AI coding & building

AI coding agents & assistants: the tech stack of 70 real products

Tools that write, edit or explain code in an editor, terminal or browser.

What sets them apart

Picks at least twice as common here as among products overall, in decisions at least 10 of them show.

The typical stack

The leading pick where at least 8 of them show the decision and the leader has at least a quarter of it.

DecisionMost common pickShareAt default usage
Frontend FrameworkReact37 of 50 · 74%—
LLM APIClaude32 of 41 · 78%$10/mo · Claude Haiku 5.5
HostingCloudflare13 of 31 · 42%$12/mo · Workers Paid
DatabasePostgreSQL14 of 28 · 50%—
Backend FrameworkExpress11 of 25 · 44%—
AI SDK & Agent FrameworkAI SDK13 of 24 · 54%—
Transactional EmailResend16 of 19 · 84%$20/mo · Pro 50k
Database Access & ORMsDrizzle ORM6 of 14 · 43%—
Product AnalyticsPostHog10 of 13 · 77%$0/mo · Pay-as-you-go
AuthenticationClerk4 of 11 · 36%$0/mo · Hobby
PaymentsStripe9 of 11 · 82%fees on revenue · $410 on $10,000/mo
Web AnalyticsVercel Web Analytics5 of 11 · 45%—
Error MonitoringSentry9 of 10 · 90%$29/mo · Team
Image & Video Hostingsharp8 of 9 · 89%—
Vector DatabaseQdrant3 of 8 · 38%$103/mo · Standard (3 nodes, 0.5 vCPU / 4 GiB each)

Monthly bills add up to about $173 at the calculators' default usage, list prices; fees on revenue (Stripe) come on top. Set your own usage →

What they chose, decision by decision

Among the AI coding agents & assistants that show each choice, from makers' products and open-source code alike.

Small samples, fewer than 8 products: File Storage (Amazon S3 3, MinIO 2) · LLM Observability & Evals (Langfuse 1, Helicone 1) · Background Jobs & Cron (Inngest 1, BullMQ 1)

AI coding agents & assistants we track

39 makers' products and 31 open-source projects. Makers' products first.

supersetDesktop IDE for running several coding agents in parallel, each in an isolated workspace, with notifications and a diff viewer for reviewing their changes. Has a companion iPhone app; aimed at developers who work with coding agents.+15
Traycer AIPlan-first AI coding for real codebases+5
RightNow AICode editor for GPU/CUDA development with built-in profiling, benchmarking and AI-assisted optimization.+3
Git PitcherReverse engineer any GitHub repo into an agent-ready plan+1
stagewiseThe frontend coding agent for existing codebases+1
AraSelf improving IDE
Fixa.devA cloud-native AI agent that can build literally anything
ShapeThe Agentic IDE for Designers and Programmers
CodebuffBetter code generation than Cursor, from your CLI
IncertoThe AI Copilot for Databases
Blop AIBlop turns design feedback into code you can ship
cto.newCompletely free AI code agent
SuperflexWrite Front-End Code 10x Faster ⚡️
cyrusThe Claude Code background agent for Linear, Slack, Github, GitLab etc. you deploy anywhere. Supports Codex, Cursor, Gemini, and Opencode harnesses too.+2
emdashEmdash is the Open-Source Agentic Development Environment (🧡 YC W26). Run multiple coding agents in parallel. Use any provider.+1
compozyAn operating system for AI agents. Plug in the agent CLIs you already use (Claude Code, Codex, Gemini CLI, Cursor) and they become a team: they split the work, hand tasks to each other, run automated
Deep Work PlanModels matter. Context matters more. Give your agent a plan.
PolygraphLet AI agents see cross repo and maintain session memory.
omnigentOmnigent is an open-source AI agent framework and meta-harness: orchestrate Claude Code, Codex, Cursor, Pi, and custom agents — swap harnesses without rewriting, enforce policies and sandboxing, and c+8
ArchonThe first open-source harness builder for AI coding. Make AI coding deterministic and repeatable.+3
paseoOrchestrate multiple coding agents from desktop and mobile+3
repomindAn open-source, AI-powered application using Agentic CAG to chat with any public GitHub repository or developer profile, offering deep code analysis, visual architecture maps and security audits+1
tabbySelf-hosted AI coding assistant+1
atomicThe verifiable coding agent runtime. Define your coding agent's process in natural language with stages, checks, and approval gates instead of hoping it follows your instructions.
code-graph-ragThe ultimate RAG for your monorepo. Query, understand, and edit multi-language codebases with the power of AI and knowledge graphs
gptmeYour agent in your terminal, equipped with local tools: writes code, uses the terminal, browses the web. Make your own persistent autonomous agent on top!
impeccableThe design language that makes your AI harness better at design.
kandevAI Kanban & Development Environment. Orchestrate multiple agents, review changes, open PRs. Multi-provider, self-hostable, no telemetry.
agentic_coding_flywheel_setupBootstraps a fresh Ubuntu VPS into a complete multi-agent AI development environment in 30 minutes: coding agents, session management, safety tools, and coordination infrastructure
oh-my-openagentOmO: Just type "mass ulw" keyword with your prompt. Now you are the master of graph engineering.
MiMo-CodeMiMo Code: Where Models and Agents Co-Evolve+21
aider-deskPlatform for AI-powered software engineers+12
costrictCostrict - strict AI coder for enterprises, quality first, including AI Agent, AI CodeReview, AI Completion. +10
WegentPlan, build, and deliver with an open-source, self-hostable AI workspace for coding, collaboration, and automation.+9
packmindPackmind seamlessly captures your engineering playbook and turns it into AI context, guardrails, and governance.+8
ai-dev-kitDatabricks Toolkit for Coding Agents provided by Field Engineering+3
gsd-2A powerful meta-prompting, context engineering and spec-driven development system that enables agents to work for long periods of time autonomously without losing track of the big picture+3
kiteco-publicPrimary Kite repo — private bits replaced with XXXXXXX+3
agent-orchestratorRun and supervise teams of coding agents from planning to merge. Any harness (Claude code, codex, +25 more). Desktop, web, mobile, and cloud agents.+1
sandboxCode editing environment with an AI copilot and real-time collaboration+1
DeepCode"DeepCode: Open Agentic Coding (Agent Harness & Loop Engineering & Multi-Agent Orchestration)"
neovate-codeNeovate Code is a code agent to enhance your development. You can use it to generate code, fix bugs, review code, add tests, and more. You can run it in interactive mode or headless mode.
qwen-codeAn open-source AI coding agent that lives in your terminal.
specweaveSpec-first AI development: describe a feature → AI creates spec + plan + tasks, builds autonomously, syncs to GitHub/JIRA. Domain-expert skills for PM, Architect, Frontend, QA learn your patterns perm
prime-agentA self-improving RLM agent for coding workflows and long-running autonomous tasks.
swarm-ide为 Agent Swarm 打造的 IDE ,支持 Kimi-2.5, GLM-4.7 等(即使不像 K2.5 那样经过强化学习的模型也能用)An IDE built for Agent Swarms, supporting Kimi-2.5, GLM-4.7, and more (compatible with models even without RL-reinforcement like
vibe-toolsGive Cursor Agent an AI Team and Advanced Skills
piAI agent toolkit: unified LLM API, agent loop, TUI, coding agent CLI
sudocodeLightweight agent orchestration dev tool that lives in your repo
advpl-specialistPlugin para Claude Code especializado em ADVPL e TLPP para desenvolvimento TOTVS Protheus
ask-bonkBonk is a code & docs agent that can build, review and triage for you, built on Cloudflare Workers & OpenCode.
codegCollaborative multi-agent AI coding workspace: aggregate sessions from Claude Code, Codex, OpenCode, Pi, Grok Build, etc. Desktop app, self-hosted server, or Docker.
gstackUse Garry Tan's exact Claude Code setup: 23 opinionated tools that serve as CEO, Designer, Eng Manager, Release Manager, Doc Engineer, and QA
OpenCodeInterpreterOpenCodeInterpreter is a suite of open-source code generation systems aimed at bridging the gap between large language models and sophisticated proprietary systems like the GPT-4 Code Interpreter. It
pi-webWeb UI for the pi coding agent