Agent frameworks & infrastructure
Local LLM runtimes
1,401 agents · most starred first
Local LLM runtimes, page 8 of 15
A feature-rich desktop GUI for Ollama with Vision, RAG, and JSON support.
Configurable Windows-native, loopback-only Hermes Agent workstation with CPU/CUDA llama.cpp and Hermes Launcher
🛠️ Enable offline NLP workflows with Local-LLM, a lightweight Python library for secure environments using the BERT model, ensuring reproducibility and reliability.
transformers gguf code qwen qwen-coder codeqwen
llama.cpp fork that lets a 27B coding agent run on a 16GB GPU: the KV cache lives on a three-tier desk/bookshelf/archive (VRAM window / host RAM / SSD) with attention-driven page recall, so context reaches 256K without decode slowing down.
gguf llama.cpp historical victorian conversational vintage-model
Self-hosted private LLM chat platform with RAG: local open-source models via Ollama/vLLM, FastAPI, pgvector, Redis semantic cache, Redpanda, Prometheus
Local LLM gateway for Apple Silicon. Works with OpenClaw, Hermes Agent, Claude Code, and Codex (AIRun). No Ollama or LM Studio required.
Archived model for a constraint-native local AI runtime exploring energy, rhythm, coherence, and persistent behavior.
A reference architecture demonstrating local-first LLM orchestration for SOC compliance workflows. Built on ~11GB VRAM edge hardware using Ollama, featuring a multi-agent coordination pattern with file-based handoffs, a two-lane integration model (human-initiated vs automated processing), and a HITL approval gate for resource-sensitive operations.
Selene é um aplicativo desktop para executar modelos de inteligência artificial localmente. O código-fonte é público e desenvolvido no Brasil 🇧🇷. Converse com modelos, envie imagens e trabalhe com um agente de programação que pode explorar arquivos e executar tarefas com sua autorização. Tudo no seu computador.
Local AI assistant with a SvelteKit web UI. Multi-phase pipeline (route → plan → generate → validate) on top of llama.cpp, Ollama, or LM Studio. RAG, web search, no API keys, no cloud.
A portable, offline-first CLI AI assistant built with C++ and llama.cpp. Features dynamic file context awareness, memory management, and runs entirely from a USB drive without dependencies.
Local AI Interface is an Electron desktop application designed to streamline your personal AI stack. It provides a unified, user-friendly hub for Dockerized services like Ollama (for LLMs) and n8n (for workflow automation), with built-in dark mode and easy one-command setup.
A starter template for building powerful, local, tool-calling LLM agents using LangGraph and llama-cpp-python
Allows filesystem access for LM Studio
DIZI-AI is an open-source local AI orchestration platform for developers who want full control over their AI stack. Create intelligent multi-agent workflows, automate tasks, generate code and images, and monitor every step with transparent execution and profiling. No cloud dependency. Just powerful, customizable AI running on your hardware.
gradio region:us
gradio region:us
gradio region:us
docker region:us
gradio region:us
gradio region:us
gradio region:us
gradio region:us
gradio region:us
gradio region:us
gradio region:us
gradio region:us
transformers openvino llama text-generation conversational base_model:TinyLlama/TinyLlama-1.1B-Chat-v1.0
Local AI Chat App / ローカル AI チャットアプリ
Run a fully private, offline AI assistant from a USB flash drive — no installation, no internet, no admin rights required.
transformers gguf TensorBlock GGUF text-generation base_model:Qwen/Qwen3-Coder-30B-A3B-Instruct
Self-hosted local-first AI research stack with Ollama, n8n, USMC & GARDENER memory, task-master, KnowledgeDigest, and Docker Compose
gguf llama-cpp ministral openzero agent-zero local-ai
transformers gguf text-generation zh arxiv:2311.17487 license:apache-2.0
gguf GGUF qwen3 qwen quantized cerebellum
mlx safetensors qwen3_5_moe text-generation conversational base_model:Kwaipilot/KAT-Coder-V2.5-Dev
gguf mergekit merge text-generation en dataset:lemonilia/LimaRP
gguf gemma4 mtp speculative-decoding draft-model llama.cpp
gguf llama.cpp pebble mamba2 hybrid small-language-model
transformers gguf heretic uncensored decensored abliterated
mlx safetensors llama omlx apple-silicon oq
Luna - a portable, offline AI assistant that lives on a USB drive. Plug into any Windows, Mac, or Linux computer and chat privately in your browser. No cloud. No accounts. No data left behind. Powered by Ollama + Open WebUI.
Local AI assistant: one Qwen3.5 model plus a library of LoRA experts, picked for each message and checked in code. Runs on a 16 GB laptop, OpenAI-compatible API.
A production-ready Pterodactyl egg for Ollama. Run a local LLM API server (LLaMA 3, Qwen, Gemma) directly on your Pterodactyl panel with zero configuration.
llama.cpp gguf quantized imatrix moe mtp
gguf qwen4_exp moe expert-pruning apple-silicon code
A command-line interface for Ollama LLM models, designed for seamless integration with shell scripts and command-line workflows.
Using open-source Llama2 as an alternate to OpenAI
Brain-inspired AI reasoning engine — local LLM swarms on consumer hardware. Django + Celery + Ollama. MIT licensed.
AI Mobile Edge chat in offline model with Google Gemma4 AI Model
AI Provider for Ollama Local for Wordpress 7.0 AI Conectors
Lightweight web UI for llama.cpp with dynamic model switching, chat history & markdown support. No GPU required. Perfect for local AI development.
🚀 Advanced offline AI assistant with one-click installation. Complete privacy, no GPU required. Built by RaxCore.
A llama.cpp based chat interface with a sandboxed environment for the LLM
🧠 A fully self-hosted, universal AI chat interface powered by local LLMs. Designed for both desktop and laptop use — supports CPU and GPU (CUDA) execution. Features real-time streaming responses, clean minimalist UI, and no external server dependencies. Ideal for building your own private, offline AI assistant.
Pure Rust inference engine for the SmolLM3-3B language model. No Python runtime, no CUDA, no external dependencies. Single executable + quantized weights = portable AI on any machine.
Small Language Models
🤖 Build intelligent, offline LLM agents with LangGraph and llama-cpp-python using this starter template for local, private tool-calling applications.
Local-first AI workstation. Run open-weight models, fine-tune, orchestrate multi-agent teams. No cloud required.
Tunnel Panda is a modular, secure reverse-proxy that streams local Ollama API and Chrome DB via Cloudflare Tunnel of yours to make it publicly accessible. Now we do have an GUI interface for the configuration.
Portable OpenWebUI workbench with offline model packages, tools, filters, skills and import artifacts.
Reliable, resumable model puller for Ollama with integrity guarantees
Speed Dating With Local AI Models
gradio region:us
docker region:us
gradio region:us
gradio region:us
gradio region:us
gradio region:us
gradio region:us
gradio region:us
gradio region:us
gradio region:us
gradio region:us
gguf safetensors llama-cpp lm-studio ollama local-llm
gguf gemma gemma-4 mtp speculative-decoding llama.cpp
gguf text-generation license:apache-2.0 endpoints_compatible region:us conversational
gguf text-generation base_model:anthracite-org/magnum-v3-9b-chatml base_model:quantized:anthracite-org/magnum-v3-9b-chatml license:gemma endpoints_compatible
transformers gguf llama-factory orpo text-generation en
gguf multilingual sea sailor sft chat
mlx safetensors qwen3_5 8bit qwen3.5 lm-studio
transformers gguf qwen2 text-generation chat en
transformers gguf facebook meta pytorch llama
transformers gguf mistral quantized 2-bit 3-bit
transformers gguf llama text-generation GGUF conversational
gguf text-generation base_model:internlm/internlm2_5-1_8b-chat base_model:quantized:internlm/internlm2_5-1_8b-chat license:other endpoints_compatible
transformers gguf gpt llm large language model h2o-llmstudio
gguf chat TensorBlock GGUF text-generation en
gguf mistral quantized 2-bit 3-bit 4-bit
transformers gguf llama text-generation base_model:01-ai/Yi-1.5-9B-Chat base_model:quantized:01-ai/Yi-1.5-9B-Chat
transformers gguf qwen2 text-generation chat en
gguf OpenAccess AI Collective MPT axolotl PyTorch Transformers
mlx safetensors qwen3_5 mlx-lm text-generation conversational
gguf text-generation license:apache-2.0 endpoints_compatible region:us conversational
Hit your Claude usage limit or Claude is down? Flip one command and your claude -p scripts keep running on a local MLX model on your Mac. Flip back when the limit resets. Claude stays primary.
A workbench for running large Mixture-of-Experts LLMs locally on consumer hardware with a tight VRAM budget.
A funky CLI that talks to Qwen 3.6 via Ollama with animations and attitude.
Run large language models locally on Windows. A native Rust desktop app and local LLM API server for GGUF models fully offline, no Python, no Docker, no cloud account. It measures your GPU and the model file, then loads a configuration that fits. Tuned on an 8 GB laptop card.