Overview
Giselle is an open-source AI app builder that enables users to create and manage AI-powered workflows without programming expertise. Built with a visual node editor, it allows individuals and teams to design complex AI applications through an intuitive drag-and-drop interface. The platform supports integration with leading AI models from OpenAI, Anthropic, and Google, making it possible to combine multiple models within a single workflow for enhanced capabilities.
Giselle is designed for product teams, engineers, solopreneurs, and fast builders who want to automate repetitive tasks and accelerate development cycles. Its key value lies in eliminating infrastructure management while providing real-time monitoring and execution tracking for long-running AI tasks. The platform also offers GitHub integration for automated code reviews, documentation generation, and workflow triggers based on repository events.
As an open-source solution backed by ROUTE06's ISO/IEC 27001-certified infrastructure, Giselle emphasizes transparency and structured security practices, making it suitable for organizations seeking both flexibility and security standards in their AI operations.
Key Features
Visual Node Editor — Build AI workflows by connecting nodes through drag-and-drop actions, enabling complex process design without writing code, reducing development time from hours to minutes.
Multi-Model AI Collaboration — Integrate models from OpenAI, Anthropic, and Google in a single workflow, allowing agents to select optimal models for specific tasks and maximize output quality. Supported models vary by plan.
Long-Running Task Execution — Execute AI apps in a dedicated environment with real-time progress monitoring and clear output display, supporting workflows that require extended processing time without session interruptions. The platform runs apps separately from the build environment for reliable long-duration tasks.
GitHub Integration — Automate code reviews, issue classification, and documentation updates by triggering AI apps based on GitHub events like pull requests, issues, and comments, streamlining development workflows directly within your repository.
Custom Knowledge Store — Import organization-specific data from PDFs, documents, and GitHub repositories into AI workflows, enabling responses and insights based on proprietary information rather than generic training data.
Zero Infrastructure Setup — Deploy AI applications without managing servers, databases, or scaling configurations, allowing immediate workflow initiation through managed cloud deployment with automatic resource allocation.
Pricing & Plans
Giselle offers multiple deployment options with different pricing tiers:
| Plan | Price | AI Usage | Key Features | Best For |
|---|---|---|---|---|
| Open Source | Free (self-hosted) | Requires own API keys | Self-hosted deployment, full source code access, community support | Developers wanting full control and customization |
| Free | $0/month | 30 minutes per month | Limited AI models (Claude Haiku 4.5, Gemini 2.5 Flash Lite, GPT-5-nano), managed cloud deployment, single-user account | Solo developers exploring AI agents |
| Pro | $20/month | $20 credits included (additional usage at 10% markup on base token rates) | All premium AI models, 5 document vector stores, 3 GitHub vector stores, email support, single user | Individual power users building production apps |
| Team | $100/month | Coming soon | Pro features + 20 document vector stores, 10 GitHub vector stores, team collaboration, up to 10 users, priority email support | Teams collaborating on AI workflows |
Notes:
- On the Free plan, usage is capped by time (up to 30 minutes per month). On paid plans, AI usage is billed by tokens processed.
- Additional usage beyond included credits is charged at a 10% markup on each AI model's base token rate.
- Cloud-hosted plans (Free, Pro, Team) include managed deployment. The Open Source edition requires self-hosted infrastructure.
- Model availability and features are subject to change; refer to official documentation for current details.
Pros & Cons
Pros:
- No infrastructure management required, enabling immediate workflow creation without DevOps expertise.
- Visual interface provides clear workflow representation, reducing debugging complexity and making AI logic transparent.
- Open-source codebase allows self-hosting, customization, and community-driven feature development.
- Multi-provider support enables flexible model selection and cost optimization across different AI capabilities.
- Built on ISO/IEC 27001-certified infrastructure through ROUTE06, providing structured security practices with TLS encryption and secure cloud providers.
Cons:
- Workflow versioning and collaboration features are evolving; advanced capabilities like branching, diffs, and approval workflows may still be developing.
- Error handling and retry features are improving over time; production deployments may require custom fallback strategies and monitoring.
- Team collaboration features are under development, with limited shared editing and role-based access control in current releases.
Best For
- Product teams and engineers who need to compose multi-step AI workflows visually without managing cloud infrastructure or handling model API integrations directly.
- Solopreneurs and fast builders launching AI products rapidly, seeking to automate research, documentation, and code review tasks without hiring developers.
- Development teams using GitHub extensively, wanting to integrate AI-powered automation for pull request reviews, issue triage, and documentation updates.
- Organizations seeking structured security practices backed by ISO/IEC 27001-certified infrastructure, though specific regulated-industry compliance should be validated against individual requirements.
- Open-source contributors and technical users who want to customize or extend AI workflow capabilities beyond standard no-code platform limitations.
FAQ
Is there a free trial available?
Giselle offers a free plan with 30 minutes of AI model usage per month, providing full access to basic AI models and managed cloud deployment. This allows users to explore the platform's capabilities before upgrading to paid plans. No credit card is required to start with the Free plan.
What AI models does Giselle support?
Model availability varies by plan. The Free plan includes Claude Haiku 4.5, Gemini 2.5 Flash Lite, and GPT-5-nano. The Pro plan provides access to premium models including Claude Opus 4.5 and Sonnet 4.5, OpenAI models (GPT-5.2, GPT-5.1 Thinking, GPT-5.1 Codex, GPT-5, GPT-5 Mini), and Google models (Gemini 3 Pro Preview, Gemini 2.5 Pro, Gemini 2.5 Flash). Users can combine multiple models within a single workflow. Model availability may change; refer to the official AI Models documentation for the latest list.
Can I self-host Giselle?
Yes, Giselle is open-source and available on GitHub under the repository giselles-ai/giselle. Users can clone the repository, install dependencies using pnpm, and run the platform locally or deploy it to their own infrastructure. Self-hosting requires managing your own API keys for AI model providers.
How does pricing work for AI usage?
The Free plan caps usage at 30 minutes per month. The Pro plan includes $20 of AI credits per month, billed by tokens processed (input and output). Usage beyond included credits is charged at a 10% markup on each AI model's base token rate. Different models consume tokens at varying rates based on their complexity and context window sizes. Users can monitor usage through the platform dashboard.
Is my data secure and private?
Giselle is developed and operated by ROUTE06, Inc., which holds ISO/IEC 27001:2013 certification (IS 779274). Giselle inherits security practices under this framework, including TLS encryption for data in transit, strict access controls, and secure cloud infrastructure through AWS, Supabase, and Vercel. Data sent to third-party AI model providers is subject to each provider's data usage policy. Verify the latest terms with your chosen AI providers regarding training data usage.
Can I integrate Giselle with my GitHub repositories?
Yes, Giselle offers native GitHub integration that allows workflows to be triggered automatically by repository events such as issues, pull requests, and comments. This enables automated code reviews, documentation generation, issue classification, and other development workflow automations directly within your GitHub environment.
What programming knowledge is required?
Giselle requires no programming knowledge for basic workflow creation. The visual node editor uses drag-and-drop interactions to design AI processes. However, users familiar with AI concepts and API integrations may benefit from advanced features like custom knowledge integration and complex multi-model workflows.
Can I cancel my subscription anytime?
Subscription changes and cancellations are managed through your account settings in the Giselle platform. Users can typically downgrade from paid plans to the Free plan or cancel their subscription. For specific cancellation terms, refund policies, and billing details, refer to Giselle's Terms of Service and billing documentation or contact support directly.