Gendora
An AI executor for every project. People stay in charge.
Submit a requirement and the project agent plans the work, writes a PRD and an interactive prototype, and checks them before they reach you. Nothing is done until a person approves it, and every deliverable keeps its versions, source and review history.
The problem
AI agents can produce a lot of work quickly, but teams struggle to trust it: it's hard to see what an agent is doing across several projects, why it made a decision, and whether the output was checked. Gendora puts every run, review and blocker in one place and keeps a person in charge of what gets approved.
- Status
- Public beta · free while in beta, no credit card needed
- Platforms
- Web · macOS app coming soon
What it does
Multi-project workbench
One inbox gathers the runs, reviews and blockers from every project in your workspace, so you always know what is waiting for you.
A persistent agent for each project
Every project gets its own agent with its own knowledge and deliverables. It understands a request, plans the steps and writes a PRD and an HTML prototype, in the language of your requirement.
Harness and learning
A harness packages the roles, workflow steps, rules, skills and templates the agent follows. Start from a built-in one, extend it for your organisation and fine-tune it per project. Learning proposals change nothing until a person approves them.
Bring your own models
Connect OpenAI, Anthropic, any OpenAI-compatible endpoint or an Ollama server, and assign models by role. Available models are loaded from the provider, so you pick from a list.
Review and traceability
Machine checks decide whether work is ready for review, never whether it is done. A person approves it or asks for changes, and every deliverable keeps its versions, source and review history.
Secure by default
Every workspace is isolated to its organisation, and people outside it can't tell whether your projects exist. Members have owner, admin or member roles.
How we built it
Multi-tenant SaaS from day one
Organisations, members, audit logs and a subscription layer, with sign-up required and the product free during beta.
Human-in-the-loop by design
Agent output goes through machine checks first, then a person's review. Self-learning arrives as proposals, never as silent changes.
Private data stays private
Automated privacy scans run in CI on the web app and the desktop build, so internal files and keys never reach a release.
Technology
Want a product like this?
The same team, the same approach. Tell our agent what you have in mind, and an engineer will take it from there.
[email protected]