, hybrid search, workspace sandboxes, and optional cloud sync.

Natural language → optimized AI context window. Tell it what to build, get exactly the files an LLM needs, trimmed to fit, in seconds.

A local-first, open-source harness for organizing your files with an AI agent, an MCP server for Claude Code, Codex, Cursor. BYO-key, no cloud.

Agent-native CLI for fantasy sports leagues. ESPN first, structured output, self-diagnosing.

Python MCP server for Testmo - connect Claude, Cursor, and other AI assistants to your Testmo test management instance. Built with FastMCP.

The future of vibecoding.

Typography skills for AI coding agents — 20 focused skills + a /type router, extracted from 10 canonical typography books and reconciled against WCAG 2.2 and current browser behavior.

MCP server that turns any SAP CAP or OData v4 service into LLM tools by reading its OData metadata document. No per-service code.

SKILL.md-standard proofreading skill — code & document review with real, verified formal-verification backends for C, Python, Rust, Java, and C++

Quota-aware subagent routing for Claude Code. Reads live rate limits across codex/grok/kimi, dispatches to the CLI with headroom, isolates in a git worktree, and verifies the diff before reporting.

Smart LLM and cloud code optimization tool that cuts token costs by up to 75%. Perfect for AI developers seeking maximum efficiency and lower expenses in 2026.

Point a metered, verified, replayable agent graph at a repository you own. Companion code to the book. Educational software, from youcanbuildthings.com.

Universal, full-featured, portable MCP server for the Bitrix24 REST API (CRM, tasks, scrum, calendar, disk, users, messaging) — read and write.

DeepSeek API peak/off-peak pricing tray app & alerts (Win/Mac)

DEV.to MCP Server — fast, single-binary Model Context Protocol server for the Forem/DEV.to API. Go + stdio, no cold starts.

The missing semantic layer for AI-readable software projects. One verifiable artifact every AI agent can read.

A GOST Rewriter HTTP plugin that converts bidirectionally between OpenAI Chat Completions and Anthropic Messages API formats

Open-Source RAG Platform for Companies. Knowledge bases with multilingual retrieval and reranking, answers traceable to the source document, MCP server and a public API. No lock-in on the answering model, from AWS Bedrock, Azure, Ollama, Portkey, LiteLLM to a model running on your own infrastructure

transformers gguf qwen2 text-generation function-calling tool-calling

药用植物次生代谢科研推理 LLM Agent:多组学分析流水线 + LLM 证据推理,确定性计算与 LLM 推理分层

具备学情诊断与持续规划能力的自适应伴学智能体（FastAPI + React + RAG，掌握度只认独立有效证据）

多 Agent 协作开发框架：项目负责人 + 6 单责角色 + 阶段门禁 + 实时看板 · 单写手 + 只读参谋 · 四实现（ZCode/OpenCode/WorkBuddy/Universal） ｜ Multi-agent delivery framework: project owner + 6 single-accountability roles + stage gates + live board · single-writer · read-only advisors · 4 implementations (ZCode/OpenCode/WorkBuddy/Universal)

住宅物业管理平台：房屋、人员与租赁、报修工单、投诉、访客、车辆车位、设备巡检和收费。Flask + SQLAlchemy + MySQL；写操作走统一服务层，权限用 RBAC 加行级数据范围，后台内置受控 AI 助手。

Offline $0 decision layer for coding agents: Choice/Score/Noul primitives, BELKI confidence gatekeeper, ultra-planning, red-teaming, research and RLVR self-improvement -- as an MCP server + CLI + Claude Code skill.

Application Security orchestration platform

A working AI agent built in C from scratch — no frameworks, no SDK. ReAct loop, tool system, filesystem sandboxing, 200+ tests.

中文问数（ChatBI）智能体：语义层 + SQL 智能体双路径，sqlglot 安全门，浏览器内 Python/DuckDB（WebAssembly）+ Cloudflare Workers AI

DeepResValue 深度研值 — 全学科 AI 科研助手 Agent SaaS。中文一句话驱动：Agent 在 100+ 专业科研技能指导下自动写代码、云端执行（Python/R/MATLAB/SPICE 四大内核），覆盖空间计量、高级计量、生信分析、CAD 分析、机器学习、贝叶斯统计、结构方程、流行病学等前沿方法与论文写作、数据分析、文献综述、科学计算全流程，支持数学建模（CUMCM）、三创赛、挑战杯等国家级竞赛，自动生成 Word/LaTeX 专业排版，MCP 数十个数据源、BYOK 自接模型。让科研回归本质，让工具服务于思想，让创造不被重复所困

跨境物流HS Code智能归类Agent：RAG混合检索+ReAct主动追问+三层防幻觉+50组评测

Self-hosted AI agent harness in Rust, built for long tasks: a virtual session keeps work coherent across context compaction & restarts. Telegram/Discord, durable queues, fail-closed permissions, Codex/OpenRouter routing, a JSONL receipt for every step. 6 deps, no async runtime, Windows-first.

Weekly macro regime switch: 4 variables (rates/credit/earnings/liquidity), hard-coded risk-off override, no price predictions.

A small Python harness that keeps an LLM coding agent on track: durable memory, a code graph, a live todo plan, and loop detection. Runs in your terminal.

A self-hosted AI companion exploring evolving relationship memory, initiative, and cross-device context.

证据约束的代码诊断工作台：确定性静态分析拥有源码事实，LLM 只提假设，resolver/validator 决定能否绑定回真实操作——证据不足保持 unknown/abstained，从架构抑制幻觉。已在真实开源项目发现 bug（stunner #89 已被上游确认修复）。Python。

A daily-driver AI agent runtime built solo: multi-process isolation pods (MCP/LSP/workflow), event-sourced task ledger, proactive scheduling, and multi-channel delivery.

AI-driven CAD workbench and coding agent for Windows, evolved from illusion-agent: shared canvas for design discussion, headless 3D preview, SolidWorks-connected real-machine modeling with live visualization, and a full agent kernel (multi-provider, MCP, plugins, hooks, skills, Cron, channels).

Experimental TypeScript plugin for STM/SPM control in DeepSeek Harness, with simulator workflows, persistent tool records, and reference-driven tests. In active development.

Self-hosted WhatsApp AI assistant on Hermes Agent — Baileys bridge, multi-tenant dashboard, Google Workspace tools

Run tool-calling LLM agents locally on Android devices using Termux and llama.cpp with complete data privacy and no external API reliance.

Claude Code-style auto-memory plugin for DeepSeek Harness (dsh): typed memory files + MEMORY.md index auto-injected into the system prompt. File-only, no external services.

Trading comps agent skill: peer screening, multiple alignment, quartile math in a tested script — the agent never does the arithmetic.

Vera — AI merchant growth assistant for magicpin's India AI Challenge. Composes grounded, context-aware WhatsApp messages for Indian merchants using trigger-kind routing, Hinglish language matching, and multi-turn conversation management.

Evidence-gated vulnerability research for AI security agents.

Easy-to-use, customizable, high-quality vulnerability management skills for AI agents.

Autonomous email processing & action system powered by multi-provider LLMs, Redis and Microsoft Graph API

AI coding orchestrator: markdown experts, scale-adaptive pipeline, atomic commits, TDD execution, expert-council review. Works with Claude Code and OpenCode.

AI-first personal OS: capture → execute → reflect. Todos, read-later, habits & reports in one calm, self-hosted workspace, with a resident agent + Claude/Codex skill. AI First 的个人操作系统：收集（Inbox）→ 执行（Todos）→ 复盘（Reports），单用户自托管。

🪶 Quill — Open-source AI super-agent framework with sandboxed execution, sub-agent orchestration, MCP, skills marketplace, session forking, FTS5 search, and a Tauri desktop app. Alternative to OpenAI Codex, Cursor, and Claude Code.

A real GTO solver, packaged as an LLM agent skill. Heads-up NLHE CFR+ with precomputed flop/turn tables and on-demand subgame solvers, accessed through a single `poker` CLI.

An AI strategy consultant (Claude Code agent) that interviews you instead of answering — structured, hypothesis-driven problem solving compiled into a working agent.

step-labeled benchmark of injection-hijacked LLM agent trajectories (12,536 trajectories, 71,024 labeled steps)

Offline-first multi-agent LLM diagnostic assistant for air-gapped satellite NOCs — LangGraph 8-node agent pipeline + local Qwen2.5 + RAG, with a self-critic anti-hallucination guardrail.

AI agent for image and creative production — image generation, thumbnails, and on-brand visual content, powered by muapi.ai.

A live research world where autonomous AI agents challenge, reproduce and audit each other's work. Agents run on their owners' machines; keys never leave. Open protocol, auditable knowledge genealogy, TEST-only economy.

High-performance, deadlock-immune Pure Go multi-agent swarm engine for Antigravity Telegram Bots. Features 1200ms streaming throttler, Inactivity Turn Watchdog, Buffer Salvage, and 429 Cold Safe Parking.

A backend service that allows uploading documents and querying them in natural language. The LLM responds based exclusively on the uploaded documents, citing the exact sources. It uses a RAG pipeline with ChromaDB as the vector database and Groq as the free LLM.

Two isolated LLM reviewers, bounded adversarial debate, preserved dissent.

Autonomous Multi-Agent Software Factory governed by Finite State Machines (FSM), deterministic verification gates, execution budgets, and Git worktree isolation.

A negotiation environment where the agent picks its counterparty and meets it again. Verifiable reward with no judge model, an optimum you can compute exactly — and every model tested loses to a twenty-line rule.

Code and data for a pre-registered audit of LLM-judged helpfulness, answer leakage, and student independence across tutor models. arXiv:2607.28128

Full-stack multi-agent studio for custom character agents, streamed group conversations, tool permissions, and persistent run history.

Harness-agnostic distillation of the guided Aegis Method: skills and guidance only, no engine, no enforcement

YieldPoint

Run local LLMs on limited VRAM safely. Dynamic model sharing and OpenAI API drop-in replacement.

Secure, reproducible KVM lab for agent-driven ML research: per-user VMs with driver / trusted / hostile zone isolation, plus five standalone scientific-state MCP servers

Agentic AI inside Autodesk Revit. Claude autonomously calls 9 typed C# tools to answer natural-language questions about live BIM data — deterministic counts, no hallucination.

Grounded finance agent over SEC filings: hybrid retrieval with cross-encoder reranking, XBRL facts instead of arithmetic over prose, and a fail-closed citation validator outside the agent loop.

Repository-native governance and support layer for software built with AI coding agents (Claude, Codex, Gemini, and other repository-aware agents).

An AI agent for answer/generative-engine optimization (AEO/GEO) — getting a brand cited by ChatGPT, Perplexity, Gemini, and Claude. Part of Agency Agents OS.

Universal multi-IDE agent teamwork skills: one team-orchestrator skill + per-tool role configs for 12 coding tools (Claude, Codex, Copilot, Cursor, Windsurf, Trae, Qoder, Antigravity…)

Model-agnostic runtime for structured AI organizations - hierarchical multi-agent systems with a CEO, executives, managers, and workers, each with defined authority, permissions, memory, and reasoning budgets. Quota-aware routing across local and frontier models. You talk to the CEO; the organization does the rest.

Behavioral biometric detection of AI web agents — distinguishing humans from scripted bots, LLM-driven agents, and custom autonomous agents using mouse, keystroke, and interaction-timing signals. Live testbed at charweb.net.