AI Tools for Coding

Signup

Go to: All AI Tools AI Tools by Tool Type AI Tools by Job Type

AI Tools for Coding

Supercharge your coding productivity with cutting-edge AI tools. Benefit from intelligent auto-completion, real-time debugging assistance, optimized code suggestions, and reduce development time substantially.

Signup & Stay Updated on the latest AI Tools

AI Tools for Coding

### AI Tools available

oqoqo

Oqoqo lets product teams build custom benchmarks and realistic evals for AI agents. It runs agent tasks in isolated sandboxes, tracks steps and costs, and scores success against your criteria. It is built for developers evaluating how discoverable...

Prime Agent

Prime Agent is an open-source, self-improving coding harness for AI developers and researchers. It uses Recursive Language Model and Continual Harness abstractions to advance agent performance, achieving 95.5% on ARC-AGI-3 with Opus 5, above the r...

bb

bb is an open-source agentic orchestrator GUI for Claude Code, Codex, OpenCode, Cursor, and other ACP-compatible agents. It is for developers who want to customize their agent workflows, as nearly every component can be changed or extended with pr...

Toolport

Toolport is a free, open-source local MCP gateway that lets multiple AI agents share the same configured servers. It reduces token usage by up to 91% through on-demand tool searches. It is for developers using Claude, Cursor, VS Code, Codex, or ot...

Progress AI Observability

Progress AI Observability gives engineering teams tracing and evaluation tools for AI agents in production. It explains why an agent chose a tool, ignored context, or produced a wrong answer, and supports .NET, Python, and JavaScript/TypeScript. I...

HAR

HAR provides a single in-repo contract that centralizes configuration and documentation for AI agents. It targets development teams managing multi-agent setups, replacing scattered CLAUDE.md files, README instructions, editor rules, and CI config ...

Soloop

Soloop provides a coordinated team of AI agents for solo founders. The AI CEO plans and coordinates, the AI CTO builds from user signals, and the AI CMO handles distribution and feedback. Founders approve decisions requiring judgment.

Whop CLI

The Whop CLI is a command-line tool that brings Whop's business API, a development tool that brings Whop's business tools. The Whop CLI is a command-line interface, a terminal interface that brings Whop's business API. It is a command-line interfa...

Rindler

Rindler provides prebuilt maps of websites that AI agents call instead of reading pages directly. Each map defines screens, actions, and response shapes, so agents receive consistent fields on every run. It serves developers building browser agent...

Keystroke

Keystroke is a collaborative platform for building, deploying, and running AI agents inside a company. It provides integrations, credentials, memory, workflows, triggers, approvals, and observability in one workspace, allowing teams to create agen...

Murmell

Murmell is a browser-based cloud canvas where AI coding agents and your team work on a single repository in a shared cloud environment. It is designed for development teams who want to avoid coordination issues and keep agents running even when la...

npm i -g hotcell

Hotcell is an open-source command-line tool that creates, pauses, and manages isolated sandboxes on local hardware, including laptops, Linux VMs, and bare metal. It is built for developers and agentic coding tools, supporting Docker, Apple VZ, or ...

mpai

mpai shares a Claude Code or Codex session over Tailscale, letting teammates send attributed prompts into the same terminal conversation. It is for developers who want to collaborate in a coding session that was previously single-player.

Termexo

Termexo manages multiple coding agents in native CLI terminals for developers running tools like Claude Code and Codex on Windows. It restores workspace layouts, resumes sessions, and alerts users when an agent needs attention.

Octomind Cloud and Hub

Octomind Cloud and Hub runs AI agents on cloud machines, letting users assign a task, disconnect, and resume sessions from any device. It offers per-second billing, 21 built-in models, and no API keys, serving developers and teams needing persiste...

agent-manager

agent-manager is a keyboard-driven tool for running coding agents inside tmux sessions, letting users start, review, and fork agent work with single keypresses. It is built for developers who use multiple CLI coding agents and want to keep their s...

ngrok AI Gateway

ngrok AI Gateway is a hosted service that provides a single URL for managing AI models across multiple providers, private infrastructure, and local hardware. It is built for developers who need to centralize access, keys, and usage tracking withou...

Coldtea.ai

Coldtea.ai is an agentic development environment that combines terminal, testing, and monitoring include production. It supports teams that release testing on iOS, Android, and web. Visual QA agents can use these agents in production, but catches ...

Capacity Desktop

Capacity Desktop is a Mac app for Apple Silicon that converts plain English instructions into working applications stored locally on your machine. It is built for developers who want to own their code and use AI at cost, with no sign-up or credit ...

SKI

SKI is a local voice interface for coding agents that lets developers speak commands and hear spoken responses. It runs offline on Mac and Windows, allowing users to control sessions hands-free or send the agent to meetings.

Liminal

Liminal is a collaborative workspace that lets humans and AI agents edit and share local markdown files in a web browser. It is built for developers and teams using AI coding agents that need direct file access and real-time cloud sync.

ADE

ADE is an app that centralizes multiple AI coding subscriptions and syncs chats across devices. It helps developers run parallel agents, review pull requests, and edit files from any computer or phone.

Memmy Agent

Memmy Agent manages memory and context for developers using coding assistants like Claude Code. It allows programmers to maintain project details across multiple coding sessions.

OpenCode Superapp

OpenCode Superapp is a coding application for software developers. It writes and debugs code to help programmers build software.

Plow Mac App

Plow Mac App helps developers build applications with GPT-5.6 that were previously impractical. It provides a native desktop environment for creating and testing these Mac software projects.

Diffsmith

Diffsmith tracks comments during agent coding sessions. Its resolution step follows anchors when AI agents rewrite code blocks. This helps developers keep review rounds readable after multiple iterations.

Replay QA

Replay QA explores your app to find real bugs and gives your coding agent the root cause and fix. Developers can add a GitHub repo for continuous testing or drop in a URL for a one-time check.

Prelint

Prelint reviews coding agent output against specifications and tickets to catch incorrect product decisions. It helps engineering teams ensure AI changes match business requirements before they ship.

tterm

tterm merges a terminal running Claude Code, a Chromium browser, and a file viewer into one window for developers. It removes the text editor so users review code diffs and commit changes directly within the same window.

ccshare

ccshare allows up to five users to operate terminal-based coding agents like Claude Code together in a live session. It helps developers who need to pair program, debug, or teach by letting everyone type in the same terminal.

Claude Overlay

Claude Overlay is a Windows tool for developers that captures screen context via a hotkey to ask Claude Code about errors. It uses your existing CLI login so the agent can read your monitors and fix code directly.

Muse Spark 1.1 by Meta AI

Muse Spark 1.1 by Meta AI is a multimodal reasoning model for agentic AI that improves coding and multi-agent orchestration. Developers building AI tools can access it in Thinking mode on Meta AI or via the Meta Model API.

agents-cli

agents-cli is a command-line tool that helps developers and coding agents build, evaluate, and deploy agents to production. It manages infrastructure and Google Cloud deployment so teams can focus on agent behavior.

LongCat-2.0

LongCat-2.0 is an MIT-licensed MoE model trained for coding and agentic workflows. It provides developers with a one million token context and integrates with Claude Code and OpenClaw.

CodeMote

CodeMote pairs your iPhone or iPad with your dev machine, streaming a live terminal as a Lock Screen Live Activity. It sends a push when your AI coding agent pauses for input, letting you approve plans remotely. It works with any terminal-based ag...

Termi Protocol

Termi Protocol provides a 3D room where CLI coding agents like Claude Code and Codex appear as robots. You can watch them read files, write code, and run commands in real time. It is for developers who want visual monitoring and control of their c...

Vox

Vox provides a voice-driven interface for GitHub Copilot. You speak commands and hear responses, with live captions and barge-in interruptions. It is for developers who need hands-free coding assistance.

Clusy

Clusy is an AI-native notebook for data science that manages the whole pipeline. Its agent works alongside users from initial idea and environment setup to model training and deployment.

PMB

PMB provides developers with local memory for coding agents by storing decisions and lessons in a SQLite workspace. It feeds this context to tools like Cursor and Claude Code to prevent repeating instructions across sessions.

AI‑Native eCommerce Infrastructure

StoreFrame is an AI-native eCommerce infrastructure hosting Magento with pre-tuned configurations. It provides a browser-based Claude Code shell for developers, agencies, and merchants to collaborate on store operations and development.

MeshPilot

MeshPilot is a workspace for developers that integrates terminals, a visual canvas, and task boards. Voice-controlled AI agents execute tasks, and persistent memory retains context across sessions.

Backgrind

Backgrind is an always-on-top overlay that runs AI coding agents over any app. It lets developers work on other tasks while the agent runs in the background, pinging only when it needs a decision.

Tencent EdgeOne Makers

Tencent EdgeOne Makers is an edge platform for developers to build and deploy web apps and AI agents. It provides built-in runtime and storage to launch applications without assembling complex infrastructure.

GitHits beta 0.9

GitHits beta 0.9 lets AI coding agents search GitHub for external library source code. It is for developers who need to inspect how third-party frameworks behave beyond standard documentation.

agentbrowse

Agentbrowse helps AI coding agents interact with websites using the accessibility tree instead of brittle CSS selectors. It auto-detects agents and writes native configuration files for tools like Claude Code, Cursor, and Gemini.

Kickbacks.ai

Kickbacks.ai is a terminal script that displays ads in the status line while developers wait for AI code generation. It targets software engineers using AI coding assistants, paying users for idle time through ad impressions.

Canopy

Canopy is a macOS tool for developers using Claude Code. It prevents parallel task collisions by running each session in an isolated git worktree and sandboxed container. The app manages multiple sessions in tabs and preserves state on exit.

Deep Work Plan

Deep Work Plan prevents AI agents from drifting during long coding tasks by storing specs and acceptance criteria directly in the repository. It gives developers a tool-agnostic way to maintain context without relying on chat windows.

Bob's CLI

Bob's CLI is an AI engineering partner for developers with day jobs. It lives in your terminal, remembering your architecture and coding patterns to avoid ramp-up time. It also allows remote command execution from a phone to your home desktop.

Otty

Otty is a terminal for developers using code agents, offering a clean interface with vertical tabs, smooth scrolling, session recovery, and clickable links, without agent-control clutter. It preserves sessions with tools like Claude Code and tmux ...

Patchrooms

Patchrooms is a feedback layer for developers and designers building apps with AI tools. The tool automatically captures technical context when users point at elements to leave feedback. This creates patch context for AI coding assistants.

SlimSnap

SlimSnap converts screenshots into structured JSON specs for AI coding tools to parse screen elements accurately. This helps developers avoid raw pixel guessing by providing exact coordinates and OCR text.

TryCase

TryCase gives coding agents disposable cloud Linux environments to run apps and capture proof. It helps developers ensure AI agents verify their work end to end by returning screenshots and video recordings instead of just code.

Revyl

Revyl is a mobile debugging tool for developers shipping mobile apps. It captures the full run to identify failures and auto-maps screens to create a live source of truth. A CLI also allows users to drive cloud devices from the terminal.

Revyl

Revyl is a mobile debugging tool for developers shipping mobile apps. It captures the full run to identify failures and auto-maps screens to create a live source of truth. A CLI also allows users to drive cloud devices from the terminal.

OLO Robotics

OLO Robotics is a browser-based platform that lets you pick a simulator and robot, teleoperate, access ROS2 topics, get an AI coding assistant and use JavaScript/Python SDKs - deploy a Docker bridge to connect your robot in minutes.

Daemons by Charlie Labs

Daemons by Charlie Labs handles operational debt for software teams using coding agents. These persistent teammates run recurring tasks like bug triage and CI repair across GitHub and Slack.

agentcad

Agentcad gives coding agents the ability to run and verify code while drafting, catching errors early so you get tested, reliable prototypes for faster feedback and iteration.

Boxes.dev

Boxes.dev provides cloud-only dev environments that give each Codex or Claude Code agent its own cloud computer. Auto-ports your local setup, runs and tests apps end-to-end, and supports parallel agent workflows.

Superlog Responder

Superlog Responder is an AI bug-fixing agent that integrates with existing Sentry or Datadog Slack channels. It investigates each alert, filters noise, and replies in the thread with the root cause, evidence, and a mergeable pull request. It is fo...

Replicas

Replicas runs AI developer agents in isolated cloud VMs that provision full dev environments, dependencies and databases. Trigger from GitHub, Slack or API to automate code reviews, CI checks and continuous background agents.

GPS

GPS anchors persistent memory to repo symbols and files so agents receive only relevant rules, fixes, tests and gotchas before acting. Agents can save memories mid-task, reducing tokens and improving recall across runs.

Phasr

Phasr centralizes engineering workflows: run 100+ persistent workspaces, manage multiple repositories, pin key commands, and coordinate AI agents-reducing context switches so teams stay organized and move faster.

BobCA

BobCA provides a sovereign digital workforce: set grading targets in Mission Control, then let your digital twin autonomously debug, refactor, and build while logging constraints and tracking bugs fixed and features shipped.

MashuPack

MashuPack compiles chosen source files into one clean text file for browser LLMs, letting you select exact context to bypass file/count/upload limits and streamline code reviews, planning, debugging, and repo discussion.

Pi Coding Agent

Pi Coding Agent is a minimal, hackable terminal harness for building and customizing AI coding-agent workflows. Keep the core small and extend or replace context management, sub-agents, permissions and workflows via extensions.

marpy.io

marpy.io is a browser IDE, deployment platform and AI assistant for Python web apps (Flask, FastAPI, Django). Build and deploy backends faster with built-in git, MariaDB/Redis support and one-click deployments.

The Incident Challenge

The Incident Challenge is a timed production-debugging game that drops engineers into realistic outages with logs, code, configs and diagrams. Find the root cause, fix, deploy and climb the leaderboard-AI aids, human judgment wins.

MoDev

MoDev: remote developer workspace to edit code, deploy and run AI from any device. BYOK on dev plans - AI billed by your provider, no markups. Plans start at $15/mo.

Revolte

Revolte automates software delivery: give a ticket and AI agents plan work, update your codebase, run checks, open PRs, assist deployment and monitor runtime-accelerating delivery with humans in control.

Staff.rip

Staff.rip: a local AI coding agent for frontend, backend, infra and tests-run hosted or self‑hosted so your code stays local. No git, no CLI. Team chat + click‑to‑edit on running apps; free to start.

Radiq

Radiq ingests signals from Slack, calls and tickets, builds an architecture-grounded knowledge graph, and pushes structured, developer-ready specs to Cursor or Windsurf-automating the customer-to-code handoff so devs get it right first time.

WOZCODE

WOZCODE is a Claude Code plugin that cuts token costs up to 55%, speeds agent runs up to 40%, and boosts Terminal Bench 2.0 scores by 11 points, making coding agents cheaper, faster, and more accurate.

WOZCODE

WOZCODE is a Claude Code plugin that cuts token costs up to 55%, speeds agent runs up to 40%, and boosts Terminal Bench 2.0 scores by 11 points, making coding agents cheaper, faster, and more accurate.

Mistral Medium 3.5

Mistral Medium 3.5 is a 128B merged model for instruction-following, reasoning and coding, with a 256k context window, configurable per-call reasoning, 77.6% on SWE-Bench Verified, and self-hosted on four GPUs.

CodeHealth MCP Server by CodeScene

CodeHealth MCP Server by CodeScene injects code-health metrics into CI and AI workflows, reducing AI-driven defects and token waste so teams can scale AI safely and keep technical debt under control.

Agent Context

Agent Context attaches external folders as first-class reference context in your workspace so AI tools can access code without copying files or polluting your repo.

Chat Skills for AI Agents

Chat Skills for AI Agents supplies framework-specific skill files so your coding agent (Claude, Copilot, Cursor, VS Code) auto-configures CometChat UIs-SSR, env vars and login/init sequencing managed; ready in under 15 minutes.

Fixa.dev

Fixa.dev is an autonomous cloud developer that browses docs, installs languages/deps, builds production-ready backends, wires databases, and deploys full-stack apps with one-click integrations (Stripe, Supabase, Clerk, OpenAI, Vercel).

Claude Code Rendering

Claude Code Rendering virtualizes the terminal viewport for Claude Code CLI, eliminating flicker and adding mouse support (click-to-position, expand results, URL/file clicks), smooth scrolling and transcript search - no external TUI or new depende...

Android CLI

Android CLI brings agentic Android development to the terminal: manage SDKs, scaffold projects, run emulators and deploy via CLI. Cuts token use and speeds tasks ~3x, grounded with official Android skills and auto-updating best-practice guidance.

Navox Agents

Navox Agents runs eight specialist Claude Code agents as an engineering team-each owns a task, passes structured briefs, and requires approvals. It preserves decisions, enforces tests, recommends stacks (defaults to Vercel) and speeds deployments.

Subspace

Subspace is an Agent Workspace that bundles agents, terminals, docs, and a browser per project. Persistent memory lets agents recall past work across sessions so you can resume tasks without repeating context.

Claude Code Desktop App Redesigned

Claude Code Desktop App Redesigned streamlines parallel agent coding: session sidebar, side chat, integrated terminal/editor, drag-and-drop layouts, and view modes for managing multiple repos and PRs. Requires Pro/Max/Team/Enterprise.

Clide

Clide: native macOS terminal with an AI pair-developer in a side panel. Reads shell panes, types commands (exec after you confirm), previews/edits files, accepts screenshots/files, and enforces zero telemetry.

CC-BEEPER

CC-BEEPER: a floating retro pager for Claude Code that surfaces agent status, permission prompts and results, with voice dictation, spoken recaps, hotkeys and auto-accept modes. Runs locally in Swift-no accounts, telemetry, or API keys.

Caveman

Caveman: a Claude prompt that removes verbosity for coding tasks-≈75% fewer tokens, ≈3x faster responses, plus terse commits and one-line PR comments. Free, MIT, one-line install.

SuperHQ

SuperHQ runs coding agents in isolated Debian microVMs, mounting projects with tmpfs overlays so your host is untouched. View unified diffs to accept or discard changes; API keys never enter VMs-they're swapped in by a local auth gateway.

ContextPool

ContextPool is a local persistent memory layer for AI coding agents: it extracts actionable engineering insights from past sessions and auto-loads relevant context while keeping raw transcripts local.

Claude Code ultraplan

Claude Code ultraplan moves planning from CLI to your browser: run /ultraplan, generate cloud-hosted implementation plans, then review, comment, react per section, and iterate in claude.ai while your terminal remains free.

Codentis

Codentis is a CLI AI assistant that brings agentic workflows, streaming output, memory, and actionable terminal commands-helping developers execute tasks, debug faster, and stay focused without constant context switches.

Grass

Grass keeps coding-agent conversations in sync between phone and laptop, provides a free pre-configured VM with 10 free compute hours, and uses BYOK so your API keys never leave your device.

Grok 4.2 Beta 2

Grok 4.2 Beta 2 runs four specialist agents that debate, verify and synthesize outputs-reducing hallucinations, boosting math/coding/research reasoning, improving LaTeX and image handling with weekly updates for devs and researchers.

Baton

Baton centralizes Claude Code agents into a single dashboard, letting you view, review and manage agents and their code changes, and launch new instances across IDEs and terminals without switching windows.

OpenClawCloud

OpenClawCloud: zero-setup cloud VM with a ready OpenClaw agent, preinstalled skills and unlimited GLM-4.7/GLM-5 tokens. Start free (7 days + unlimited GLM-4.7); no API keys, configs, or per-token billing.

RepoLens

RepoLens analyzes PRs and branches to surface changed modules, endpoints and review hotspots. It provides branch-aware chat with code references, structural branch comparisons, and alerts so teams track code changes faster.

CrabTalk

CrabTalk: an 8MB Rust daemon that composes your CLI tools via PATH. Components connect as services, crash or swap independently. Open-source, one-curl install-build apps on top, not beneath.

Cosyra

Cosyra lets you run terminal coding agents and code from your phone-patch, build, audit, and manage projects with GitHub, localhost preview, session switching, and built-in isolation. Free 7-day / 10-hour trial.

Drift

Drift previews commands before running and lets you pause mid-execution, giving engineers control over automation to reduce errors, manage dependencies and multi-terminal processes, and improve reproducibility.

Cursor Glass

Cursor Glass gives engineers a unified workspace to run, monitor and manage multiple local and cloud agents, with Cloud Handoff to switch mid-task. Composer 2 adds faster, lower-cost performance for scalable multi-agent workflows.

.

As seen on