kev
★ 9.8kAbout
Kev is a local decision-model server that adapts a Qwen3 base model with LoRA and a small readout head to answer structured questions about a document. Instead of generating prose, it produces...
Community Ratings
No ratings yetNew this week
Read recap →Weekly Recap — Oct 23, 2026 – Oct 30, 2026Oct 30, 2026
Features
- typed questions
- yes/no questions
- multi-option questions
- ordered score questions
- single-pass inference
- block-causal question isolation
- probability outputs
- TypeSafe-compatible API
- local playground
- chess playground
Details
- Last Updated
- Nov 4, 2026
- Created
- Sep 17, 2026
- Install Methods
- dockersource
- Requirements
- Python 3.12+uvNode 20+ for the playgroundHugging Face Hub weightsApple Silicon (MPS) for servingCUDA (H100 via Modal) for training and evaluation
- Minimum Requirements
- RAM: 32 GB
- API
- REST
- Backup & Export
- file-backupnative-export
- Privacy & Independence
- Cloud: OptionalOffline Capable
- Deployment
Deployment: no container deployment found
Run kev yourself
Pick how much you want to manage.
netcupBest matchFull control
A server with more than 8 GB of RAM, then Docker Compose.
About 20 minutes with Docker
HetznerFull control
A server with more than 8 GB of RAM, then Docker Compose.
About 20 minutes with Docker
DigitalOceanFull control
A server with more than 8 GB of RAM, then Docker Compose.
About 20 minutes with Docker
1 more way to host
Some links earn us a commission. netcup pays us one and is our preferred VPS host.
Is this your project? Sponsor a listing
Track your self-hosted stack
Bookmark software to try, rate tools you've used, and keep your collection in one place.
Metadata extracted from README on Sep 20, 2026
Alternatives to kev
ollaya
1.4k
Ollaya runs open decision models locally and provides Ollama-like CLI, daemon, and API access for model serving.
Artificial IntelligenceLocal LLMsInference Serving+2
Related Software
Ollama
185.8k
Ollama is a tool for running open models locally and exposing them through a REST API for apps, agents, and integrations.
Artificial IntelligenceLocal LLMsGenerative AI+3
LLMKube
252
Kubernetes operator for LLM inference with pluggable runtimes (llama.cpp, vLLM, TGI, Ollama, vllm-swift), multi-GPU sharding, NVIDIA CUDA + Apple Silicon Metal support, and OpenAI-compatible API.
Artificial IntelligenceLocal LLMsInference Serving+2
Text Generation Inference
10.9k
A Rust, Python, and gRPC server for deploying and serving large language models with high-performance text generation.
Inference ServingArtificial IntelligenceLocal LLMs+1
2 Containers
vLLM
96.3k
A fast, easy-to-use library for LLM inference and serving.
Inference ServingLocal LLMsAI Tooling
2 Containers
KoboldCpp
12.1k
KoboldCpp is a self-contained AI text-generation runner for GGML and GGUF models, with bundled UI, multiple inference modes, and broad support for image, audio, video, and vision tasks.
Inference ServingLocal LLMsAI Interfaces+2
Single Container
Dify.ai
160.4k
An open-source platform for building, testing, and operating LLM-powered applications with workflows, RAG, agents, and observability.
Low Code DevelopmentArtificial IntelligenceFOSS with Issues+6
36 ContainersOpen CoreFOSS with Issues
openclaude
34.3k
OpenClaude is an open-source terminal-based coding agent CLI for cloud and local model providers.
AI Coding AssistantAI AgentsAI Tooling+1
LLM Harbor
3.3k
Harbor is a CLI and companion app for spinning up and managing a local LLM stack with pre-wired services like Open WebUI, llama.cpp, Ollama, vLLM, SearXNG, Speaches, and ComfyUI.
Artificial IntelligenceLocal LLMsAI Tooling+5
Aider
49.9k
AI pair programming tool for working with large language models directly in the terminal.
Artificial IntelligenceAI Coding AssistantPermissive License+1
Open-WebUI
157.7k
Open WebUI is a self-hosted AI platform for chatting with LLMs, managing RAG, and building custom model workflows, designed to run entirely offline.
Artificial IntelligenceAI InterfacesLocal LLMs+7
2 ContainersOpen CoreFOSS with Issues
Wiznote
Manage your knowledge in documents with folders, markdown, full text search and webpage collection support.
Knowledge ManagementNote Taking AppsDocument Management+1
Quizmaster
327
A web app for hosting quizzes with player answer submission, master controls, and configurable question types.
GamesPermissive LicensePolls and Events+2