Code agents

Universal AI writing skill — tech articles, marketing copy, research reports, Xiaohongshu notes, technical docs. Research-driven, full-pipeline, anti-AI-slop. Bilingual (EN/ZH).

Memory backbone for AI agents. Four-tier store — working, episodic, semantic, procedural — with decay, consolidation, and association graphs. Fused semantic + SIMD-accelerated hybrid recall, in-process MCP, REST/gRPC, and language SDKs.

Agent skills for working with Zapier, maintained by Zapier teams. Indexed by skills.sh.

Mission control for a fleet of AI coding agents (Claude Code, Codex, Antigravity, OpenCode, Cursor, Aider) across many repos — desktop app + Rust TUI, tmux-backed, with durable fleet mail and policy-based agent supervision.

A curated list of papers, benchmarks, project pages, and code for proactive agents.

transformers safetensors mistral text-generation openchat C-RLFT

gguf imatrix conversational qwen3_next ik_llama.cpp text-generation

transformers pytorch codegen text-generation arxiv:2203.13474 license:bsd-3-clause

mlx safetensors gemma4_assistant speculative-decoding mtp gemma

transformers safetensors olmo3 text-generation conversational en

mlx safetensors gguf qwen2 n8n workflow

transformers pytorch llama text-generation code math

Agentic code review with structural graph intelligence — PR gate + branch stewardship. Self-hosted. Apache-2.0.

Local AI coding-agent history + API cost analytics (loopback-only).

AI-powered autonomous trading agents for Polymarket prediction markets. This framework enables developers to build sophisticated trading bots using state-of-the-art LLMs, RAG (Retrieval-Augmented Generation), and superforecasting methodologies. Built with Python 3.12+, LangChain, FastAPI, and modern development tooling.

Turn Claude Code into an assistant with persistent memory: one interview-driven prompt builds your context files, rules and decision log, and every session starts already knowing you.

Evidence-grounded AI agent for Java code repair with LLM-guided patches and human-in-the-loop review.

한국 취업 자기소개서를 기업조사→초안→글자수→리뷰→윤문→검증 8단계로 완성하는 Claude Code 플러그인

Terminal discovery hub and package manager for AI coding tools, MCP servers, and agent skills. Built with Python & Textual

Give Claude a checklist before bed. It can't clock out until every box is ticked, never stalls on a question, and revives itself if the API dies at 3 AM.

Your AI development team — 27+ agents and 21 skills that build, review, debug, and ship production code. Works with Claude Code, Cursor, VS Code, Windsurf, Codex, and OpenCode. 7 framework packs: Vue, React, Next.js, SvelteKit, Angular, Astro, Nuxt.

Describe an app, watch it run. Multi-model code generation into live E2B sandboxes — Next.js, Vue, Streamlit and Gradio templates.

A local dev tool where your agents are weird alien dogs. Would you let them in?

Graph-native studio, runtime integration, and self-hosted observability for mutable multi-agent LLM workflows.

Claude Code Growth Operating System (OS): Sales, Marketing, Product and Retention as one Revenue system

ClawSouls — an open-spec platform for shareable AI agent personas (souls). 80+ curated souls, one-command install, works with any SOUL.md-compatible agent (OpenClaw, Claude Code, Cursor & more). Apache-2.0.

Guardrails for AI coding agents — block catastrophic tool calls before they run. Semantic, agent-neutral, near-zero false positives.

Transparent Codex wrapper and account-rotation proxy

Market intelligence toolkit for Claude Code. Iterative research workflows, trend modeling with three-valued logic, multi-format reports, and automated GitHub issue creation from findings.

Production-grade Agent Skill for TypeScript, React & Next.js — decision guides, hard rules, and debugging playbooks for AI coding agents (Claude Code, Cursor, Codex)

Let AI agents use agent-browser, Browser Use, or Playwright CLI in the Chrome or Edge you already use.

Skill RSI is a recursive self-improvement loop for Agent Skills, grounded in evals. Standalone or Codex plugin.

Stop opening /usage — a Claude Code status line that does the weekly-limit math: today's share, sustainable burn rate, sleep-aware pacing. Pure bash + jq.

Cross-platform Rust daemon that prevents disk-full incidents for AI coding workloads using predictive pressure control, safe artifact cleanup, and multi-volume ballast pools.

Your SvelteKit app's code health, checked before it ships. Statically, no browser — SEO, Performance, Correctness, Security, Architecture, Accessibility.

LLM agents that write machine-checked cryptographic proofs in EasyCrypt (arXiv:2607.02847)

Native macOS menu bar app for managing usage, sessions and remotely controlling your AI Agents.

探客AI ai-tungke 外贸智能获客平台：基于 Google 地图 + 高德地图的深度数据挖掘系统，遍历式地点检索 × AI 联网搜索 × 行业数据综合评估，让外贸 B2B 获客 lead generation 更精准高效

Personal knowledge vault plugin for Claude Code — session recording, memory distillation, and hybrid semantic + BM25 retrieval.

rust-in-peace — agentic security review for Rust: autonomous find/triage/patch for unsafe/FFI memory bugs, panic-DoS, and deserialization-trust flaws (Miri / sanitizer / panic / hang detectors). A Rust-security fork of anthropics/defending-code-reference-harness.

OpenCurro AI Agent is a fast, lightweight, and autonomous general-purpose AI agent.

Local-first desktop command center for Claude Code, Codex, OpenCode, and other coding agents—parallel tasks, worktrees, dev services, port forwards, diffs, and review.

Policy-aware field mission orchestration agent with bounded planning, auditable replanning, travel and expense constraints.

Local Windows desktop monitor for your running Claude Code agents - live status, estimated cost, model, host and one-click focus, grouped by project. Read-only and fully offline.

Canonical memory infrastructure: BM25 recall over trusted files for AI agents.

Local-first repo maps for coding agents—ranked files, test routes, risks, CLI/MCP/GitHub Action, and public GitHub URLs.

An agentic software factory that closes the loop

A local-first knowledge management tool that connects concepts and let an LLM safely maintain a plain-Markdown vault you can read, audit, and edit yourself.

Remote jobs MCP server — search 100,000+ remote jobs, post listings, find candidates, and check salary benchmarks from Claude, ChatGPT, Cursor, and any MCP client. Free, no API key required.

A curated GPT-Image-2 prompt library with preview images and copy-ready prompts. OpenAI image generation. Free & open source.

AI assistant with persistent memory for Home Assistant. Voice & text via Assist, plain-language automations with confirm-first previews, one-click add-on install. Cloud or bring your own key.

Claude Code 非官方开源桌面客户端——接入 SDK 控制协议，权限卡片审批、多模型切换、多 Tab 会话、视频分析（Tauri 2 + React）

Offline-first AI memory for coding — 29 MCP tools, temporal knowledge graph, and local vector search. No API keys, no cloud, no server.

A native macOS terminal for running AI coding agents in parallel — built on real libghostty, with persistent tmux-style sessions and a scriptable Lua/CLI control plane.

Agent skills from StarSling

File explorer plugin for DeepSeek Harness: file tree, preview, markdown, syntax highlighting, in-panel editing, VS Code integration - DeepSeek Harness 全局文件资源管理器插件

基于“躺着学”长期雅思教研与学员服务实践整理的 IELTS Agent Skills，覆盖学习计划、作文批改、口语陪练、阅读与听力复盘、词汇和模考复盘，支持 Codex、Claude Code、Cursor、WorkBuddy 等本地 Agent。

A safety gate for DeepSeek Harness: a stronger model reviews dangerous tool calls before they run. Plus vision and BlockRun's full model catalog from one wallet, paid per request over x402.

Agentic coding in the terminal: the model writes its own multi-agent workflows (Gigacode). Provider-agnostic, local-first, 15+ model providers, MCP support.

Local OpenAI-compatible proxy that exposes opencode's free Zen models (deepseek-v4-flash-free, hy3-free, nemotron, ...) to any agent - Cline, Roo, Continue, Aider, mimo. No accounts, no keys, one command.

Open-source repository standard, starter template, validator, and multi-agent workflow for making vibe-coded and AI-generated software understandable, testable, reviewable, and maintainable. Codex-first reference implementation.

gguf qwen3_5_moe_text qwen3 moe a3b mtp

28 OSINT Agent Skills that turn Cursor, Claude & AI coding agents into a full open-source intelligence platform — reconnaissance, attribution, GEOINT, breach checks & due diligence. Ethical, sourced, passive-first.

Spec-driven development plugin for Claude Code. SpecManager gives you an agile AI team that takes a feature from interview → PRD → Architecture → Design → Plan → Build → Walkthrough.

Compare UI, copy, and states in your app with your coding agent.

Behavior sharing for AI agents in teams — the topos CLI + self-hostable plane keep every agent's skills current

The AI agent-native systems programming language: Meaning in. Verified machine code out. All target OS, memory managed through Ownership & fully interoperable with existing ecosystems & object-oriented AI Agents with payment capability.

Connect a coding agent (Claude Code, Codex, Antigravity) to Telegram. Dependency-free, robust, secure.

Your AI coding harness, ported to every client you use. Capture Claude Code (or Codex) rules, hooks, skills, subagents, commands and MCP servers once; apply them identically to Codex, Gemini CLI, Cursor and 16 more. Zero-dependency Node.

🐢⚡ Smart API key rotation for Agent Zero. Paste several keys: KAME picks the healthiest one per call, reads every 429 / RESOURCE_EXHAUSTED / quota error, rests each key exactly as long as needed and never lets a rate limit end your run. Gemini, OpenAI, OpenRouter, Anthropic, any provider.

Run Claude Code (or another coding agent) unattended, inside a disposable microVM, with its work committed to git so you can review everything from your host.

The review app for code your agent writes. Native Rust/GPUI desktop app with real Git workflows.

AI-powered log diagnostics engine that analyzes server logs, stack traces, and infrastructure failures to identify root causes and recommend fixes.

Blue: a TUI is not a package, it is a Cordis plugin tree — a modern terminal UI for DeepSeek Harness with hot-swappable render, interaction, and command plugins.

Score any OpenAPI document for AI-readiness. Command-line tool, GitHub Action and agent skills that implement the open JAIRF scoring framework, with HTML reports and OpenAPI Overlay output.

Maintain the same context between AI chats, models, and coding agents. Stop re-explaining your project every time you switch AI tools.

AI agent plugins & managed-agent templates for China A-share market research and financial modeling, powered by Tushare. Research workflows and valuation tools for professional analyst review—not investment advice. | 面向中国 A 股市场的 AI 智能体插件与管理代理模板，基于 Tushare 数据驱动，提供行业研究与财务建模工具链。所有输出仅供专业分析师审阅参考，不构成任何投资建议。

Vulnerability scanning with your own scanners and threat feeds, plus a coding agent that opens the fix PR. CLI, GitHub Action, or scheduled Managed Agents deployment.

Self-hosted AI customer service. Your documents, your database, your data - answered with citations across every channel.

Portal - public MCP endpoint

Git-free file snapshots and rewind — put a directory back the way it was, without a repository and without touching your version control.

This repository is a comprehensive, hands on roadmap to Python Mastery and AI Engineering. It is designed to take a learner from the very foundations of programming to building professional grade AI agents and scalable systems...

IFRS accounting knowledge skill for AI coding agents — Claude Code, Codex, Cursor. Every IFRS and IAS standard, paragraph-cited: IFRS 15 revenue recognition, IFRS 16 lease accounting, IFRS 9 ECL, IFRS 17, and IFRS 18, IFRS 19, IFRS S1/S2. Disclosure checklists, worked journal entries, GAAP-to-IFRS transition guide.

Open-Source-Boilerplate für PersonalOS: Markdown-basierte Systemlogik, Templates und lokale Prüfungen für Menschen und KI-Agenten.

中文 AI 文本去痕迹 + Claude 水印检查 — 六段式改写；零宽字符、同形字清干净，SynthID 采样水印只量残留、不声称能删。纯 Python 本地跑，零 LLM 零 API Key。Chinese AI-text humanizer & Claude / SynthID watermark inspector, fully offline, zero-dependency.

A universal AI writing skill that turns generic drafts into specific, truthful, voice-consistent prose.

An architectural audit where a finding is admissible only once its cost is measured from git history. A doctrine for coding agents plus a stdlib-only measurement CLI.

A curated, taxonomy-driven collection of influential papers and benchmarks in AI for cybersecurity.

Six skills tell coding agents how to work. Two guards enforce the parts that should not depend on judgment.

Citation-ready YouTube research for AI agents — transcript search, exact timestamp links, cross-video evidence, and channel intelligence over MCP

Make it easy to automate personal desktop tasks

Touhou-inspired Agent Skills: distinct, testable, composable problem-solving workflows.

Automate on-chain events and actions reliably and securely. Build Workflows in minutes without the need for infrastructure, code or wallet management. Get instant alerts and never miss what matters.

Drive your Mac focus-free over MCP: OS APIs, AppleScript, CDP, and Accessibility

Research Agent for the Open Web

2 text files and a folder. The ICM Folder System I run several businesses on, in plain English, for people who do not write code.

2Captcha MCP server for AI agents with web search, web scraping, browser automation, captcha solving, and scalable web data collection.

在網路受限的 Docker Dev Container 裡安全執行 Claude Code，透過 iptables/ipset 防火牆白名單限制 AI Agent 的對外連線，降低資料外洩與誤操作風險。改自 Anthropic 官方 .devcontainer 參考實作。

Mac daemon for multi-agent iOS simulator fleet orchestration: leases, warm pools, deterministic state, and a run journal.