AI Coding Assistants
Local-first desktop coding agent; compatible local models can avoid subscriptions and API calls.
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 checked .
Check official pricing
A local-first coding assistant and model server with an optional cloud-provider lane. The local path avoids an AI API bill; model choice and device capacity still matter. Visit the project website to check the currently available deployment options.
Official README and root license checked against this revision on 2026-11-01. Local model and provider costs are recorded separately; AltStack did not execute the project or its installers.
Availability checked 1 Nov 2026. Check the provider’s release or installation information
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 documentationTechnologies recorded in the catalog snapshot.
Use an AI assistant to write and edit code.
OpenCode can be used without a Go subscription. Optional Go is USD 10/month and Go Plus USD 40/month, with model-specific usage limits. Local models use your hardware; connected provider APIs and subscriptions bill separately. Promotional free models are limited-time offers.
Minimal terminal coding agent you can fully customize.
Official README supplies the installable Pi harness under MIT and instructs users to connect their own provider subscription or API key. The free harness does not include model usage or provider subscription fees.
Autonomous coding agents that complete real engineering tasks.
Official pricing lists MIT Agent Canvas free to self-host using own LLM key, Teams $499/month for up to 10 users with extra seats $50/month, and custom Enterprise. Provider tokens and managed cloud are separate.
ClineProduct logo · See the interface on the official websiteUse an AI coding agent in an editor or terminal, with an optional local model.
The Apache-2.0 Cline VS Code extension and CLI have no software license charge. Use local Ollama models without a paid API key or per-request model charge, on your own hardware. Cline usage-billing, ClinePass subscriptions and external cloud model providers are optional paid routes with their own terms. The current repository says its JetBrains plugin is not open sourced. This review establishes the local client route, not unlimited hosted inference.
Coding agent that runs on local and open-weight models.
The Open Interpreter repository edition is available under Apache-2.0 with documented installation or build instructions and no required source-license subscription. Your server, storage, backups and administration remain your costs. External model/API usage is billed by its provider; no model allowance is included. This check covers that source edition; managed services, premium extensions and commercial relicensing, if offered, are not included or price-verified.
General-purpose AI agent for code, workflows, and more.
The Apache-2.0 agent has a documented local model/provider route with no required agent source-license subscription. You provide hardware, storage, power and separately licensed models. Optional hosted inference, credits and cloud accounts have separate charges and limits.
Allow Google Analytics to measure page visits and basic device information using cookies? Your searches and form entries are excluded. You can change this choice at any time. Privacy details.
