Source
History of Lovable
A post about the evolution from GPT Engineer to a platform with a rating of $6.6B.
Lovable - an example of how an open-source project turns into a platform AI product. The company has gone from a CLI code generation utility to a full-stack AI builder, where the user controls development through a dialogue with an agent.
- Anton Osika - co-founder, engineering background in ML and physics (including CERN experience).
- Fabian Hedin is co-founder, serial entrepreneur and engineer.
Timeline
Open-source beginning
The project starts as GPT Engineer: a CLI tool that generates a code base one prompt at a time.
Transition to a commercial product
The team is developing the SaaS version, and at the end of 2024, consolidates the Lovable brand and focus on creating ready-made web applications.
Hypergrowth valuations
The company goes from an early round to Series B and reaches a valuation of $6.6B, attracting large strategic investors.
Platform stage
Focus on enterprise-governance, autonomous agents and infrastructure development around the full development cycle.
Rounds and business dynamics
Pre-Series A
February 2025
$15M
Lead: Creandum. Among the angels: Charlie Songhurst, Adam D'Angelo, Thomas Wolf.
Series A
July 2025
$200M at $1.8B valuation
Lead: Accel. Participants: 20VC, byFounders, Hummingbird, Visionaries Club.
Series B
December 2025
$330M at a valuation of $6.6B
Leads: CapitalG and Menlo Ventures. Strategic investors: NVentures, Salesforce Ventures, Databricks Ventures, Atlassian Ventures.
Related chapter
AI Engineering
Context about production practices and a systemic view of AI products.
Conceptual architecture
Product UX
- Chat-first interface: request on the left, live preview on the right.
- Iterative cycle: prompt, generation, verification, revision.
- Vibe coding approach: the user sets the intent, the platform does the implementation.
AI Orchestration
- The agent analyzes the task and builds a change plan.
- Changes are generated for front end, API, data and integrations.
- The platform applies the patches and moves on to the next iteration.
Runtime & Delivery
- The output stack typically includes React, TypeScript, and Tailwind.
- For the backend layer, integration with Supabase is often used.
- There is code export and git synchronization for full code ownership.
Agent workflow
- 1The user formulates the product goal and requirements.
- 2The system collects the project context: files, logs, restrictions.
- 3The LLM agent proposes a plan and generates changes to the code base.
- 4The project is being rebuilt, the result is immediately visible in the preview.
- 5Errors and new requirements are returned to the next iteration cycle.
What works well
- Significantly reduces the time-to-prototype for web products.
- Shifts value to the result, rather than to manually typing code.
- Suitable for both engineering and product roles.
- Retains the ability to develop the project outside the platform.
Where are restrictions needed?
- Quality depends on the clarity of the problem statement and prompts.
- Manual checks of security, architecture and cost control are needed.
- Enterprise scenarios require governance and a policy loop.
- Without observability, agent cycles are more difficult to diagnose.
Materials and references
Official website of Lovable
Product, demo and public materials of the team.
GPT Engineer (open source)
The original project from which the Lovable story began.
Platform architecture (part 1)
Stack, integrations and product conceptual diagram.
Agent workflow and infrastructure (part 2)
How the platform orchestrates code generation and the dev cycle.
Additionally: vibe coding UX patterns in the post book_cube/4246 and disassembly of internal components in book_cube/4253.
From adjacent chapters: Prompt Engineering And AI Engineering Interviews.