Open-source engine
Free
EUPL-1.2; model/hardware requirements separate
- Included scope
- Native bindings; local text/speech/vision inference
On-device AI inference bindings · Official-source review 2026-10-09
NobodyWho is a Rust-based local inference engine with bindings for Python, Kotlin, Swift, React Native, Flutter and Godot. It combines GGUF language models, structured tool calling and local speech/vision capabilities for application developers.
Relevant to developers embedding model capabilities on supported desktop or mobile devices.
Desktop supports 64-bit Linux/macOS/Windows, with Windows x86_64 only; web export and Windows ARM64 are not yet supported. Godot has no iOS export. Free RAM guidance is roughly 1.5–2× model size; mobile needs approximately twice model size beyond system reserves. Uses one GPU, falling back to CPU layers. EUPL distribution of modified engine requires source disclosure; confirm license interpretation for your use. Model compatibility and speech quality were not tested.
Select a small appropriately licensed model, run a fixture query in the intended binding and measure RAM and tool-schema behavior before embedding it.
Desktop supports 64-bit Linux/macOS/Windows, with Windows x86_64 only; web export and Windows ARM64 are not yet supported. Godot has no iOS export. Free RAM guidance is roughly 1.5–2× model size; mobile needs approximately twice model size beyond system reserves. Uses one GPU, falling back to CPU layers. EUPL distribution of modified engine requires source disclosure; confirm license interpretation for your use. Model compatibility and speech quality were not tested.
Official product evidence reviewed on 2026-10-09; product artwork inspected visually. No hands-on vendor application test was performed. Application performance, security claims and plan enforcement were not independently tested.
What it can do
Unknown is different from unavailable. Each fact carries its own evidence.
| Capability | Value | Evidence | Checked |
|---|---|---|---|
| Product workflow | NobodyWho is a Rust-based local inference engine with bindings for Python, Kotlin, Swift, React Native, Flutter and Godot. It combines GGUF language models, structured tool calling and local speech/vision capabilities for application developers. | Facts sourced | 2026-10-09 |
| Pricing and restrictions | Desktop supports 64-bit Linux/macOS/Windows, with Windows x86_64 only; web export and Windows ARM64 are not yet supported. Godot has no iOS export. Free RAM guidance is roughly 1.5–2× model size; mobile needs approximately twice model size beyond system reserves. Uses one GPU, falling back to CPU layers. EUPL distribution of modified engine requires source disclosure; confirm license interpretation for your use. Model compatibility and speech quality were not tested. | Facts sourced | 2026-10-09 |
Understand the total cost
Open-source engine
Free
EUPL-1.2; model/hardware requirements separate
RunInfra provides hosted open models through OpenAI- and Anthropic-compatible APIs. It offers prepaid token billing and workspace coding plans, with session-aware caching and separately reported cached-token usage.
Explore toolApp Gacha generates small desktop applications and floating widgets from a plain-language idea. Apps live in a local library and can be arranged into workspaces; users can bring a model-provider key or purchase hosted AI credits.
Explore toolAuriko provides an OpenAI-compatible model gateway with provider routing, fallback, key orchestration and cost analytics. It supports user-supplied or platform keys and configurable objectives such as cost, latency and data policy.
Explore toolThe practical questions
No. This listing is based on dated official-source evidence and a visual artwork check. Unconfirmed costs and restrictions are identified explicitly.
NobodyWho is a Rust-based local inference engine with bindings for Python, Kotlin, Swift, React Native, Flutter and Godot. It combines GGUF language models, structured tool calling and local speech/vision capabilities for application developers.
EUPL-1.2 open source with no per-token engine fee; hardware, model licenses and distribution obligations remain separate.. This record lists ongoing free access; check the plan limits before starting.
No paid monthly price is listed; this record treats the product as free to start. See the plan cards for entitlements, billing commitments and seat minimums.
Language bindings and experimental local OpenAI-compatible /v1/models and /v1/chat/completions server are documented.. API access and subscription access may have different terms; consult the linked sources.
Desktop supports 64-bit Linux/macOS/Windows, with Windows x86_64 only; web export and Windows ARM64 are not yet supported. Godot has no iOS export. Free RAM guidance is roughly 1.5–2× model size; mobile needs approximately twice model size beyond system reserves. Uses one GPU, falling back to CPU layers. EUPL distribution of modified engine requires source disclosure; confirm license interpretation for your use. Model compatibility and speech quality were not tested.
No retained pricing changes yet. A current price alone does not establish a historical trend.
Current official product source read individually; product artwork inspected visually.
Read original source ↗Official product page reviewed for disclosed costs; unverified prices and allowances are identified in the listing.
Read original source ↗Facts apply to the named version and check date. Send a sourced correction if something changed.