>_

devBldr Agentic AI Coding Assistant

A local-first coding agent powered by Ollama LLMs

Privacy-first AI that runs entirely on your machine. An agentic loop that reads, searches, edits, and runs your build and tests to verify its own work, plus on-demand skills, tool calling, and spec-first scaffolding.

devbldr

$ devbldr /path/to/project

Indexing project... done

Found 42 files, 156 symbols

> Add authentication to the user API

read user routes, edited handler, ran tests _

Your Code. Your Machine. No Limits.

devBldr uses Ollama to run AI models locally, keeping your code private while an agentic loop plans, writes, refactors, and verifies your code with the safety gates always in your hands.

Everything You Need for AI-Assisted Development

🤖

Agentic Loop

A single loop that reads, searches, edits, and runs your build and tests to verify its own work. Follow-ups keep their context.

🛠️

Tool Calling

Instead of stuffing the whole project into every prompt, the model requests what it needs (read, search, edit, and run commands) on demand.

🧩

Skills

On-demand SKILL.md instruction folders, loaded only when a task matches, so specialized know-how stays out of the prompt until it is relevant.

🏗️

Spec-First Scaffolding

Point it at an empty directory and it plans a complete, runnable app (requirements, architecture, per-file generation), then builds and verifies it, all with your approval.

🔒

Local LLM Integration

Uses Ollama for privacy-first AI inference. Your code never leaves your machine.

🧠

Project-Aware Context

Automatically indexes your codebase using tree-sitter and builds intelligent context for each request.

🛡️

Safe File Operations

Every write goes through colorized diffs, an approval workflow, and automatic backups. Commands ask before they run. The agent works with the gates, never around them.

🌐

Multi-Language Support

Tree-sitter parsing for C, C++, Python, JavaScript, TypeScript, JSX, TSX, Rust, Go, Java, and more.

🔍

Project Type Detection

Recognizes Flask, Django, FastAPI, Express, NextJS, React, Vue, C++, Rust, and Go projects.

How It Works

On startup, devBldr indexes your project with tree-sitter to extract symbols and detect the project type. What happens next depends on the request.

EXISTING CODE

The Agentic Loop

Fixing a bug, adding a feature, refactoring: devBldr hands the model the full tool set and lets it drive. It understands, changes, and runs your build and tests to verify, looping until the task is done.

BUILD & TEST

Iterate Until It Works

After generating code, devBldr runs your build and test suite, reads any failures, and keeps fixing and re-running until everything passes.

NEW PROJECTS

Spec-First Planning

Your request expands into requirements, then an architecture, then a file plan you approve. Each file is generated, then the result is built and exercised automatically.

Install with Homebrew

Get started in seconds on your Mac

Terminal

# Add the tap and install

$ brew tap jefferyabbott/devbldr

$ brew install devbldr

# Or install in one command

$ brew install jefferyabbott/devbldr/devbldr

Make sure you have Ollama installed and running

Built-in Commands

Just type what you want in plain language and the agent handles the rest. These slash commands are there when you want them.

/model [name] List or select Ollama model
/explain <file> Explain code in a file
/analyze <file> Analyze code for issues
/fix <file> Fix bugs in a file
/refactor <file> Refactor code
/files Show indexed project files
/readonly <pattern> Mark files as read-only
/include <file> Include file in LLM context
/context Show current context info
/reset Clear conversation history

Requirements

Apple Silicon Mac

macOS 12.0 or later

Ollama installed and running

Agentic features work best with a tool-capable model (llama3.1/3.2/3.3, qwen2.5/qwen3, mistral-nemo).

Support This Project

If you find devBldr useful, consider buying the developer a coffee!

Buy Me a Coffee
🏠
العربية Català Čeština Dansk Deutsch Ελληνικά English Español Suomi Français עברית हिन्दी Hrvatski Magyar Bahasa Indonesia Italiano 日本語 한국어 Bahasa Melayu Norsk Bokmål Nederlands Polski Português (Brasil) Português (Portugal) Română Русский Slovenčina Svenska ไทย Türkçe Українська Tiếng Việt 简体中文 繁體中文