Back to Categories

Coding & Assistance shortlist

AI Code Generation & Completion

Code generation, completion, and dev assistance

Tool List

114 tools
GitHub Copilot

GitHub Copilot

GitHub Copilot works alongside you directly in your editor, suggesting whole lines or entire functions for you

Cursor

Cursor

Built to make you extraordinarily productive, Cursor is the best way to build software with AI

Claude Code

Claude Code

Anthropic AI coding assistant for terminal, IDE, web, and cloud development workflows

Conan

Conan

Native macOS live HUD and session cockpit for Claude Code

Kiro

Kiro

Spec-driven AI IDE that turns prompts into requirements, designs, tasks, and working code

Windsurf

Windsurf

AI-native IDE with Cascade agents, code completion, MCP support, and local/cloud development workflows

Codeium

Codeium

AI code completion, chat, and search assistant in the Windsurf ecosystem

Continue

Continue

Continue is an open-source AI code assistant for VS Code and JetBrains with model choice, context retrieval, and configurable workflows

Cline

Cline

Cline is an open-source VS Code AI coding agent that can plan tasks, edit files, and run terminal commands with user approval

MoDev

MoDev

Mobile development environment that brings Claude, GitHub, Vercel, and Supabase to the phone

Vox

Vox

Voice-in, voice-out extension for talking with GitHub Copilot CLI

Aider

Aider

Open-source terminal AI pair programmer that directly edits code in local Git repositories

BobCA

BobCA

AI workspace for building and iterating web applications

Krater AI

Krater AI

All-in-one AI platform for chat, writing, images, code, and productivity tasks

Augment Code

Augment Code

Augment Code is a developer AI platform with deep codebase context that helps engineering teams ship faster

Tabnine

Tabnine

Tabnine is the AI code assistant that accelerates and simplifies software development while keeping your code private, secure, and compliant

Invoke

Invoke

Invoke is a professional AI coding agent powered by Claude with subagent workflows, code generation, and automated development execution

Kilo

Kilo

Build, ship, and iterate faster with Kilo, the popular open-source AI coding agent with local-first workflows and 500+ model support

Cosine

Cosine

Cosine is an agentic AI software engineer for end-to-end coding tasks across CLI, editor, and cloud workflows

Ovren

Ovren

Hire AI frontend and backend developers that understand your codebase and deliver production-ready updates

Fixa

Fixa

Fixa helps you build real software from idea to production with the best agent on the web. Full-stack apps, APIs, workflows, and more

v0

v0

Your collaborative AI assistant to design, iterate, and scale full-stack applications for the web

Replit AI

Replit AI

Build and deploy software collaboratively with the power of AI without spending a second on setup

Jitera

Jitera

AI-powered software development agent for accelerating app delivery from requirements to code

Solarch

Solarch

AI diagram-to-code platform that keeps backend architecture and boilerplate in sync

Kimi K2.7 Code

Kimi K2.7 Code

Moonshot AI coding-focused agentic model on Hugging Face for long-horizon software engineering tasks

jebi

jebi

Mac terminal with built-in local AI for next-command suggestions, error explanations, and terminal-native chat

Mycelis

Mycelis

Serverless AI workspace with OpenAI-compatible gateway, smart routing, semantic cache, RAG, and MCP agents

Polygram

Polygram

AI-native design and coding app that plans products, designs screens, and turns them into mobile or web apps

sub2api

sub2api

Sub2API-CRS2 一站式开源中转服务,让 Claude、Openai 、Gemini、Antigravity 订阅统一接入,支持拼车共享,更高效分摊成本,原生工具无缝使用

aily-blockly

aily-blockly

AI IDE for hardware development, support Arduino, MicroPython, ESP32, STM32, RP2040, Nrf5x

orca

orca

Orca is the next-gen IDE for building with coding agents

mlx-audio-swift

mlx-audio-swift

A modular Swift SDK for audio processing with MLX on Apple Silicon

Lumina-Note

Lumina-Note

Lumina Note - A modern Markdown note-taking app with live preview, bidirectional links, and AI assistant

DeepScientist

DeepScientist

Now, Stronger AI Pushes Frontiers, Stronger Our Shared Future

mcp-gateway-registry

mcp-gateway-registry

Enterprise-ready MCP Gateway & Registry that centralizes AI development tools with secure OAuth authentication, dynamic tool discovery, and unified access for both autonomous AI agents and AI coding assistants. Transform scattered MCP server chaos into governed, auditable tool access with Keycloak/Entra integration

ForgeCAD

ForgeCAD

Code-first parametric CAD and engineering design automation tool for JavaScript/TypeScript with live parameters, constraints, assemblies, and STEP/BREP export

openrelay

openrelay

几百个免费 AI 模型配额,一键接入本地项目。| Hundreds of free AI model quotas, one-click access to local projects

models.dev

models.dev

An open-source database of AI models

vscode-gitlens

vscode-gitlens

Supercharge Git inside VS Code and unlock untapped knowledge within each repository — Visualize code authorship at a glance via Git blame annotations and CodeLens, seamlessly navigate and explore Git repositories, gain valuable insights via rich visualizations and powerful comparison commands, and so much more

DeepSeek-TUI

DeepSeek-TUI

Coding agent for DeepSeek models that runs in your terminal

dev3000

dev3000

Captures your web app's complete development timeline - server logs, browser events, console messages, network requests, and automatic screenshots - in a unified, timestamped feed for AI debugging

semiotic

semiotic

React data visualization library for streaming, networks, and AI-assisted development

storageless

storageless

:mailbox_with_mail: storage-less PSR-7 session support

agentic-flow

agentic-flow

Easily switch between alternative low-cost AI models in Claude Code/Agent SDK. For those comfortable using Claude agents and commands, it lets you take what you've created and deploy fully hosted agents for real business purposes. Use Claude Code to get the agent working, then deploy it in your favorite cloud

phantom

phantom

An AI co-worker with its own computer. Self-evolving, persistent memory, MCP server, secure credential collection, email identity. Built on the Claude Agent SDK

MirageKit

MirageKit

Peer to Peer screen sharing framework from macOS to iPadOS, visionOS, and macOS

mcp_agent_mail

mcp_agent_mail

Asynchronous coordination layer for AI coding agents: identities, inboxes, searchable threads, and advisory file leases over FastMCP + Git + SQLite

MiniGPT-4-ZH

MiniGPT-4-ZH

MiniGPT-4 中文部署翻译 完善部署细节

omlx

omlx

LLM inference server with continuous batching & SSD caching for Apple Silicon — managed from the macOS menu bar

nixtla

nixtla

TimeGPT-1: production ready pre-trained Time Series Foundation Model for forecasting and anomaly detection. Generative pretrained transformer for time series trained on over 100B data points. It's capable of accurately predicting various domains such as retail, electricity, finance, and IoT with just a few lines of code 🚀

vllm

vllm

A high-throughput and memory-efficient inference and serving engine for LLMs

monorepo

monorepo

Commonware Library Primitives and Examples

Model-Optimizer

Model-Optimizer

A unified library of SOTA model optimization techniques like quantization, pruning, distillation, speculative decoding, etc. It compresses deep learning models for downstream deployment frameworks like TensorRT-LLM, TensorRT, vLLM, etc. to optimize inference speed

OpenOmniBot

OpenOmniBot

你的端侧 AI 助手,她可以操作终端,也可以完成 Android 世界的广泛任务 || Your on-device AI assistant, capable of operating terminals and performing a wide range of tasks in the Android world

forgecode

forgecode

AI enabled pair programmer for Claude, GPT, O Series, Grok, Deepseek, Gemini and 300+ models

aigcpanel

aigcpanel

AIGCPanel 是一个简单易用的一站式 AI 数字人系统,支持视频合成、声音合成、声音克隆,简化本地模型管理、一键导入和使用 AI 模型

open-design

open-design

🎨 Local-first, open-source alternative to Anthropic's Claude Design. ⚡ 19 Skills · ✨ 71 brand-grade Design Systems 🖼 Generate web · desktop · mobile prototypes · slides · images · videos · HyperFrames 📦 Sandboxed preview · HTML/PDF/PPTX/MP4 export 🤖 Runs on Claude Code / Codex / Cursor / Gemini / OpenCode / Qwen / Copilot / Hermes / Kimi CLI

codebuff

codebuff

Generate code from the terminal!

NanoResearch

NanoResearch

🦞+🔬: NanoResearch: The Autonomous AI Research Assistant

wiseflow

wiseflow

为你 7*24 在线搞钱的“云上牛马”团队

posthog

posthog

🦔 PostHog is an all-in-one developer platform for building successful products. We offer product analytics, web analytics, session replay, error tracking, feature flags, experimentation, surveys, data warehouse, a CDP, and an AI product assistant to help debug your code, ship features faster, and keep all your usage and customer data in one stack

erigon

erigon

Ethereum implementation on the efficiency frontier

NotionNext

NotionNext

使用 NextJS + Notion API 实现的,支持多种部署方案的静态博客,无需服务器、零门槛搭建网站,为 Notion 和所有创作者设计。 (A static blog built with NextJS and Notion API, supporting multiple deployment options. No server required, zero threshold to set up a website. Designed for Notion and all creators.)

agent-rules-books

agent-rules-books

AGENTS.md rules / skills for AI coding agents: Codex, Cursor & Claude Code. Inspired by Clean Code, Refactoring, DDD, Clean Architecture and DDIA programming books

9router

9router

Unlimited FREE AI coding. Connect Claude Code, Codex, Cursor, Cline, Copilot, Antigravity to FREE Claude/GPT/Gemini via 40+ providers. Auto-fallback, RTK -40% tokens, never hit limits

piclaw

piclaw

I'm going to build my own OpenClaw, with blackjack... and bun!

register

register

Grab your own sweet-looking '.is-a.dev' subdomain

openless

openless

Hold a key, speak, release — AI-polished text appears at your cursor in any app. Open-source voice input for macOS & Windows. (按住快捷键说话,松开即得润色后的文字)

azure-dev

azure-dev

A developer CLI for working with Azure resources to build and deploy AI applications. Commands map to key workflow stages: code, build, deploy, and monitor

finance-skills

finance-skills

A collection of skills for AI financial analysis and trading

emdash

emdash

Emdash is the Open-Source Agentic Development Environment (🧡 YC W26). Run multiple coding agents in parallel. Use any provider

relay-pulse

relay-pulse

Availability monitoring system for LLM relay services with real-time status dashboards

VTCode

VTCode

Open-source coding agent with code understanding and robust shell safety. Supports multiple LLM providers with automatic failover and efficient context management

nango

nango

Build product integrations with AI

easy-vibe

easy-vibe

💻 vibe coding 2026 | Your first modern Coding course for beginners to master step by step

litellm

litellm

Python SDK, Proxy Server (AI Gateway) to call 100+ LLM APIs in OpenAI (or native) format, with cost tracking, guardrails, loadbalancing and logging. [Bedrock, Azure, OpenAI, VertexAI, Cohere, Anthropic, Sagemaker, HuggingFace, VLLM, NVIDIA NIM]

obsidian-copilot

obsidian-copilot

THE Copilot in Obsidian

arkon

arkon

Arkon gives organizations centralized control over how employees use any Ai Client. Admins manage resources, access policies, and workspace contexts from a single portal. Employees connect once via the Model Context Protocol (MCP) and get the right context automatically

epicenter

epicenter

Open-source, local-first apps

metamask-mobile

metamask-mobile

Mobile web browser providing access to websites that use the Ethereum blockchain

magic-context

magic-context

Magic Context cache-aware infinite context, cross-session memory, and background history compression

vite-plus

vite-plus

Vite+ is the unified toolchain and entry point for web development. It manages your runtime, package manager, and frontend toolchain in one place

NotionNext

NotionNext

使用 NextJS + Notion API 实现的,支持多种部署方案的静态博客,无需服务器、零门槛搭建网站,为 Notion 和所有创作者设计。 (A static blog built with NextJS and Notion API, supporting multiple deployment options. No server required, zero threshold to set up a website. Designed for Notion and all creators.)

wuphf

wuphf

WUPHF is a collaborative office of AI employees who build and maintain their own knowledge base to never lose context for the tasks you give them. Supports Claude Code, Codex, OpenClaw and local LLMs via OpenCode

supermemory

supermemory

Memory engine and app that is extremely fast, scalable. The Memory API for the AI era

aiox-core

aiox-core

Synkra AIOS: AI-Orchestrated System for Full Stack Development - Core Framework v4.0

fallow

fallow

Codebase intelligence for TypeScript and JavaScript. Free static layer: unused code, duplication, circular deps, complexity hotspots, architecture boundaries. Optional paid runtime layer: hot-path review and cold-path deletion evidence from real production traffic. Rust-native, sub-second, 90 framework plugins

Rapid-MLX

Rapid-MLX

The fastest local AI engine for Apple Silicon. 4.2x faster than Ollama, 0.08s cached TTFT, 100% tool calling. 17 tool parsers, prompt cache, reasoning separation, cloud routing. Drop-in OpenAI replacement. Works with Claude Code, Cursor, Aider

Megatron-Bridge

Megatron-Bridge

Training library for Megatron-based models with bidirectional Hugging Face conversion capability

big-AGI

big-AGI

AI suite powered by state-of-the-art models and providing advanced AI/AGI functions. Includes AI personas, AGI functions, world-class Beam multi-model chats, text-to-image, voice, response streaming, code highlighting and execution, PDF import, presets for developers, much more. Deploy on-prem or in the cloud

chrome-devtools-mcp

chrome-devtools-mcp

Chrome DevTools for coding agents

llm-agents.nix

llm-agents.nix

Nix packages for AI coding agents and development tools. Automatically updated daily

claude-code-rust

claude-code-rust

🚀 Rust 全量重构的 Claude Code - 性能提升 2.5x,体积减少 97% | High-performance Rust implementation of Claude Code with 2.5x faster startup and 97% smaller binary

tambo

tambo

Generative UI SDK for React

lanhu-mcp

lanhu-mcp

⚡ 需求分析效率提升 200%!全球首个为 AI 编程时代设计的团队协作 MCP 服务器,自动分析需求自动编写前后端代码,下载切图

spec-kitty

spec-kitty

Spec-Driven Development for serious software developers. Spec Coding with with Claude, Cursor, Gemini, Codex. Kanban dashboard, git worktrees, auto-merge and more

conduit

conduit

Mobile (iOS/Android) client for OpenWebUI. Chat with your self‑hosted AI

pdd

pdd

Prompt Driven Development Command Line Interface

page-assist

page-assist

Use your locally running AI models to assist you in your web browsing

OmniRoute

OmniRoute

Never stop coding. Free AI gateway: one endpoint, 160+ providers (50+ free), connect Claude Code, Codex, Cursor, Cline & Copilot to FREE Claude/GPT/Gemini. RTK+Caveman stacked compression saves 15-95% tokens, smart auto-fallback, MCP/A2A, multimodal APIs, Desktop/PWA

AutoGPT

AutoGPT

AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters

kvcached

kvcached

Virtualized Elastic KV Cache for Dynamic GPU Sharing and Beyond

verl

verl

verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework

maggy

maggy

What started as an opinionated Claude Code setup kit is now an autonomous AI engineering command center

CodeWhale

CodeWhale

Agentic coding terminal. DeepSeek-first, multi-provider, cache-maximal, whale-themed. Five-locale UI, CN-region endpoint, CNB mirror

llama.vscode

llama.vscode

VS Code extension for LLM-assisted code/text completion

smallcode

smallcode

AI coding agent optimized for small LLMs. 87% benchmark with 4B-active model

GitNexus

GitNexus

GitNexus: The Zero-Server Code Intelligence Engine - GitNexus is a client-side knowledge graph creator that runs entirely in your browser. Drop in a GitHub repo or ZIP file, and get an interactive knowledge graph wit a built in Graph RAG Agent. Perfect for code exploration

vllm-studio

vllm-studio

Control panel for VLLM, Sglang, llama.cpp, exllamav3

Chat2API

Chat2API

Chat2API enables zero-cost access to leading AI models by leveraging official web UIs. It supports providers such as DeepSeek, GLM, Kimi, MiniMax, Qwen, and Z.ai, and seamlessly integrates with tools like openlcaw, Cline, and Roo-Code

llama.cpp

llama.cpp

LLM inference in C/C++

fastllm

fastllm

fastllm 是后端无依赖的高性能大模型推理库。同时支持张量并行推理稠密模型和混合模式推理 MOE 模型,任意 10G 以上显卡即可推理满血 DeepSeek。双路 9004/9005 服务器+单显卡部署 DeepSeek 满血满精度原版模型,单并发 20tps;INT4 量化模型单并发 30tps,多并发可达 60+

uzu

uzu

A high-performance inference engine for AI models

Related guides

Related categories