Developer Tools

GitHub Copilot

GitHub's official AI coding assistant spans editors, the terminal, desktop, and the GitHub website, supporting the full workflow from issues and code generation to PR review and merge, with multiple model and agent controls.

Lovable

A low-code AI platform that turns ideas into deployable full-stack applications using natural language. It covers conversational generation, hosting, payment integration, and security, enabling you to go from prototype to launch without extensive coding experience.

Cursor

AI-native coding agent that plans and executes multi-step changes in parallel, with multi-model support and cross-repo context. Available as desktop app and CLI.

OpenAI Codex

OpenAI's Capabilities for Code Scenarios and Entry to Development Documentation. Developers can create API Keys, install SDKs to make their first successful calls, and learn about agent construction and multimodal model selection from here.

Base44

Base44 is a no-code AI development platform that turns ideas into functional applications and websites using natural language. It comes with built-in backends, storage, databases, payment processing and hosting, requiring no coding. It is ideal for entrepreneurs and teams to quickly build full-stack products.

OpenCode

OpenCode is an open-source AI programming agent that can write code in terminals, IDEs and desktop clients. It supports LSP, multi-session parallelism and 75+ models, and prioritizes privacy without storing code.

Replit

Replit is a cloud-based IDE and AI application building platform. In the browser, use Replit Agent to generate and deploy full-stack applications conversationally, with built-in authentication, databases, hosting, and integrations, suitable for going from prototype to production.

Emergent

Emergent is an AI application building platform from YC S24. It uses natural language conversations to let multiple AI agents complete design, coding, testing and deployment, generating full-stack Web/mobile applications that you can own, and is suitable for quickly going from an idea to launch.

n8n

An open-source workflow automation platform that integrates AI capabilities with business processes. It features a visual canvas for building while retaining code editing space, with full traceability of Agent reasoning on the canvas. It supports over 500 integrations and can be self-hosted for deployment.

Bolt.new

Bolt.new is an AI building tool for generating applications and websites through conversation. It automatically selects models and provides real-time previews. With built-in databases, authentication, hosting, and SEO features, it claims to handle large-scale projects while automatically testing and fixing errors. It is suitable for the rapid launch of products, startups, and marketing campaigns.

Groq

Groq's in-house LPU chip-powered inference cloud runs open-source models such as Llama and Mixtral with ultra-low latency. It has a low migration cost for OpenAI-compatible APIs, and the company claims it processes trillions of tokens per week.

CodeBuddy

Tencent Cloud has launched an AI full-process intelligent programming tool, which the official says is available in three forms: IDE, editor plug-ins and CLI. Based on conversational large models such as Hunyuan, it covers demand analysis, design draft to code conversion, code completion and one-click deployment.

v0

An AI building platform launched by Vercel, which can directly generate production-ready full-stack Web applications with prompts, supports design mode fine-tuning, repository synchronization and one-click deployment, and also enables creation and publishing on mobile devices.

LangChain

An open-source agent engineering platform for building LLM applications. With LangSmith Engine, it covers development, testing, deployment, and monitoring across the full lifecycle while keeping model, context, and execution-framework choices open.

TraeCode

The AI programming IDE under ByteDance's TRAE offers, according to the official statement, a dual development mode of IDE and SOLO. It has a built-in Coding Agent that can take over tasks and schedule tools, and supports custom agents and MCP.

Devin

Devin is an autonomous AI software engineer launched by Cognition. It handles cross-repository engineering tasks in parallel on the cloud: PR review and visual QA, code migration and refactoring, issue triage, document generation, and it can also learn your codebase.

Windsurf

The original Windsurf AI editor has now been integrated into Cognition's Devin system. The official website directs to Devin Desktop, where multiple coding agents on local and cloud can be scheduled on a unified interface.

Coze is an all-in-one AI development platform under ByteDance. You can build intelligent agents and visual workflows without complex instructions, and deliver results directly on computers and mobile phones, covering scenarios such as PPT creation, data analysis, mini-program and web page development.

Zed

Zed is a high-performance multi-person code editor created by the authors of Atom and Tree-sitter. Written in Rust, it supports parallel editing with AI agents and in-line assistants, enables real-time collaboration for teams, and is ideal for developers who value speed and collaboration.

Model Context Protocol

MCP is an open-source standard promoted by Anthropic that enables AI applications such as Claude and ChatGPT to connect data sources, tools, and workflows in a unified manner. A single set of interfaces opens up the external world, and ecological support is becoming increasingly extensive.

Together AI

Together AI is an AI-native cloud platform that provides open-source model inference, fine-tuning and GPU clusters. It features easy migration with OpenAI-compatible interfaces, and the company claims it offers 2x faster inference, 60% lower costs and 90% faster pre-training.

Dify

Dify is an open-source LLM application development platform for production-grade Agentic workflows. It enables the building of Agents, knowledge pipelines (RAG) and workflows on a unified canvas, and supports cloud, VPC or self-hosted deployment.

Comate

Wenxin Kuaima Comate is a programming tool developed by Baidu based on the Wenxin large model. It supports code completion, unit testing, commenting and intelligent Q&A, provides multi-agent scheduling and multi-file editing, and can be integrated with IDEs such as VS Code and JetBrains.

Kane CLI

Kane CLI is a command-line testing tool for developers. You can describe test cases in natural language to execute them on browsers and mobile devices. Its official website states that it will provide pass/fail conclusions and shareable execution evidence. New users can get a free quota.

Langfuse

An open-source (MIT) LLM engineering platform that integrates tracing, evaluation, prompt management and datasets in one place. Based on OpenTelemetry, it continuously improves AI applications with production data and is self-hostable.

Jishi Design

A professional online UI design tool for domestic designers, supporting real-time multi-person collaboration, prototyping and interaction, resource management and development annotation, compatible with Figma, Sketch, and XD file formats. It can be used directly in a browser and is permanently free.

Uizard

An AI UI design tool for product teams that can generate interface prototypes for apps, websites and desktop software using natural language and screenshots. Its official website claims it is as simple as using PowerPoint, making it ideal for quickly validating product ideas.

T3 Code

T3 Code is an open-source control plane for coding agents that schedules multiple mainstream coding agents in a single interface. According to its official website, it comes with built-in subscriptions, enabling one-click commit, push and PR creation, and is available on both desktop and mobile platforms.

tabnine

An enterprise-level AI code assistant focusing on code privacy and compliance, offering completion and agent capabilities. It can be deployed controllably in the enterprise's own environment through an enterprise context engine and has been acquired by Tricentis.

Abliteration

Abliteration is a large model interface for high-risk scenarios. Its official website states that it is compatible with the message formats of two mainstream manufacturers and can be directly replaced. It supports batch generation of training data and declares that it does not store prompt words and is not used for training.

LlamaIndex

An AI data framework centered on document intelligence, its flagship capability LlamaParse uses agent-style OCR to parse documents with complex tables and charts into structured context usable by AI.

Continue

Open-source AI code assistant project, focusing on integrating any model for custom completion and conversation; the team has been acquired by Cursor, and the open-source code repository is still freely available for self-deployment and modification.

Pixso

A domestic AI collaborative design tool that integrates whiteboarding, prototyping, UI design and delivery in one. Its official website states that it supports AI one-click generation of UI design drafts and React/Vue code, connects the entire design-to-development pipeline, and can import Figma files.

aider

An AI pair programming tool that runs in the terminal, automatically maps codebases, supports over 100 languages and multi-model access, directly commits every change to Git, and is fully traceable throughout the process.

Portkey

A production-grade platform for generative AI that unifies access to multiple models via an AI gateway, equipped with observability, guardrails, governance and prompt management, and has now been renamed PRISMA AIRS AI Gateway.

Qodo

An AI platform for code review provides cross-repository context and more than 15 agent workflows, covers IDE, PR and security scenarios, and transforms team specifications into executable governance rules.

Helicone AI

Helicone is an open-source LLM observability and AI gateway platform: request logs, monitoring alerts, policy routing, multi-dimensional segmentation and HQL analysis, access with one line of base_url modification, used by the fastest-growing AI companies.

Qoder CN

The AI programming intelligent agent launched by Alibaba Cloud (formerly known as "Tongyi Lingma", officially renamed in May 2026) is officially said to provide capabilities such as intelligent code generation, intelligent R&D Q&A, multi-file modification, and programming intelligent agents, and supports free switching of various domestic large models.

Nutrient Data Extraction API

Nutrient's cloud document extraction interface parses PDF, scanned documents, images and Office files into spatial JSON or Markdown with coordinates, confidence and page number context. It can also extract by field name with reference sources. The official website states that the free quota is 5,000 credits per month.

Haystack

An open-source AI orchestration framework maintained by deepset, which builds production-ready agents, retrieval-augmented and semantic search systems with modular components, where every step can be inspected, debugged and replaced.

Clipy

Clipy is a screen recording tool for coding agents. Record a defect reproduction or interface feedback once. Humans watch the video, while Claude Code, Codex and Cursor read the summary, transcription, clicks and key frames. The official website says it starts for free, and viewers don't need to register.

Monid

Monid is a platform that enables AI agents to invoke web data endpoints on demand. According to its official website, the catalog features 2,897 tools from 92 vendors, covering categories such as social media, leads, search, e-commerce, and crypto. It charges based on usage with no subscriptions or contracts required, and can be integrated via MCP, Skill, CLI, or HTTP API.

BetterClaw

BetterClaw is a no-code AI agent building platform for teams. The official claims that the first Agent can be launched in 60 seconds. It supports 120+ connectors and built-in model keys, and executes tasks on schedule through channels such as Slack and Telegram.

HyperFrames Studio

HyperFrames Studio is a desktop video editor for AI agents. According to its official website, it renders HTML, CSS and addressable animations into MP4. It supports macOS, Windows and Linux, and is developed by the team behind the open-source project HyperFrames.

Sim

Sim is an open-source AI workspace where enterprises build, distribute and govern AI agents. Its official website states that it supports 270+ integrations and mainstream large models, can be orchestrated with canvases, dialogues or code, and provides permission groups, quota limits and self-hosting.

Inference.net

Inference infrastructure for AI-native teams, enabling the deployment and monitoring of open-source, self-trained, and fine-tuned models. The official website lists full provider production monitoring, 99.99% available model deployment, minute-level fine-tuning, and cost and quality evaluation based on production traces.

Jet Admin

A business application development platform built on existing data sources: its official website states that it can integrate with over 200 data sources including Postgres, MySQL, MongoDB, Supabase, and Airtable. It automatically generates backends and APIs, and comes with built-in SSO, role-based access control, and audit logs.

We0

An AI programming platform for large-scale projects. According to its official website, it can generate deployable systems with payment, login and backend functions, and can also build official websites and customer acquisition tools. Describe requirements in natural language to get real-time previews, make visual adjustments, and deploy to your domain with one click. The payment link supports integration with WeChat Pay, Stripe and PayPal.

AnySearch

Privacy-first search infrastructure for AI agents. According to the official website, it offers anonymous access, no tracking, zero telemetry, and no log retention, along with zero-retention execution. It features a unified entry point to access multi-domain data sources, intelligently routes queries based on intent, outputs structured Markdown, and supports three integration methods: API, MCP, and Skill.

Diffusion Studio

Diffusion Studio official website positions itself as a professional video editor for coding agents: Claude Code, Codex, Cursor, etc. can analyze materials, clip segments, transcribe and generate media. Every modification is written into the real codebase, supporting both browser and desktop usage.

OpenWorker is an open-source AI agent that runs on your own computer. According to its official website, you just need to state the desired outcome, and it will complete tasks in daily tools such as files, code repositories, Slack, and calendars, delivering code reviews, cloud configuration checks, documentation, and session responses. It covers research and development, security, and daily office scenarios.

Scalebrowser

Scalebrowser equips each AI agent with an independent browser with a persistent identity. Its official website states that it can maintain logins, handle verification codes, and input data like humans, with credentials never leaving the local machine. It can be accessed via MCP, SDK, or CDP, covering scenarios such as social media, e-commerce, and business accounts.

Dograh

Dograh is a self-hostable open-source voice agent platform. According to its official website, it can carry its own models, be driven by MCP, deployed on your own servers or in the cloud, supports two link types: voice-to-voice and cascading, and covers voice automation scenarios for customer service, outbound notifications and regulated industries.

Linkly AI

Linkly AI is a local document full-text retrieval tool for AI Agents. Adding a folder automatically indexes PDF, DOCX, HTML, Markdown, EPUB, and image OCR content, and it can be integrated with any AI tool. The official website claims a 0.5-second response time, and all data remains on the local machine.

Bruin

Bruin is an open-source AI data platform. Its official website states that one platform can replace the combination of access tools, dbt, Airflow and BI: write pipelines with SQL and Python, equipped with quality checks and column-level lineage, and there is also an AI data analyst that can answer questions on channels such as Slack.

Mixpeek

Mixpeek is a multimodal retrieval platform for agents. According to its official website, it directly reads videos, images, audios and documents in object storage, extracts faces, scenes, voices and screen text, and then locates specific moments with a single hybrid query. It covers scenarios such as material retrieval, advertising creative clustering, content review and quality inspection.

Weave

Weave is an engineering metrics platform, and its official website states "AI to measure engineers and agents". It aggregates commits, pull requests and AI telemetry, combines developer feedback to locate delivery bottlenecks, and links token costs to output, covering the scenario of evaluating AI coding investment.

Retriever AI

Retriever AI is a free AI browser agent self-proclaimed on its official website. It offers two running methods: Chrome extension and cloud-based. It can work across open web pages and logged-in sites and return results; it supports connecting to Drive, Slack, and Notion, can record repetitive processes and then replay them, and is suitable for clue mining and form filling.

EUrouter

EUrouter is a unified AI interface tailored for European compliance scenarios. According to its official website, a single endpoint can connect to hundreds of models and intelligently route them based on price, quality, or latency. All requests are processed within the EU and are compliant with GDPR by default. It covers scenarios such as OpenAI-compatible migrations, key-based rate limiting, and real-time observability.

TrustedRouter

An AI routing gateway compatible with OpenAI; changing just one base_url allows access to hundreds of models. It can filter routes based on zero data retention and end-to-end encryption levels. The gateway's source code and deployment configuration are public with build proofs. When no route meets privacy requirements, requests fail directly instead of degrading. Billing is based on vendor costs.

Zof

Zof is an independent verification and control layer located between AI and production environments. According to its official website, after the changes generated by AI arrive, Zof first judges the possible scope of impact, then runs unit tests, security and compliance checks and leaves evidence, and finally decides to allow, block or transfer to manual approval through strategies. It covers scenarios such as output from coding agents, release review and audit forensics.

Zoah

Zoah is a full-stack software development platform, and its official website states that design, building and deployment can be completed in one place. The canvas is based on the real DOM, and what you draw is the production code; the Interfacer and Operators agents continuously improve the product, and the Operand framework is built into every application, covering scenarios from prototyping to large-scale operation.

Vendo

Vendo is an open-source custom layer that, according to its official website, enables each customer to automate work within your product, build their own views and connect tools, all within your brand and guardrails. After a customer describes their requirements, the product assembles a micro-app with actions, automation and status in real time, which the customer retains exclusively.

HarnessRouter

HarnessRouter integrates harnesses such as Codex, Claude Code, and Hermes into your product as runtime environments, allowing you to switch between harnesses and models with a single set of APIs. It configures isolated sandboxes for each task and provides Arena to compare the time consumption and costs of various combinations.

OpenTypeless

OpenTypeless is a free and open-source desktop AI voice input tool that supports Windows, macOS and Linux. Press the global shortcut key and speak, use the recognition service of your choice for real-time transcription, and then the AI can optionally polish the grammar; after enabling app awareness, you can turn dictation into emails, group chats or documents.

Osaurus

Osaurus is an open-source client for running AI agents natively. It works with local models like Raptor, is private by default and can run offline, offering a stable Mac version and a public beta version for Windows; the agent can read documents and notes in local folders, retain cross-session memory, and ask for confirmation before modifying files.

MeetStream

MeetStream is a meeting bot API for developers: integrate with Zoom, Google Meet and Teams with a single connection, enabling the bot to join meetings for recording, real-time streaming and transcription. It outputs independent audio tracks and speaker labels per participant, allowing you to build your own AI agents on top of this.

Corsair

Corsair is an open-source integration layer for AI products: it connects applications like Gmail, Slack, and Notion to agents via plugins, unifies the handling of OAuth, multi-tenant credentials and authorization pages, requires explicit approval for destructive operations, and can be either cloud-hosted or fully self-hosted.

Reflexio

Reflexio is a learning platform for AI agents: it collects the execution failures, user corrections and successful results of agents, refines them into executable rules and retrieves and injects them before the next execution, covering agents in customer service, coding, data analysis, recruitment and other fields.

puppyone

puppyone is a folder for AI agents: Over 40 agents such as Claude Code, Codex, and Cursor can read from and write to the same folder simultaneously. All changes are committed to Git, allowing you to view diffs and roll back. It is free by default locally and can also be hosted in the cloud for permanent use.

Oumi

Oumi is an AI factory as claimed on its official website: starting from a natural language description, it automatically runs evaluations, data synthesis, training and deployment to create your exclusive model. The official website states that it can improve accuracy by up to 50%, reduce costs by up to 90%, and launch the model in as fast as 2 hours.

boat

The official website states that Boat is a persistent Linux cloud sandbox for AI agents, offering SSH, Docker, virtual desktops, snapshot forking, and external agent calls. It charges by the second and does not count downtime, making it suitable for batch execution of coding, testing, and browser tasks.

Bloxks

According to the official website, Bloxks is a natural language-driven no-code mobile app building platform that can generate Android and iOS applications, integrate with APIs such as database and payment APIs, and assist in submitting to app stores. It is suitable for idea validation, independent development, and lightweight game development.

Zide

According to the official website, Zide is an intelligent agent desktop for developers, integrating code, Git, Issues, PRs, CI, terminals, and AI assistants into a native workspace. It supports multi-model access, repository-level modifications, Worktree, and cross-repository project management.

Mireye

Mireye is a physical world data infrastructure for AI agents. It provides cited data, plot enhancement, signals and computing capabilities through the same set of APIs and MCP tools, covering U.S. scenarios such as data center site selection, renewable energy site selection, insurance underwriting, mortgages and commercial credit.

BenchGen

BenchGen is an AI agent evaluation and training infrastructure. According to its official website, it runs multi-step tasks in digital twin environments, records complete decision trajectories and scores them step by step, and can convert operation results into training data, covering scenarios such as finance, national defense, energy, software development and research.

Watcher

Watcher is an AI agent monitoring and control tool launched by Apollo Research. According to its official website, it centrally issues strategies, conducts pre-execution checks and blocks out-of-bounds actions. It can also analyze events, connect to systems such as Splunk and Datadog, and support Claude Code and Codex.

Coldtea

Coldtea is a governance layer for AI-generated code. According to its official website, it integrates change understanding, regression testing and production observation into the same workflow, helping teams assess impacts before release and automatically fix issues when they occur.

Revolte

Revolte is an AI platform for software engineering as defined on its official website. It uses intelligent agents to connect development, testing, deployment, and production operations. Engineers define requirements and approve key results, while the platform records the execution process, enabling automated delivery to retain manual governance and traceable boundaries.

Autosana

Autosana is an end-to-end testing tool for iOS, Android and Web. It creates test cases in natural language. According to its official website, the AI agent will adjust the tests based on code differences and run them on cloud devices or browsers.

Antigma

Antigma is a terminal coding agent and agent runtime: a single command to install a single-file program, switch between cloud or local models in a session, built with Rust and with no external runtime dependencies.

OpenComputer

OpenComputer is a high-performance infrastructure for coding agents as described on the official website: the agents run on its cloud and can be mentioned in chat tools or called via APIs; the official website states that responses are returned in a streaming manner, the reading, writing and execution processes are visible, and interface changes come with screenshots and previews.

MySpec

MySpec is a specification generation tool for coding agents: it first clarifies the scope, user flows and boundary conditions through structured interviews, then produces four specification documents for coding agents to follow, and supports export and interface integration.

Harden AIF

Harden AIF is the security layer for coding agents: according to its official website, its local model makes judgments before the execution of supported intelligent agent tool calls, allowing, recording, desensitizing, correcting, or blocking dangerous actions, and retaining the local decision-making history.

easybits

According to its official website, easybits positions itself as an AI orchestration layer within applications: first, configure tasks such as classification, extraction, and summarization on the platform, and then the application sends a request to call them; prompts, models, and output structures are maintained on the platform, and the results are directly mapped to program types.

Native Soil

Native Soil is a workflow state handoff layer for AI projects: it saves decisions, constraints, current tasks, and next steps. After inspection, scoring, and desensitization, it generates a 17-section Markdown handoff that can be reloaded in other models and clients.

ditto

Ditto is an open-source deterministic website cloner: by entering a public URL, the official website states that you can get clean, componentized Next.js or Vite code within five minutes without relying on LLM guesses.

AlphaWeb

AlphaWeb is an e-commerce infrastructure for AI: agents generate pages, checkout flows, and funnels through conversation, while the platform handles hosting, payment routing, order data, and security controls, and can sync with existing stores.

Switch Trust

Switch Trust is a local-first Python command-line tool. According to its official website, it can scan security risks, misconfigurations, dangerous tool permissions and missing guardrails in the source code of intelligent agents, conduct adversarial evaluations such as prompt injection and jailbreaking on running intelligent agents, and output findings mapped to OWASP ASI as well as reliability scores.