kev
★ 848About
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 — Sep 11, 2026 – Sep 18, 2026Sep 18, 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
- Sep 20, 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
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
Related Software
hermes-agent
247.2k
Hermes Agent is a self-improving AI agent with a built-in learning loop, terminal UI, and messaging gateway for chatting and automating work across platforms.
Artificial IntelligenceAI AgentsAI Coding Assistant+2
2 Containers
opencode
208.7k
An open source AI coding agent.
Artificial IntelligenceAI Coding AssistantPermissive License+3
AutoGPT
187.4k
AutoGPT is a platform for creating, deploying, and managing continuous AI agents that automate complex workflows.
Artificial IntelligenceAutomation ToolsPermissive License+2
13 ContainersOpen Core
Ollama
181.3k
Ollama is a tool for running open models locally and exposing them through a REST API for apps, agents, and integrations.
Artificial IntelligenceLocal LLMsGenerative Artificial Intelligence Genai+3
Dify.ai
156.5k
An open-source platform for building, testing, and operating LLM-powered applications with workflows, RAG, agents, and observability.
Low Code DevelopmentArtificial IntelligencePermissive License+6
36 ContainersOpen CoreFOSS with Issues
Langflow
155.0k
Langflow is a platform for building and deploying AI-powered agents and workflows with a visual builder, API deployment, and MCP server support.
Low Code DevelopmentAutomation ToolsModel Context Protocol+2
11 Containers
Open-WebUI
152.6k
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
Claude Code
146.8k
Claude Code is an agentic coding tool that runs in the terminal and helps with coding tasks, code explanation, and git workflows using natural language commands.
Artificial IntelligenceAI Coding AssistantAI Harness+2
Cloud Required
ComfyUI
134.0k
ComfyUI is a modular node-based AI engine for creating images, video, 3D, audio, and other content with fine-grained control over models and parameters.
Artificial IntelligenceAI Media GenerationCopyleft License+2
Freemium
Codex
125.3k
Codex CLI is a local coding agent from OpenAI that runs on your computer.
Artificial IntelligenceAI Coding AssistantPermissive License+3
Pi
107.4k
Pi Agent Harness is a mono-repo for a self-extensible coding agent, including an interactive coding agent CLI, agent runtime, and a unified multi-provider LLM API.
AI HarnessAI AgentsAI Coding Assistant+1
vLLM
92.2k
A fast, easy-to-use library for LLM inference and serving.
Inference ServingLocal LLMsAI Tooling
2 Containers
