Build apps and fix code with ad-funded coding access; check current model and session limits.
Provider-checked pricing
AI TOOL DETAILS
Nekko Agent
Local-first desktop coding agent; compatible local models can avoid subscriptions and API calls.
Nekko Agent
Free local app · model and hardware separate
What does it cost?
The listed option is free to use. Hosting or model usage may still cost money.
Nekko bundles local inference with an agent and can connect to existing local runtimes. It can also use Claude API keys or hosted model providers, which are separately billed. No model license is inherited from the MIT app. No model weights are bundled. A compatible local model such as Ollama's qwen2.5-coder:7b is listed under Apache-2.0 at 4.7GB; confirm model compatibility and its license separately. Hardware, model download/storage, and electricity remain user costs. Optional hosted or API inference may be billed.
Provider pricing checked 1 Nov 2026.
Installation and setup
- Check the README and choose the bundled local-inference mode or an existing local model runtime; no hosted API is needed for the local path.
- Install Nekko Agent from the official repository instructions for your operating system.
- Select a compatible local model and verify its separate model license, storage footprint, and hardware needs before downloading it.
- Run a short prompt with a test folder first; connect a hosted model only if you accept that provider’s account, privacy, and billing terms.
Local inference is the no-subscription path. The app license does not grant rights to model weights, and the project’s optional cloud providers can bill separately.
Self-hosting & quickstart specs
- License
- MIT
- Deployment
- Local desktop application
- Free edition / costs
- Free local application · model/hardware costs separate. Nekko bundles local inference with an agent and can connect to existing local runtimes. It can also use Claude API keys or hosted model providers, which are separately billed. No model license is inherited from the MIT app. No weights are bundled. The official Ollama qwen2.5-coder:7b listing states Apache-2.0 and 4.7GB; verify compatibility and model licensing separately. Local hardware, storage, download, and electricity still have costs. Optional remote inference can be billed. Pricing evidence.
- Devices / hardware
- Local inference is the no-subscription path. The app license does not grant rights to model weights, and the project’s optional cloud providers can bill separately.
No one-line command has been verified for Nekko Agent; follow its official installation instructions instead of guessing a Docker image or installer.
Nekko Agent provider setup documentationWhat can you use it for?
Source code and self-hosting
Read the repository for the license, installation steps, and operating costs.
Source repositoryView the full software profileLearn how to use this type of tool
Read a practical guide before choosing a plan or setting up a workflow.
How to use an AI coding tool and check its workDoes this tool help you?
This preference stays on your device. It does not change public rankings.
More tools for similar tasks
Repository questions, code edits and shell-driven coding tasks
Provider-checked pricing
Prototype AI workflows visually and connect components into runnable applications.
Provider-checked pricing