From source
git clone https://github.com/fbobe321/drydock.git
cd drydock
pip install -e .
drydockLocal-first • Terminal-native • Open-source
____ ____ _
| _ \ _ __ _ _| _ \ ___ ___| | __
| | | | '__| | | | | | |/ _ \ / __| |/ /
| |_| | | | |_| | |_| | (_) | (__| <
|____/|_| \__, |____/ \___/ \___|_|\_\
|___/
Local-first CLI coding agent.
Chart your course. Execute with precision. DryDock is a focused TUI for exploring, modifying, building, and testing code with your own local LLM — primary target Gemma 4 26B on llama.cpp. No accounts, no telemetry, no cloud.
drydock
$ drydock
Loading local model route...
GraphRAG context: synced
Tools online: 14
Ready to execute.
What it is
A coding agent designed for your machine, your model, and your code.
DryDock is a TUI coding assistant designed to work with local LLMs. It gives you a conversational interface to your codebase — explore, modify, build, and test projects through natural language and a focused set of tools.
No data leaves your machine. No API keys. No per-token billing. Just your laptop, your model, and your code.
Install
Rebuilding clean — from source for now.
DryDock is being rebuilt from the ground up as an original, Apache-2.0 codebase we own end to end — no upstream fork. Every release is gated by a credential-exfiltration scanner that refuses to publish anything that reaches off-box. PyPI and Docker images return once the rebuild lands and the account is restored.
Recommended serving stack
Optimized around Gemma 4 + llama.cpp.
DryDock is tested and optimized for Gemma 4 26B-A4B served by llama.cpp with --jinja, the chat-template fix that prevents tool-call loops. Other OpenAI-compatible providers such as Ollama, LM Studio, Mistral, OpenAI, and Anthropic can work, but are not as thoroughly tested.
One command from a fresh box with Docker + an NVIDIA GPU. Downloads the GGUF (~13 GB, one-time, resumable) into ~/.cache/drydock/models/, starts the official ghcr.io/ggml-org/llama.cpp:server-cuda container on port 8000 with all the load-bearing flags baked in.
One-command LLM setup
# Docker + nvidia-container-toolkit required.
curl -sSL https://drydock.pages.dev/setup-llm.sh | bash
# Then point drydock at it:
export DRYDOCK_LOCAL_URL=http://localhost:8000/v1
export DRYDOCK_LOCAL_MODEL=gemma4
drydockKnobs: QUANT=Q4_K_M for higher quality, VISION=1 for image input, PORT=8001, CONTEXT=16384 if <16 GB VRAM.
Context that moves with the work
GraphRAG memory keeps relevant code in view.
DryDock combines an AST symbol indexer with retrieval so the model can work with the right code context instead of guessing from a narrow window.
What's in the box
Purpose-built for serious local development.
TUI-first
Textual-powered terminal UI with slash commands, plan/edit modes, session history, undo, back, and goal controls.
14 built-in tools
Includes read_file, write_file, search_replace, bash, grep, glob, mechanical_rename, retrieve, and more.
Local-first
OpenAI-compatible endpoint support for llama.cpp, Ollama, and LM Studio. No cloud required.
GraphRAG
AST symbol indexing plus TF-IDF retrieval. Auto-prefetches relevant code on every turn.
Adaptive thinking
Per-turn thinking budget: HIGH for planning, OFF for routine writes, and LOW for recovery.
Multimodal vision
Optional mmproj-F16.gguf projector enables OpenAI-style image inputs with Gemma 4.
Architecture
The agent loop, without the cloud dependency.
User
→
DryDock TUI
→
Tools
GraphRAG
Local LLM
→
Codebase
Tested hardware
Built for real local inference rigs.
GPU: 2× NVIDIA RTX 4060 Ti 16GB, 32GB total VRAM
RAM: 64GB recommended, 32GB minimum
Model: Gemma 4 26B-A4B, 26B MoE, 4B active params per token
Performance: ~15–17 tok/s decode with llama.cpp Q3_K_M
OS: Ubuntu 22.04 / 24.04, kernel 6.8+
Minimum: single 24GB VRAM card with reduced context
