Browse & Compare AI Tools

aider (Paul-Gauthier Aider-AI Apache-2.0 Apr-2023 active-2026-09 not-shut-down no-acquisition 48k-stars 6.8M-installs 15B-tok-wk v0.86.2-Feb-2026 maintenance-slowed-not-archived MCP-roadmap-unshipped) = terminal-native-git-aware-AI-pair-programmer BYOK-not-autonomous-not-IDE-plugin: chat-SEARCH-REPLACE-apply-lint-test-auto-commit /undo-reverts-commit repo-map-tree-sitter architect-mode-planner+editor-split /add-explicit /web-url-to-markdown image-voice-whisper 100plus-LLMs-Claude-Sonnet-Opus4 GPT-4o-o1-o3mini-GPT-5 DeepSeek-R1-V3-V4Flash Gemini-1.5-2.5Pro Qwen Ollama-LM-Studio-LiteLLM vim-emacs-Helix-Zed-VSCode-JB-sidepane SSH-tmux-Docker no-tab-complete no-GUI no-MCP no-browser-tool; CLI $0 Apache-2.0 LLM-BYO $0-local-or-5-50-mo typical no-paid-tier; category ai-productivity-data pipeline_stage none; competitors Claude-Code OpenAI-Codex-CLI Gemini-CLI-Qwen-Code Continue Cline-Roo Cursor Windsurf GitHub-Copilot JetBrains-AI Devin Factory; not-ElevenLabs-AIVA-PixVerse-Synthesia-Voicemod-overlap.

aiXcoder is an AI coding assistant delivered as an IDE plugin, with a strong focus on enterprise private and offline deployment — code completion, generation, and search across Jav. Best for: enterprise dev teams needing code-data sovereignty.

Amazon Q Developer is in sunset — not shut down yet, but AWS closed new signups 2026-05-15 and will end support for IDE plugins + paid subscriptions on 2027-04-30 (successor = Kiro). Per your rule ("if closed, warn and do not output intro"), I warn: not outputting full English introduction body, but giving the rest in table form with status flag upfront.

Scraping and automation marketplace — turns messy web data into clean datasets for AI.

Baidu Comate (文心快码) is an AI coding assistant from Baidu that suggests code, explains functions, and automates routine development tasks inside popular IDEs. Best for: Chinese-market developers and enterprises wanting an in-ecosystem coding copilot.

Bito is an AI assistant for software teams that combines in-IDE code completion with automated code review, PR summaries, and test generation. Best for: dev teams wanting AI code review and faster PRs.

Bloop is a semantic code-search tool that lets developers ask natural-language questions and find relevant code across a repository using embeddings. Best for: engineers navigating large or unfamiliar codebases.

Bolt.new = StackBlitz's browser-native AI app builder that turns a natural-language prompt into a running full-stack web app (React/Next/Vue/Svelte/Vite/Express + Tailwind/Shadcn/MUI) by generating the files, npm-installing, booting a dev server, and live-previewing entirely inside one browser tab via WebContainers — then one-click deploying to Bolt Cloud/Netlify with built-in databases, auth, custom domains, SEO. Token-metered: Free 300K/day + 1M/mo (watermark, no rollover), Pro $25/mo ($18 ann) 10M/mo no daily cap + rollover 1 cycle, Teams $30/seat/mo ($27 ann) same 10M/seat + centralized billing/private NPM/design-system prompts, Enterprise custom (SSO/SAML/audit/BYOK). Agentic loop: on build error the agent reads the stack and self-heals before you ask. It is the "prompt→running app" bench, not a media tool (Veo/HeyGen), not a DB AI layer (Airtable AI), not a text-repurpose tool (Lumen5/Pictory/Opus).

Braintrust (Braintrust Data, Inc.) is active (not shut down). SF, founded 2023 by Ankur Goyal (ex-Impira), Series B 80MledbyICONIQFeb2026(800M val, $124M total). AI-native evals + observability for LLM apps/agents. No acquisition, no sunset. Category ai-productivity-data, pipeline_stage=none. File under Dev (LLM-eval/observability sublane). This is a re-run of your prior Braintrust turn with verified 2026-09 figures.

CiCrew

#270 Paid from $20/mo

Developer Tools

CiCrew is an AI-powered, no-code mobile app builder that lets founders describe an app idea in natural language and get back branded screen designs, a working Expo/React Native codebase, automated tests, security checks, an app landing page, analytics, and App Store publishing support. Higher plans add ad-copy generation, campaign planning, and dev/advertising advisors. Store accounts, external services, and ad spend are billed separately. It is best understood as a “prompt-to-launched-app” platform rather than a creative-video suite.

Claude Code = Anthropic's terminal/CLI agentic coding agent that authenticates with a Claude Pro/Max/Team/Enterprise account or an Anthropic API key, then reads your local repo, edits across files, runs bash/tests/git

Cline — Open-Source Human-in-the-Loop Coding Agent for VS Code, CLI, JetBrains & SDK (BYOK, Plan/Act, MCP-Native)

Edge serverless runtime for running small AI proxy, auth and webhook functions globally.

CodeAssist is a free AI coding-assistant plugin for JetBrains IDEs (IntelliJ, PyCharm, and the rest of the family) built by Exafunction. Best for: developers who want free in-editor AI help without a subscription.

CodeFuse is Ant Group's open-source AI coding toolkit — a family of code models plus an IDE plugin for completion, translation, and test generation. Best for: Chinese/finance teams and developers who want an open, self-hostable coding assistant.

CodeGeeX is an open-source AI coding assistant from Zhipu AI and Tsinghua's THUDM lab, available as a free plugin for VS Code and the full JetBrains family. Best for: developers who want a permanently free, self-hostable coding assistant with strong translation.

Codeium launched in 2021 in Mountain View (originally Exafunction; founders Varun Mohan + Douglas Chen). It became the default "free unlimited Tab autocomplete" rival to GitHub Copilot, then shipped the Windsurf Editor (Nov 2024, VS Code fork with the Cascade agent), renamed the company Windsurf (Apr 2025), saw Google hire away the founding team via a $2.4B licensing deal (Jul 2025), was acquired by Cognition AI (Devin) for the remainder (~$250M, Jul 2025), and on June 2, 2026 the flagship editor was renamed Devin Desktop — codeium.com now redirects to devin.ai.

Qodo (formerly CodiumAI) is an AI code-review and test-generation platform that reviews pull requests for bugs, security issues, and style, and auto-writes unit tests that actually. Best for: engineering teams that want shift-left review and test coverage without a separate QA tool.

continue (continuedev-inc Apache-2.0 25k-stars active 2026-09 not-shut-down no-acquisition VS-Code-2.4M-installs JetBrains-Neovim-CLI) = open-source-model-agnostic-in-IDE-AI-assistant+agent BYOK-local-LLM not-standalone-editor not-bundled-model: chat-@codebase-@files-@docs-@terminal-@web autocomplete-model-separate Edit-highlight-diff Agent-plan-edit-terminal-verify background-PR-review-doc-draft MCP-stdio-SSE-http-config-yaml rules-PR-security-Docker-Rust-React-Pandas Ollama-LM-Studio-llama-cpp-vLLM-airgap VS-Code JetBrains-IntelliJ-PyCharm-WebStorm-GoLand Rider Neovim CLI Continue-Hub-Team-central-config-secret-mgmt-allowed-models-MCP SSO-Enterprise; Core $0 Apache-2.0 pay-LLM-vendor-or-0-local Hub-Starter-usage-3per-Mtok Hub-Team $20-seat-mo-10-credit-incl Enterprise-custom; starting_price=$0; category ai-productivity-data pipeline_stage none; competitors Cursor GitHub-Copilot Cline-Roo-Code Tabnine Sourcegraph-Cody Amazon-Q-Developer JetBrains-AI-Assistant; not-ElevenLabs-AIVA-PixVerse-Synthesia-Voicemod-overlap.

Cursor (San Francisco, 2022; Anysphere — Michael Truell, Sualeh Asif, Arvid Lunnemark, Aman Sanger; valued ~$60B mid-2026) = the AI-native VS Code fork that made agentic coding mainstream — Tab autocomplete (Sub-100ms, multi-line) + Composer (multi-file diff plan) + Agent mode (explore→plan→run tests→fix lint) + Cloud/Background agents (up to 8 parallel in 2.0) + Bugbot PR review + MCP/skills/hooks + bring-your-own-key, routing across GPT-5.4 / Claude Opus 4.6 / Gemini 3 Pro / Grok Code / Composer 2.5. Not GitHub Copilot (plugin, cheaper, shallower), not Claude Code (terminal-first, no IDE), not Windsurf (SWE-1.5 only, same price), not JetBrains AI (different editor family). Your 38th CPT card, fits ai-productivity-data; pipeline_stage none (spans code-generation + refactor + agent-execution + pr-review). Table-first, Claude Code skeleton. The 2026 trap: June-2025 credit-meter reprice — $20 Pro includes ~$20 of frontier-model API usage, Auto mode unlimited but manual frontier picks burn credits, heavy agent users report $40–100/mo effective spend.

DALL·E 3 (OpenAI, San Francisco 2015-founded parent; model shipped Oct 2023, API Nov 2023) = the prompt-faithful text-to-image model that lives inside ChatGPT — natural-language prompting + conversational inpainting/outpainting + legible in-image text + C2PA provenance, no standalone app. Not Midjourney (artistic interpretation), not Flux (photoreal king/open-weight), not Ideogram (text-in-image specialist), not Adobe Firefly (license-safe training). Your 39th CPT card, fits ai-productivity-data; pipeline_stage none (spans text-to-image + conversational-edit + api-image-batch). Table-first, Claude Code skeleton. The 2026 trap: DALL·E 3 removed from OpenAI Images API on 2026-05-12 — new API projects get GPT Image 1, not DALL·E 3; existing integrations grandfathered. Encode that sunset as the headline gotcha.

DeepCode was an AI static-analysis engine that found bugs and security issues in source code across many languages. Best for: teams that wanted fast AI-assisted bug and security scanning in the IDE.

DevChat is an open-source AI pair-programming plugin for VS Code, JetBrains, and Neovim that wraps multiple LLM backends (OpenAI, Claude, local models, and others) and adds a "Chat. Best for: developers who want a model-agnostic coding assistant they control.

Devin (Cognition, SF, Aug 2023; Scott Wu + Steven Hao + Walden Yan; $1B+ raised @ $26B post-money May 2026; acquired Windsurf Jun 2026 → rebranded Devin Desktop) = the cloud-sandboxed autonomous AI software engineer that takes a whole ticket to a merged PR — plan → clone repo → write code → run tests → self-debug CI → open PR → respond to review comments, driven from Slack/GitHub/Linear/Jira, not inside your editor. Not Cursor (AI IDE, interactive), not Claude Code (terminal agent, steerable), not GitHub Copilot (autocomplete+agent plugin), not Factory AI (same autonomous lane, $100 Plus middle tier). fits ai-productivity-data; pipeline_stage none (spans code-generation + refactor + test-gen + migration + pr-review-respond). Table-first, Claude Code skeleton. The 2026 trap: April-2026 reprice killed the old $500 Team + ACU-meter — new self-serve is Free/Pro $20/Max $200/Teams $80+multi-seat, but overage bills in dollars at model API rates, not ACUs; legacy ACU ($2.25/≈15min) still lingers in Enterprise contracts and stale aggregator pages. That's the line to encode.

Documatic is an AI tool that reads your codebase and answers questions about it in plain language, while also generating and maintaining documentation and a searchable knowledge ba. Best for: teams onboarding engineers onto complex or legacy code.

Ellipsis is a GitHub App (from YC's W24 batch) that reviews every pull request for bugs, style, and security issues, and — unlike most review tools — can generate a working fix or. Best for: engineering teams wanting review plus auto-fixes inside GitHub.

Design-to-site builder with AI layout and copy generation, then one-click publishing.

Gemini Code Assist = Google Cloud-bound, IDE + terminal + PR tri-surface AI coding assistant on Gemini 3 / 2.5 Pro with a 1M-token context window, extensions for VS Code + JetBrains + Android Studio + Cloud Workstations, open-source Gemini CLI terminal agent, Agent Mode (Preview, multi-file + MCP + human-in-the-loop), automated GitHub PR review, and native hooks into Firebase / BigQuery / Cloud Run / Apigee. Not GitHub Copilot (GitHub-ecosystem plugin), not Cursor (AI-native editor), not Claude Code (autonomous terminal agent), not Amazon Q (AWS-bound). Fits ai-productivity-data; pipeline_stage none. 2026 traps: free individual tier dead (solo devs start at $19/mo or flee to Antigravity), Agent Mode still Preview with per-step approval, 5–10s latency vs Copilot, no native Neovim/Emacs extension, consumer GitHub bot not replaced 1:1.

CI/CD automation that runs tests, builds and deploys on every push.

Copilot = GitHub-native AI engineering layer: type → inline completion + Next Edit Suggestions (unlimited, zero credits) → Chat in IDE/GitHub/CLI → Agent Mode plans+makes+tests across files → assign a GitHub issue to Copilot cloud agent, it opens a self-reviewed PR → PR diff gets inline review comments (bugs/edge-cases/security) → model picker swaps GPT-5.6 ↔ Claude Opus 4.8 ↔ Gemini 3.7 Flash ↔ Grok 4.6 per task → Spaces ground org context → MCP + third-party agents (Claude Code, Codex) on Pro+. Fits ai-productivity-data; pipeline_stage none (type→complete→chat→agent→review→merge). For teams already on GitHub+VS Code/JetBrains who want one governed seat, it's the lowest-friction default; for agent-maximalists on complex multi-repo refactors, Cursor+Claude Code edge out.

Programmatic Gmail access for auto-classifying, drafting and routing inbound email.

JetBrains AI Assistant is active (not shut down). JetBrains s.r.o., Prague, AI Assistant launched 2023, major revamp 2025.1 (free tier + Junie bundled). No acquisition, no sunset. Category ai-productivity-data, pipeline_stage=none. File under Dev.

Open-source VS Code AI coding extension (MIT) offering autocomplete, chat and agentic edit/apply flows; built by a European team and acquired by Anaconda in 2026. Best for: VS Code developers who want a free, MIT-licensed coding agent with optional managed 'Kilo Pass' credits and team controls via a known data-science vendor.

Letta — Memory-Native Stateful Agent Runtime with Tiered Self-Managing Memory (Core / Recall / Archival + Letta Code)

Lovable = the AI software engineer for web apps: type "CRM with login, Kanban, team roles, Stripe billing" → Plan Mode drafts screens/data models/flows → approve → Default Mode generates React+TS pages, wires Supabase tables/RLS/auth (Google/GitHub/email), Tailwind+shadcn UI, edge functions → visual editor click-to-edit elements → chat to iterate ("remove footer" 0.9 cr, "add dark mode" ~1 cr) → GitHub sync pushes repo you own, or clone to Cursor → one-click deploy on *.lovable.app or custom domain → built-in AI features (chatbot/Q&A/translate) run via Lovable AI gateway → Business adds SSO/team workspace/internal publish, Enterprise adds SCIM/audit/custom connectors. Fits ai-productivity-data; pipeline_stage none (prompt→plan→generate→iterate→deploy→run). For founders/freelancers/designers shipping a real CRUD app Tuesday, Pro $25 is fastest; for deep backend/complex domain logic/native mobile, pair with Cursor or hire.

Mintlify — AI-Native Documentation Platform with MCP Server, llms.txt & Self-Updating Doc Agents