Free
$0/mo
30 credits/mo
An AI app builder that turns natural-language prompts into full-stack web applications. Agent Mode handles autonomous building and debugging; Visual Edits cover credit-free tweaks; Lovable Cloud provides native hosting, Postgres, and auth, while every project syncs to GitHub for full code ownership.
+Pros
- Full-stack app generation from a single natural-language prompt
- Agent Mode handles autonomous building, debugging, and web search
- Lovable Cloud provides native hosting, Postgres, auth, and storage
- GitHub sync ensures full code ownership with no vendor lock-in
- 8 million users — largest vibe coding platform by 2026
−Cons
- Credit-based model can be costly for heavy iterative use
- Generated code quality can vary on complex business logic
- Less control than code-first tools like Bolt or Cursor for experienced developers
- Primarily React-based — limited support for other frontend frameworks
Pricing
Pro
$25/mo
More credits, Agent Mode
Business
$50/mo
Branded URLs, advanced features
Enterprise
Custom
SSO, RBAC, audit features
Lovable (formerly GPT Engineer) is an AI app builder that turns natural-language prompts into full-stack web applications. By 2026 it had grown into one of the largest "vibe coding" platforms with around 8 million users, putting it among the leaders in AI-driven app creation for non-developers and product teams.
Lovable combines three modes: Agent Mode for autonomous building, exploration, and debugging; Chat for guided iteration; and Visual Edits / Manual Edit for credit-free tweaks to text, layout, and styling. The default model is Gemini 3 Flash, with optional access to GPT-5.5 Pro, GPT-5.4 Pro, Gemini 3.1 Pro, and image models. Lovable Cloud (launched mid-2025) provides native hosting, a Postgres database, authentication, and storage, while every project syncs to GitHub for full code ownership.
Key Features
• Prompt-to-app: full-stack web apps from natural-language descriptions
• Agent Mode: autonomous codebase exploration, debugging, and web search
• Visual Edits: no-credit edits for text, colors, and layout
• Multi-model: Gemini 3 Flash, GPT-5.5 / 5.4 Pro, Gemini 3.1 Pro, plus image models
• Lovable Cloud: hosting, Postgres database, auth, storage — or BYO Supabase
• GitHub sync: code ownership from day one, no lock-in
• Credit-based pricing with monthly rollover
• Enterprise: SSO, RBAC, data opt-out, audit features
Version History
Workspace owners can now delete a workspace directly from Settings. Project toolbar gets improved view switcher and clearer active states.
Custom MCP servers are now available on all plans (Free included). Group member pages and CSV exports now exclude deactivated users.
Lovable Cloud database health check lets you troubleshoot DB issues on-demand from chat. Auto-compress large images on upload.
Branded app URLs for Business/Enterprise. New app connectors: Google Maps Platform, Semrush, TikTok. Gemini 3.5 Flash added.
SEO & AI search tab with on-demand audits, Semrush-powered SEO research, Google Search Console integration. Telegram bot. Lovable MCP server.
Signature Snippet
Prompt Lovable: "Build a client portal with user login, a dashboard showing project status, and a messaging feature." Agent Mode scaffolds the React app, provisions auth and a Postgres database in Lovable Cloud, wires up the messaging UI, and gives you a live URL plus a synced GitHub repo.More in this Space
Prime Agent (Prime Intellect)
Prime Agent is an open-source (MIT) self-improving coding and research harness by Prime Intellect, built on a Recursive Language Model that runs inside a persistent IPython REPL and a Continual Harness that refines its own state via /refine. It took the same frontier weights from 30.2% to 95.5% on ARC-AGI-3 RHAE Best@1, powered daemon-backed sessions, and ships no hosted offering.
OpenCodeReview (ocr)
OpenCodeReview (ocr) is Alibaba's open-source AI code-review CLI. It reads git diffs and drives an LLM agent through a hybrid architecture where deterministic pipelines handle file selection, rule matching, and comment positioning while the agent does the reasoning. Built on two years of internal use at Alibaba scale, it ships a multi-language ruleset and consumes roughly 1/9 of the tokens of general-purpose agents.
Delta (by Zed)
Multiplayer environment from Zed for coding with agents. Threads unify the agent conversation, the code edits, and human review in one shareable artifact, replacing the branch/PR loop. Built on DeltaDB, a CRDT-based version control layer that records every edit between commits alongside the prompts and reasoning that produced them.