awesome-ai-coding-tools

Code Editors and Assistants

• Cursor – AI-first code editor with advanced autocompletion, codebase-aware chat, and multi-file editing.
• Windsurf – AI code editor with Cascade, a deep contextual coding agent that goes beyond autocompletion.
• GitHub Copilot – AI pair programmer integrated across VS Code, JetBrains, and GitHub with chat, code completion, and workspace agents.
• Zed – High-performance multiplayer code editor built in Rust with integrated AI assistance.
• Cody (Sourcegraph) – AI assistant for code understanding, navigation, and generation across entire codebases.
• Claude Desktop – Anthropic's desktop app for development tasks, code analysis, and programming assistance.
• Trae – Adaptive AI IDE by ByteDance for faster coding and AI collaboration.
• Aider – Terminal-based AI pair programming tool for editing code in local git repos.
• Phind – AI search and coding assistant for instant answers and code solutions.
• Google Antigravity - Review – Google's agent-first IDE with multi-agent orchestration, browser automation, and Gemini 3 Pro integration. Free during preview.
• Kiro – Spec-driven AI development environment by AWS.
• Tabby – Self-hosted, open-source AI coding assistant you can run on your own infrastructure.
• Continue – Open-source AI tool for code completion and chat, pluggable into VS Code and JetBrains.
• Supermaven – Extremely fast AI code completion with low-latency, large-context responses.
• PearAI – Open-source AI-powered code editor.
• Jupyter AI – AI extensions for Jupyter notebooks with natural language code generation.
• Blackbox AI – AI coding assistant with code completions, chat, and search.
• StackSpot AI – Enterprise-focused AI platform for code generation and developer efficiency.
• Magic – AI software engineer platform that handles complex development tasks autonomously.
• Augment Code – AI coding platform with deep cross-repo codebase understanding via its Context Engine, built for large enterprise codebases.
• Amp (Sourcegraph) – Agentic coding tool built on Sourcegraph's code search infrastructure with deep codebase graph and unconstrained token usage.
• Kilo Code – Open-source VS Code extension supporting 500+ models at zero API markup, a superset of Cline/Roo Code.
• Roo Code – Popular open-source VS Code extension (fork of Cline) with multi-model support and autonomous coding modes.
• Qoder – Agentic coding platform focused on deeper reasoning.
• Aide – Open-source AI-native IDE with proactive agents, built on top of VS Code.
• Coworker – Local-first AI coding assistant desktop app with MCP integration, multi-provider AI support, and skills marketplace. Built with Electron, React, and LangGraph. MIT licensed.
• Cate – Infinite zoomable canvas IDE where editor, terminal, browser, and Claude Code agent panels float spatially, like Figma or Miro but for coding.
• BBARIT – Free native all-in-one AI coding IDE (Tauri/Rust) with multi-agent terminals, office editing, and an embedded agent-driven browser; bring any model or run locally with Ollama.
• Bodega One Code – Free, local-first AI IDE with a built-in coding agent, bring-your-own-LLM, and full offline/air-gap support.
• Harness Desktop – Open-source Windows client for the official DeepSeek Harness Web UI, with a Simplified Chinese installer, portable build, verified updates, and persistent themes.

Code Completion

• GitHub Copilot – Industry-standard AI code completion across IDEs.
• Codeium – Free AI code completion for 70+ languages and 40+ IDEs.
• Tabnine – AI code completion with personalized suggestions and privacy-first options.
• JetBrains AI – Integrated AI for code completion and analysis in all JetBrains IDEs.
• Amazon Q Developer – AI assistant for code completion, debugging, and AWS integration.
• Google Code Assist (Gemini) – AI coding assistant for Google Cloud developers.
• Refact.ai – Open-source AI code completion and refactoring with self-hosting support.
• Continue – Open-source, pluggable AI code completion for VS Code and JetBrains.
• Visual Studio IntelliCode – Microsoft's AI code completion for Visual Studio.
• Amazon CodeWhisperer – Real-time AI code suggestions with security scanning. (Now part of Amazon Q Developer)
• CodeGeeX – Open-source multilingual code generation model.
• Supermaven – Ultra-fast completions with 1M token context window.

Coding Agents

• Claude Code – Anthropic's agentic coding tool for the terminal with deep codebase understanding.
• Devin AI – Autonomous AI software engineer that plans, codes, debugs, and deploys end-to-end.
• OpenHands (OpenDevin) – Open-source AI software engineer for autonomous development.
• Cline (Claude Dev) – VS Code extension with full file system access and autonomous coding.
• Replit Agent – Builds complete applications from natural language descriptions inside Replit.
• Aider – AI coding agent for collaborative editing and code generation via CLI.
• GPT Engineer – AI agent for building full applications from natural language.
• Codename Goose – Desktop and CLI agent by Block for automating tasks using LLMs and extensions.
• Smol Developer – Lightweight AI coding agent for rapid prototyping.
• JunieAI (JetBrains) – AI coding agent that plans, writes, tests, and refactors within JetBrains IDEs.
• Fine – AI dev agent that understands requirements, writes code, and iterates autonomously.
• Factory – AI platform automating repetitive coding tasks at scale.
• Devon – AI software engineer for autonomous coding.
• Rovo Dev (Atlassian) – Atlassian's terminal coding agent.
• Gemini CLI – Google's terminal coding agent powered by Gemini.
• OpenAI Codex CLI – OpenAI's CLI coding agent with cloud sandboxed execution.
• OpenCode – Open-source terminal AI agent (95K+ GitHub stars) supporting 75+ providers. Free, privacy-first, with LSP integration.
• Roo Code – Open-source VS Code agent (fork of Cline) known for reliable multi-file editing on large codebases.
• PraisonAI – Multi-agent framework with 100+ LLM support and MCP integration.
• Potpie – AI coding agent for streamlined development workflows.
• Pythagora – AI agent that builds apps through conversational interaction.
• Open Interpreter – Open-source agent that runs code locally in response to natural language, supporting Python, JS, shell, and more.
• SWE-agent – Princeton's autonomous agent that resolves real GitHub issues by navigating repos, editing files, and running tests.
• AutoGen – Microsoft's multi-agent framework for building AI agent teams that collaborate on coding tasks.
• CrewAI – Multi-agent orchestration platform for building teams of AI agents for development and automation.
• Copilot Workspace – GitHub's agent-powered dev environment that turns issues into code changes with plans, specs, and implementation.
• brood-box – Run coding agents (Claude Code, Codex, OpenCode) inside hardware-isolated microVMs with snapshot isolation, egress control, and MCP authorization.
• Wiggum CLI – Open-source agent that scans codebases, generates specs through AI interviews, and runs autonomous coding loops via Claude Code or Codex. Agent mode ships GitHub issues end-to-end.
• OpenASE – Open-source, ticket-driven software engineering platform that orchestrates Claude Code, Codex, and Gemini CLI agents across your machines with workflows, skills, and full traceability.
• SwarmClaw – Self-hosted multi-agent runtime with MCP client and server support, 23+ LLM providers, persistent memory, skills, schedules, and messaging connectors. Electron desktop app, CLI, and Docker.
• AgentsMesh – Self-hostable AI Agent Workforce Platform. Orchestrates Claude Code, Codex CLI, Gemini CLI, Aider, OpenCode across remote AI workstations (AgentPods) with PTY sandbox + git worktree isolation, channels-based multi-agent collaboration, built-in Kanban, and per-pod MCP server. Multi-Git (GitHub/GitLab/Gitee), multi-tenant, SSO/RBAC, BYOK.
• Codex Infinity – Autonomous coding agent that runs continuously on bare metal VPS. Run your Claude Max or OpenAI Codex plans with full root access and no cloud timeouts.
• Agent Shadow Brain – AI background code analysis agent that watches your codebase and provides real-time insights, suggestions, and automated reviews.
• OpenMagic – AI-powered coding toolbar for any web app. Injects a floating toolbar via reverse proxy, captures element context, previews diffs, and applies approved changes in real time.
• Emdash Skills – 14-category autonomous product-building OS with 18 specialized agents that turn one-line prompts into deployed products on Cloudflare Workers.
• Browy – Open-source AI agent for Chrome that drives real browser tabs through chat, with a built-in DevTools CLI terminal for power users. Powered by the GitHub Copilot SDK.
• cc-code – Open-source Rust terminal coding agent, Claude Code compatible. Runs DeepSeek, MiMo, GLM with ~50MB memory and 95-99% prompt cache hit rate.
• Coworker – Local-first AI coding agent desktop app with long-term memory, human-in-the-loop, web search, and 11-language i18n. MIT licensed, 396+ commits.
• Ivy Tendril – Open-source agentic software factory with an amazing UI that handles parallel Git worktrees for you, complete with programmatic verifications and fast review loops.
• Claude Skills – 14-category autonomous product-building OS bundling 18 specialized agents (architect, test-writer, deploy-verifier, security-reviewer, visual-qa, performance-profiler, accessibility-auditor, content-writer, completeness-checker, dependency-auditor, migration-agent, incident-responder, computer-use-operator, meta-orchestrator, seo-auditor, cost-estimator, changelog-generator, code-simplifier). One config drops into Claude Code, Codex, Cursor, Copilot, Gemini CLI, Windsurf, opencode, Cline, and Aider. One-line prompts deploy production sites with hard quality gates (Playwright at 6 breakpoints, axe-core 0 violations, Lighthouse a11y >=95, AI vision >=8/10).
• great_cto – Engineering management layer for 34 specialist AI agents covering the full SDLC (architect, pm, senior-dev, code-reviewer, qa, security, devops, l3-support + 18 archetype-specific reviewers). 25 archetypes auto-detected with compliance gates (PCI-DSS, HIPAA, FedRAMP, GDPR, EU AI Act). Multi-platform — Claude Code, Cursor, Codex CLI, Aider, Continue. Local kanban board, OWASP LLM Top 10 scanner, MIT.
• AgentTier – Self-hosted Kubernetes-native sandbox runtime for AI coding agents (Claude Code, OpenHands, LangGraph). Same Sandbox CRD provisions a Pod + PVC + default-deny NetworkPolicy with optional gVisor isolation, hierarchical governance, and a streaming SSE invoke API.
• Maestro – Open-source desktop command center for running multiple AI coding agents (Claude Code, Codex, Gemini CLI, etc.) in parallel, with Cue event automation, Auto Run playbooks, Group Chat across local and remote agents, and a maestro-cli that agents can drive themselves.
• DvalinCode – Provider-neutral, local-first CLI coding agent (Chat/Cowork/Code modes) built for governance: org policy engine, enforced network egress, and a verifiable hash-chained audit trail. Works with any OpenAI-compatible endpoint (DeepSeek, OpenAI, Claude via OpenRouter, Groq, Ollama). Zero runtime deps. MIT.
• OpenCode Mobile – Open-source (MIT) Android client for the OpenCode coding agent; run AI coding sessions from your phone against your own self-hosted server with bring-your-own keys.
• WithVibe – Self-hostable shared AI development environment for teams. Spin up an isolated, code-seeded env, build with AI, and share the live session; an agent gate (security, code review, tests, policy) plus human approval reviews every change before it ships.
• issue-orchestrator – Open-source orchestrator that runs Claude, Codex, and Gemini agents on GitHub issues in isolated worktrees, treating agent output as a claim, not authority: nothing advances until validation and a reviewer agent pass, with crash recovery and human merge authority.
• agentic-harness – Claude Code plugin that builds, reviews, and maintains a project's agentic harness — the agents, skills, and orchestrator under .claude/ — coordinating with existing spec systems and issue trackers instead of reinventing them.
• Gokin – Open-source terminal AI coding agent that works with local models via Ollama or providers like DeepSeek and Kimi, with no telemetry and secret redaction.
• LoopTroop – Local GUI orchestrator for long-running, high-correctness AI software delivery — LLM councils plan it, Ralph loops perfect it, OpenCode worktrees ship it.
• Weco (weco-cli) – Autoresearch CLI that optimizes code (GPU kernels, ML models, prompts) by editing a file, running your eval, and keeping changes only when the metric improves.
• Orca – An open-source IDE for orchestrating multiple AI coding agents — Claude Code, Codex, Cursor, Gemini, OpenCode and more — side-by-side, each in its own isolated git worktree.
• NarraNexus – Open-source AI agent team workspace with a ready-to-run team of agents that remember, collaborate, and use tools, supporting multi-agent coding workflows.
• octomux – Local dashboard for orchestrating parallel Claude Code and Cursor agents in isolated git worktrees, with a unified permission inbox, a live monitor grid, and in-app diff review. MIT.
• Aura IDE – Open-source desktop AI coding harness that plans, edits through reviewable diffs, validates changes, and leaves receipts.
• DevIntern – Picks up tickets from Jira, Linear, Trello, Asana, Azure DevOps, GitHub Issues, or markdown files and turns them into self-reviewed pull requests using the coding agent of your choice (Claude Code, Codex, Cursor, OpenCode), running on your machines with your own model keys. A feasibility gate flags vague tickets back to the tracker with questions.
• Septim Agents Pack – 10 named Claude Code sub-agents covering planning, architecture, brand, marketing, finance, design, legal, customer research, and cross-lane coordination. Drop the .claude/agents/ folder into any project; pay-once at $49.
• LingShu – Native Apache-2.0 macOS execution agent with a replaceable model backend and an open runtime for code, documents, presentations, and authorized computer actions.
• agentty – Native C++26 terminal coding agent and drop-in claude-code alternative. Single static binary, sub-millisecond cold start, sandboxed by default, and model-agnostic (Claude, OpenAI, Groq, OpenRouter, Ollama). Runs inside Zed over ACP and drives air-gapped hosts over SSH. MIT.
• AgentGrid – Desktop app (macOS/Linux/Windows) with an infinite zoomable canvas for orchestrating multiple AI coding agents in parallel. A master orchestrator pane spawns role-based workers (builder, QA, reviewer) in isolated git worktrees, alongside integrated terminals and Playwright browser panes. Runs Claude Agent SDK and OpenAI Codex SDK. Free tier available.
• Orkas – Open-source local-first desktop workspace that runs Claude Code, Codex CLI, OpenCode, Cline, and built-in agents in parallel with shared files and approval controls. Website
• Garcon – Self-hosted browser and mobile workspace for running and steering parallel Claude Code, Codex, Cursor Agent, OpenCode, Amp, Droid, and Pi sessions, with integrated terminal, files, diff review, Git/PR workflows, mobile approvals, and cross-agent transfers.
• BitFun – Cross-platform desktop coding agent built on a Rust runtime, with Git-aware workflows, Deep Review, MCP/Skills/Hooks, remote workspaces, and state-bound Mini Apps.
• Mirafold – Browser UI for Claude Code, Codex, and Gemini CLI where the agent renders live charts, diffs, and task lists as it works, with mission control across multiple sessions and E2E-encrypted phone pairing (self-hostable relay). Open source, local-first.
• Ordewell – Plan-first CLI/TUI orchestrator that turns one goal into an ordered plan of coding-agent tasks, each with its own runner (Claude Code, Codex, OpenCode), model, thinking effort and mode — editable before execution, run as one agent session per task, and marked done only when its own completion marker appears in the output. Apache-2.0, free, no paid tier.
• intentic – Self-hosted workspace that runs Claude Code, Codex, OpenCode, and Gemini CLI agents in parallel, each in its own Docker container and git worktree on hardware you own. Browser and mobile UI, terminals that survive disconnects, an editable sandbox Dockerfile, and per-file, per-hunk diff review before changes land. MIT, TypeScript.
• Dcode – The coding agent you own. Open-source, model-agnostic, and built by LangChain to give you maximum control over your software development lifecycle.
• Atomic Agent – Local-first coding agent that runs open-weight models entirely on your machine via a llama.cpp fork. 56 built-in tools (browser, filesystem, git, memory, vision), MCP support, and a five-layer memory system. No account or API key required.
• Kolega Code – Open-source terminal coding agent where the model writes its own multi-agent workflows (Gigacode), with 15+ providers and MCP support.
• Keen Code – An open-source, context-aware terminal-based coding agent written in Go. Supports multiple providers, MCPs, subagents, Agent Skills, controllable tool output retention, hashline edits, and more.
• Derivative – Open-source AI-assisted engine for greenfield requirement-to-software synthesis with typed requirement preservation, isolated execution, independent evidence-based validation, bounded repair, and fail-closed packaging.
• mix2 – Terminal app that turns two coding agents into one team. One question, both investigate independently, disagreements are disclosed, one answer. Works with Claude Code, Codex, Cursor, OpenCode, and Copilot CLI.
• Superagent – Open-source macOS desktop app giving Claude Code and Codex a real browser to drive, an iOS Simulator to install and screenshot apps in, and a phone companion app for remote monitoring.
• Sinatra – Coding agent for Linear and GitHub issues; runs in an isolated sandbox, opens a PR, and runs on your Claude or ChatGPT subscription.
• VibeFuse – Free Windows desktop harness that runs Claude Code, Codex, Gemini, Cursor, and Qwen as live widgets on one canvas, with a marketplace for selling AI skills and widgets (sellers keep 80%).
• Nexus-Agent – Open-source autonomous AI software engineering agent featuring dual-engine UX (Rich TUI + Cyberpunk Web Visualizer) and self-healing AST code engine.
• TaskHandoff – Self-hosted control plane for running Docker-based Codex workspaces on local and remote machines, with per-task workspace isolation, a diff review gate before changes land in your repository, and multi-agent handoff to a human reviewer.
• Sillage – Self-hosted, MIT-licensed, mobile-first web UI that drives the native Claude Code and Codex CLIs on your own machine, with server-side sessions, full-text search, an IDE panel, an MCP board the agents read, and an installable PWA. Single Docker container.
• Aura – Open-source semantic layer on top of Git for reviewing AI-generated code, tracking intent/provenance, and surfacing risky change areas.

CLI Tools

• Warp – AI-enhanced terminal with smart command suggestions and collaborative workflows.
• Claude Code – Anthropic's terminal-based coding agent.
• OpenAI Codex CLI – OpenAI's terminal agent with sandboxed code execution.
• Gemini CLI – Google's open-source terminal coding agent with free Gemini 3 Pro access and 1M token context.
• OpenCode – Open-source terminal AI agent supporting 75+ providers with multi-session support. Free.
• GitHub Copilot CLI – GitHub's AI assistant for command-line with context-aware suggestions.
• ShellGPT – ChatGPT integration for shell command generation and system administration.
• Aider – Open-source terminal AI pair programmer with deep git integration; every AI edit is auto-committed.
• AICommits – AI-powered meaningful git commit message generation.
• Amazon Q Developer CLI – AI CLI for AWS-related coding and scripting.
• Mentat – AI coding assistant for command-line development.
• TmuxAI – AI assistant for automating tmux workflows.
• Butterfish – AI tool for enhancing shell productivity with natural language.
• codachi – Context window monitor for Claude Code that shows burn rate and time remaining, with an ASCII pet that reacts to your workflow.
• agx – Checkpoint-based execution engine for AI coding agents; durable Wake→Work→Sleep loops that resume across sessions. Supports Claude Code, Codex, Gemini CLI, and Ollama.
• VibePod – Unified CLI for running Claude Code, Codex, OpenCode, Pi, and other AI coding agents in isolated Docker or Podman containers, with local metrics and an analytics dashboard.
• AI Badger – Local-first CLI for extracting clean, relevant codebase context to paste into any AI coding assistant.
• agentchecker – CLI that scans AGENTS.md, CLAUDE.md, Cursor rules, and Copilot instructions for contradictions and auto-fixes them. npx agentchecker
• cc-code – Rust-native terminal agent, Claude Code .claude/ config compatible. Multi-model (DeepSeek/MiMo/GLM), ~50MB memory.
• dotdog – CLI for structured software specs. Write .dog files, compile to .dag graphs, query via MCP server. Validates completeness, detects drift.
• Vernclaw Connect CLI – Official connector CLI with JSON-first agent-friendly connector invocation, managed connectors, and bundled skill docs for open-source workflows.
• grokpack – Unofficial Grok Build companion suite for Claude Code: observe (orientation card), drive (Grok executes / Claude orchestrates + gate), display (tmux HUD). MIT.
• agent-trace – Post-session analysis for AI coding agents. Track costs, tokens, tool health, and every conversation. Supports Kimi Code, Claude Code, Codex, OpenCode.
• token-meter – Real-time token cost meter for AI coding agents with status bar mode. Watch your tokens burn as it happens.
• AIPM – Open-source CLI and registry for finding, installing, publishing, and managing reusable agent skills across Cursor, Claude Code, and Codex.
• Crab Code – Rust-native agentic coding CLI supporting any LLM provider with multi-entry-point architecture (CLI/IDE/Web/Desktop). Apache-2.0.
• oh-my-kimi – Multi-agent orchestration harness for Kimi K2.6. Parallel coding teams in git worktrees, DAG scheduling, live quality gates, terminal HUD, and MCP skill-hooks.
• Pluribus – Open-source CLI that keeps one versioned AI coding context in sync across Claude Code, Cursor, Copilot, OpenClaw, Windsurf, Continue, and Zed.
• aicfg – AGENTS.md ecosystem CLI: init, validate, and manage project instructions for Claude Code, Cursor, Codex, and 20+ other AI coding tools.
• Sipcode – Open source MIT CLI for Anthropic Claude Code. Caps verbose terminal tool output (git, npm, grep, ls, cat, find, tsc), dedups duplicate file reads within a session via a PreToolUse hook, and surfaces per-session cost stats via 15 MCP tools. 1,317 tests, zero network calls.
• Runcap – Free local CLI that estimates, hard-caps, and losslessly compresses the cost of AI coding agents. Delta-encodes re-read files (37.9% proven on a real OpenAI call). MIT, 100% local.
• Vibe Creating – Open-source bilingual (EN/中文) Claude Agent Skill that rewrites a rough idea or over-specified shot script into a model-ready text-to-video prompt (Seedance 2.0, Kling, Veo, Hailuo, Wan, Vidu). Install via npx. Free, MIT.
• RoleCraft – Zero-dependency CLI to install AI agent skills as roles & behaviors from any source. Works with 86 coding agents.
• Lifeboat – Failover for coding agents: when Claude Code hits a rate limit, ban, or outage, hands the task to Aider, OpenCode, or a local Ollama model, carrying context. Multi-provider and local resilience, not account evasion. Open-source (MIT).
• Lacy Shell – ZSH/Bash plugin that auto-detects commands vs natural language and routes to the right place. Shell commands run normally; questions go to your AI agent (Claude Code, Gemini CLI, OpenCode, etc). Sub-millisecond lexical detection, no API calls.
• patina – Multilingual CLI and agent skill that audits and rewrites AI-sounding writing patterns while preserving claims, numbers, polarity, and causation.
• Vox Director – Agent skill that turns one topic into a finished Vox-style paper-collage explainer/ad video (script, collage art, motion, voice-over, music, captions); runs on Atlas Cloud + ffmpeg. Works with Claude Code, Codex & any SKILL.md agent.
• OpenAgentRelay – Open-source CLI that exposes a restricted local Claude Code, Codex, or automation as a keyed trusted-LAN capability, with JSON output and meaningful exit codes for agent workflows.
• stepback – Checkpoint and rewind for any AI coding agent (Claude Code, Codex, aider) via isolated git shadow-refs that never touch your real HEAD, index, or branch, with best-effort conversation resume for Claude Code and Codex.
• Atomic Agent – Open-source CLI and TUI coding assistant (React + ink) that runs open-weight models entirely on your machine. Install with one curl command, no account or API key required. macOS, Linux, and Windows.
• DevSpecs – Local-first CLI for AI-assisted brownfield development that indexes existing plans, source, tests, and Git history into model-agnostic context, bounded task slices, and durable checkpoints without calling an LLM.
• Portable Handoff – Local-first CLI that compacts a coding session into a Markdown/JSON capsule for resuming in Claude Code, Codex, or Cursor, with verified Git facts and no API key.
• CommitLore – Git-native decision memory that stores constraints and ruled-out alternatives as git trailers and notes, giving coding agents only the guidance still in force for the file being edited.
• fx – Tiny, open-source coding agent harness by Vercel Labs, written in Zig; model-agnostic, Unix-shell-like output, and embeddable in agent sandboxes.
• Loadout – Adaptive context engine for AI coding agents. Detects your stack and equips the right context when you launch load claude, load codex, load cursor. Works with Claude, Codex, Cursor, opencode, and Copilot.
• AgentBridge – Local MIT CLI that keeps Claude Code and Codex as live peers in one session for mid-turn review and quota-boundary handoff.
• Mantyl – CLI that turns a repository and its coding-agent history (Claude Code, Codex, Cursor) into a verified, recipient-checkable project passport for handing over AI-built software. Free, MIT.
• Tuff – Rust-based CLI for managing coding-agent capabilities (skills, tools, hooks, workflows, MCP servers) from a canonical manifest — install, track provenance, catch config drift, and emit harness-specific output for Claude Code, Codex, and others.
• agent-top – Terminal dashboard (htop-style) for monitoring multiple coding-agent sessions at once — status, token usage, cost, and associated processes for Claude Code, Codex, Gemini CLI, and more.
• Webcmd – Self-learning browser infrastructure CLI for coding agents; learns a site once, then reuses it as deterministic per-site commands.

App Builders

• Bolt.new – Build, edit, and deploy full-stack web apps in the browser using natural language with one-click deployment.
• Lovable – Create and deploy web apps from a single prompt in a browser tab.
• Replit – Cloud IDE with AI agent for building complete applications from descriptions.
• v0.dev – Vercel's AI tool for generating UI components and full pages from text prompts.
• Create.xyz – AI-powered app creation from natural language.
• Dyad.sh – Free, local, open-source AI app builder with any model and IDE integration.
• Builder.ai – AI-driven custom software development for web and mobile.
• Framer AI – AI-powered website builder with advanced design capabilities.
• Webflow AI – AI features within Webflow for automated design and content generation.
• FlutterFlow – Visual app builder for Flutter with AI assistance.
• Capacity – Agentic platform using Claude Code to turn ideas into full-stack web apps.
• Mage – Generate full-stack apps from natural language prompts.
• Microsoft Power Apps – Enterprise low-code platform with AI-powered app generation.
• Glide – No-code app builder with AI features.
• Durable – AI website and business app builder from simple text prompts.
• 10Web – AI-powered WordPress builder with automated design and optimization.
• Rocket.new – AI-powered rapid app development from natural language.
• base44 – AI-native software development OS for startups.
• MagicLoops – No-code platform for creating apps in minutes from text instructions.
• Rosebud AI – Vibe coding platform for 3D games and interactive web apps.
• Plandex – AI tool for planning and generating code from text prompts in the terminal.
• Softr – No-code app builder with AI assistance.
• Databutton – AI-powered app development platform.
• Builder.io Fusion – AI-powered visual development platform.
• Bolt.diy – Open-source fork of Bolt.new supporting any LLM (local or cloud) for building full-stack apps in the browser.
• Screenshot-to-Code – Convert screenshots and designs into clean HTML/React/Vue code using AI.
• Forge – BYOK full-stack app creator — use your own API key (Anthropic, OpenAI, Google) with no markup. Multi-stage pipeline generates production-ready Next.js apps from natural language.
• MeterCall – Universal API gateway over 10M+ APIs with AI router across 25+ models. Type a sentence in plain English, get a working app. 727+ ready-made modules to fork. Free tier, usage-based pricing.
• VULK – AI app builder for full-stack React + PostgreSQL, Flutter mobile, Three.js games, Shopify themes. Firecracker microVM live preview, BYOM with 16+ models, EU-hosted, full code export.
• OTF — Open Template Forest – Production-ready full-stack kits (Next.js, Expo) pre-wired for Claude Code, Cursor, and Lovable, with tested prompt libraries and AI configs included. MIT SDK + commercial kits.
• RapidNative – AI-native mobile app builder that turns ideas, sketches, or screenshots into working React Native and Expo apps with production-ready code. Freemium with 20 free credits.
• Vibes DIY – Open-source AI app builder that turns a plain-English description into a real, live web app you can share, remix, and collaborate on.
• KI-App-Bauplan – Free guided planner that turns an app idea into a focused MVP scope, risk review, seven-step build plan, and a starter prompt for Cursor, Claude Code, or Codex.
• Cactal – Cactal is the website platform for AI agents. Connect Claude Code, Cursor, or anything that speaks MCP, and your agent gets the tools to design, build, host, and operate production websites: source code, CMS, assets, domains, analytics, and publishing.
• Taskade Genesis – Prompt-to-app builder for live portals, CRMs, and dashboards with agents and automations.

UI Generators

• v0.dev – Vercel's AI tool for generating React UI from text and image prompts.
• Stitch (Google) – Google Labs tool using Gemini to generate multi-screen UI designs and front-end code from text or images.
• Magic Patterns – AI platform for creating reusable UI components.
• Figma AI – Native AI features in Figma for design automation and design-to-code.
• Uizard – Convert hand-drawn mockups, screenshots, or text into interactive prototypes.
• Kombai – Convert Figma designs into production-ready UI code.
• TeleportHQ – Generate production-ready code from visual designs.
• Deepsite – Build websites with AI on Hugging Face, no code required.
• tldraw Make Real – Draw UI wireframes on a canvas and convert them to working HTML/CSS with AI.
• CopilotKit – Open-source framework for building custom AI copilots, chatbots, and text areas into React apps.
• Freepik – AI design platform with image generation and mockup tools for UI designers.
• StyleSeed – Design engine that makes Claude Code & Cursor produce professional UI — 33 components, 69 design rules, 8 brand skins, and a named framer-motion motion system.

Code Review and Refactoring

• AICodeSlopMonitor – Detects low-quality and AI-generated code patterns to help developers review and improve codebases.
• SynthScan – Scans codebases for AI-generated code patterns.
• CodeRabbit – AI-driven contextual pull request reviews with actionable feedback.
• Sourcery – AI code reviewer supporting 30+ languages.
• Qodo (CodiumAI) – Code review and automated test generation platform.
• Sweep – AI agent for automating PR reviews and fixes.
• Greptile – AI bot for in-depth code review and PR analysis.
• What The Diff – AI tool for summarizing and analyzing code diffs.
• DeepSource – Automated code review with tech debt tracking and security analysis.
• Codacy – Code quality platform with 30+ language support.
• JetBrains Qodana – AI-powered static analysis for code quality.
• Semgrep – Static analysis for finding bugs and security issues.
• CodeQL (GitHub) – Semantic code analysis for security and quality.
• Snyk (DeepCode) – Security-focused code analysis with vulnerability detection.
• Pixee – AI bot for security-focused PR reviews and automatic fixes.
• Qodo PR Agent – Open-source AI agent for PR reviews with actionable insights.
• Amazon CodeGuru Reviewer – ML-powered code reviews with AWS integration.
• Refact.ai – AI-driven refactoring and code optimization.
• Embold – AI code analysis for quality, maintainability, and tech debt.
• Veracode – AI-driven application security with static and dynamic analysis.
• PullRequest – Human-AI hybrid code review combining automated analysis with expert reviewers.
• Z.ai Code Review - AI-powered GitHub Pull Request code review using Z.ai models.
• MiniMax Code Review - AI-powered GitHub Pull Request code review using MiniMax models.
• VibeDoctor – AI code health scanner for vibe-coded apps. Detects hallucinated imports, phantom packages, and security issues that traditional scanners miss with MCP Support.
• Relay – Persistent memory for AI coding workflows. Give AI coding agents memory of what was built, what broke, and what's next.
• MealMacroAI – AI-powered reverse macro calculator that converts target nutrition into precise raw and cooked food portion weights.
• Kodus – Open-source AI code review tool for pull requests, with repository context, custom rules, Git workflow integration, and BYOK support.
• brooks-lint – Claude Code plugin that reviews code against twelve classic engineering books, citing each finding to its source and scoring codebase health 0–100.
• Swarm Orchestrator – Audits AI-generated pull requests for eleven cheat patterns (relaxed tests, swallowed errors, fake renames). Advisory by default, opt-in merge gate.
• Git AutoReview – VS Code extension for pull request review on GitHub, GitLab, and Bitbucket, including self-hosted Server and Data Center. You pick Claude, Gemini, or GPT, then approve each suggestion before it posts. Runs on your own API key, so code goes straight to the provider.
• argot – Guardrail that flags AI-written code foreign to a repo's own patterns (unfamiliar deps and APIs, reinvented functions, misplaced code, layering breaks, tests gamed to pass CI), learned statistically from git history. Runs 100% local as a single Rust binary, no second LLM.
• MergeFix – AI website audits (SEO, performance, accessibility, security) delivered as real GitHub pull requests, plus a Migrate & Own flow to move an AI-built app into a repo you fully own.
• UIZZE – Stop generic UI before it ships. The free MIT anti-ui-slop Skill gives coding agents a product-specific design contract, required loading/empty/error states, and a hard finish gate. The optional authenticated MCP provides find_ui_references and find_ui_materials over 800,000+ real web and iOS screens.
• OrcaCode Review – GitHub Action for AI pull request review that posts findings inline on the affected lines and blocks merges on critical severity.
• twoperson – Two-person rule for AI coding agents: a builder agent and a reviewer agent share a file-based review inbox whose schema won't let work be marked shipped without a verdict bound to that exact commit, so the review can't be skipped or applied to the wrong revision. Stop-hook installer, credential scan, worktree-aware; MIT.
• VibeAudit – Pre-launch code audit that reads your whole repo and returns a launch-readiness score plus fixes as paste-ready prompts for your AI editor.
• OpenFiles – VS Code extension that opens every file an AI agent edits so linters and type checkers run on it, lists the changes for review, and returns the problems to Claude Code, Codex, Copilot, Gemini CLI or Cursor. Free and open source (MIT).

Testing and QA

• Playwright – Microsoft's end-to-end testing framework (often used with AI-powered test generation).
• Qodo – AI-powered test generation and code quality assurance.
• DiffBlue Cover – AI-generated unit tests for Java applications.
• Testim – AI end-to-end testing with self-healing locators.
• TestRigor – Plain English test automation with self-healing.
• Mabl – AI-native test automation with auto-healing and visual testing.
• Applitools – Visual AI testing platform with cross-browser support.
• Meticulous – AI-driven visual and functional testing.
• Checksum AI – AI automated software testing and validation.
• KushoAI – AI-driven API testing.
• Katalon Studio – Comprehensive test automation with AI features.
• Testsigma – AI test automation with natural language test creation.
• Launchable – AI-driven test optimization that predicts which tests to run.
• Autify – Self-healing test automation with visual regression testing.
• Reflect – No-code test automation with AI maintenance.
• Parasoft – AI-enhanced testing suite covering static analysis, unit testing, and API testing.
• Rainforest QA – AI-assisted testing with crowd-sourced manual testing.
• Codeflash – AI-powered Python performance optimization and benchmarking.
• Wopee.io – Autonomous visual regression testing with Playwright/Cypress integration.
• Prompt Evaluator – Web-based prompt and workflow QA tool. Evaluate, compare, and audit AI prompt outputs and workflow quality.
• BenchGen – AI agent benchmarking and evaluation platform. Score agent runs across tool-call accuracy, goal completion, and skill coverage, then export filtered trajectories for fine-tuning.
• AI Test Case Generator – AI-powered test case generator that turns plain-language requirements into structured QA test cases for web and software testing workflows.
• agent-qa – Self-improving QA agent for web and mobile apps with natural-language tests, run memory, UI-change adaptation, and regression detection.
• AIFast Model Check – Free browser-based diagnostics for public HTTPS OpenAI-compatible API endpoints, including metadata, token handling, dynamic responses, SSE streaming, and tool-call checks.
• SDKProof – Type-checks how well AI writes your SDK's current API by compiling model output against the real installed package (no LLM judge).
• QualityMax – Independent AI QA platform that generates, executes, and gates tests across web, mobile, API, performance, and security, with self-healing automation.
• rung – Deterministic, AI-free CI gate that checks whether an AI coding agent ran the checks it claims: reads an evidence bundle from the real run and passes or blocks the build. Ships as a GitHub Action, CLI, and agent-agnostic skill.
• squirrelscan – CLI website audit tool built for coding agents (Claude Code, Cursor). Runs 260+ rules across SEO, performance, security, accessibility and agent experience, and hands the agent exact, source-mapped fixes. Free local audits, GitHub Action, MCP server.

Code Search and Navigation

• Sourcegraph Cody – AI-powered code search and navigation for large codebases.
• Pieces.app – AI-powered code snippet management, search, and sharing.
• 16x Prompt – AI tool for enhanced code context and prompt-based navigation.
• codebase-recon – AI coding agent skill that analyzes git history to reveal hotspots, bug magnets, bus factor risks, and development momentum before reading any code.
• Reflex – Local-first full-text code search engine with MCP server and JSON output built for AI coding agents.
• CocoIndex Code – AST/tree-sitter code search MCP server that indexes a codebase and returns compact, relevant snippets to reduce coding-agent context usage.

Documentation

• Mintlify – AI-powered documentation platform that auto-generates and maintains docs from code.
• GitBook AI – AI-enhanced documentation with intelligent content suggestions.
• README-AI – AI tool for creating professional README files automatically.
• DocuWriter.ai – AI documentation generator for codebases and APIs.
• DiagramGPT (Eraser) – Generate diagrams from code and text descriptions.
• Theneo.io – AI-powered API documentation generation.
• Slab – Team knowledge base with AI search and automated documentation.
• GPTutor – VS Code extension for LLM-powered code explanations across 120+ languages.
• Repowise - Open-source codebase intelligence tool that indexes repos into dependency graphs, git history, auto-generated docs, and architectural decisions via 7 MCP tools.
• SwarmVault – Local-first RAG knowledge vault. Compiles raw sources into a durable markdown wiki with a knowledge graph and hybrid SQLite FTS plus embeddings. Built-in MCP server for Claude Code, Codex, and OpenCode.
• ReadMeAI – Generate professional README.md files from any GitHub repo URL with AI. Includes description, installation, usage, and contributing sections. Free, instant.
• LegacyDoc AI – VS Code extension that generates AI code audit reports, Markdown docs, JSDoc, and Mermaid architecture maps from existing codebases.
• CodeAlmanac – Self-updating repo wiki for AI coding agents that tracks project conversations and context locally, lives in your repo, and is free to use.
• PolicyAI – AI-powered legal document generator. Creates GDPR & CCPA compliant Privacy Policy, Terms of Service, and Cookie Policy for developer products in 60 seconds. Free tier available.
• notabene – Self-hosted docs viewer with Google-Docs-style comments and a human-agent review loop that turns comments into source edits.

Code Models

• Claude (Anthropic) – Opus and Sonnet models dominate coding benchmarks in 2026; Claude Code is built on them.
• GPT-5 (OpenAI) – Powers GitHub Copilot, Codex CLI, and ChatGPT coding workflows.
• Gemini (Google) – Powers Google Code Assist, Gemini CLI, and Antigravity with 1M token context.
• DeepSeek Coder – High-performance open-source coding model; popular for cost-efficient AI coding via API.
• Qwen2.5-Coder – Alibaba's open-source coding model, leading choice for self-hosted/local deployment in 2026.
• Code Llama – Meta's open-source LLM optimized for code generation and completion.
• StarCoder 2 – Open-source LLM for code generation by BigCode, supporting 600+ languages.
• Codestral – Mistral's open-weight model designed for code generation.
• Phi-4 (Microsoft) – Microsoft's lightweight, efficient model family with strong coding performance.
• outsourcerer – Delegates coding grunt-work to other harnesses and models from the terminal while your main session stays the orchestrator.

Developer Productivity Tools

• Agent Cost Guardrails – Framework-native budget limits and circuit breakers for AI agent frameworks (CrewAI, AutoGen, LangGraph). Hard token caps, cost alerts, and spend tracking with hooks that integrate directly into agent execution loops. Open-source, available on PyPI and npm.
• Raycast AI – AI-powered productivity launcher with coding capabilities and workflow automation.
• Warp AI – AI-enhanced terminal with intelligent command suggestions.
• Context7 – MCP server providing up-to-date library documentation to LLMs and AI editors.
• Task Master – AI-driven task management for development with Claude, designed for Cursor.
• SpecStory – Cursor/VS Code/Claude Code extension for summarizing and sharing AI chat context.
• Git AI – Git extension that tracks AI-generated code and the prompts behind each line.
• Perplexity Pro – AI search engine with real-time web access for coding solutions.
• CodeCosts – Compare pricing across AI coding tools with an interactive calculator.
• Supercode.sh – Cursor extension adding Architect Mode, voice input, and prompt enhancement.
• toprank – Open-source (MIT) Claude Code plugin with 9 SEO and Google Ads skills. Connects Google Search Console, PageSpeed Insights, and the Google Ads API to audit traffic, ship meta tag and schema markup fixes, and manage ad campaigns directly from Claude Code.
• Google Drive – Memyard – Agent skill that lets AI coding agents create and edit Google Docs and Sheets without sign-in. Documents hosted on Memyard with shareable links.
• MemClaw – Persistent project memory for AI coding agents (MCP-compatible). Creates isolated memory workspaces per project with a web dashboard to review and manage context. Free and open source.
• git-parsec – Git worktree lifecycle manager that gives each AI agent an isolated workspace tied to issue tickets (Jira, GitHub Issues, GitLab), avoiding index.lock conflicts in parallel workflows.
• AI Dev Jobs – AI job board aggregating 6,000+ positions from 340+ companies like OpenAI, Anthropic, and Google DeepMind. Free API and MCP server for AI-powered job search.
• CronAI – Convert plain English schedule descriptions to cron expressions with AI. Supports st

内容由编辑整理，部分信息来自 GitHub 与项目官网，版权归原作者所有。发现错误？报告问题