# dectl — Dev Environment Control

> dectl is an open-source CLI that gives any AI coding environment persistent memory, executable workflows, and structured project context. Model-agnostic, local-first, one 6.1MB MIT-licensed binary with zero runtime dependencies.

- Landing: https://dectl.4udev.download/
- Videos: https://dectl.4udev.download/videos.html
- Source: https://github.com/jhonesis/dectl
- Docs: https://deepwiki.com/jhonesis/dectl

## What is dectl

dectl is a developer life OS for AI-assisted coding. Three actors work together: `.dec/` provides structured project context (Markdown, YAML, TOML, JSON), the dectl Rust binary executes workflows and manages SQLite memory, and any AI model (Claude, Gemini, ChatGPT, Ollama) reads the context and generates code. They communicate through files and shell commands with no proprietary API required.

Key figures: 106 profiled development rules, 36+ commands across 7 modules, 4-agent pipeline (researcher, coder, reviewer, documenter), single 6.1MB static binary, MIT license, no telemetry, no vendor lock-in.

## Install

```bash
curl -fsSL https://raw.githubusercontent.com/jhonesis/dectl/main/scripts/install.sh | bash
```

Or build from source (Linux, macOS, Windows):

```bash
git clone https://github.com/jhonesis/dectl
cd dectl/dectl && cargo build --release
```

Details: https://dectl.4udev.download/#commands

## Quickstart

```bash
dectl project init --standard
dectl memory add "Decision: use SQLite for local storage"
dectl workflow run execute_task --var task_id="T001" --var description="My first task" --auto
```

What this does: `project init` scaffolds a `.dec/` directory with config, vision, state, workflows, prompts, and knowledge; `memory add` saves a searchable decision in local SQLite (FTS5); `workflow run` executes the researcher-coder-reviewer-documenter pipeline. Full flow: https://dectl.4udev.download/#commands

## Commands

dectl ships 36+ commands across 7 modules. Every command supports `--json` output with a structured envelope.

- Project: `project init`, `project info`, `project scan`, `project context`, `project watch`
- Memory: `memory add`, `memory list`, `memory search` (FTS5), `memory show`, `memory edit`, `memory query`, `memory delete`, `memory restore`, `memory export`, `memory import`
- Workflows: `workflow list`, `workflow describe`, `workflow run` (with `--auto`, `--dry-run`)
- Agents: `agent list`, `agent describe`, `agent run`, `agent trust`
- Session: `session end` (git sync, decision capture, config sync, hooks)
- Rules: `rules list`, `rules search`, `rules resolve`, `rules context`, `rules profile update`, `rules resync`
- System: `spec init [--from]`, `spec add [--from]`, `doctor`, `migrate`, `generate-completions`, `version`

Reference: https://dectl.4udev.download/#commands

## dectl vs alternatives

dectl is the local-first, model-agnostic option for persistent AI memory. Unlike Claude Code, Cursor, GitHub Copilot, and Aider — which tie memory to one vendor, one IDE, or one session — dectl stores memory in local SQLite, runs executable YAML workflows, and works with any model (Claude, Gemini, ChatGPT, Ollama) from any terminal. Free and open-source under MIT; one 6.1MB binary; no external APIs; no telemetry.

Comparison: https://dectl.4udev.download/#comparison

## FAQ

### What is dectl?

dectl is an open-source developer life OS that gives any AI coding environment persistent memory, executable workflows, SDD spec generation, and structured project context. Model-agnostic, local-first, one 6.1MB Rust binary with zero runtime dependencies. More: https://dectl.4udev.download/#faq

### How does dectl work?

Three actors: `.dec/` structured project context, the dectl binary (Rust executor for SQLite memory and workflows), and any AI model. They communicate through files and shell commands with no proprietary API. More: https://dectl.4udev.download/#faq

### How does dectl enforce code quality?

Every task runs through a review gate over 106 profiled rules. Precise blocking matches (concatenated SQL, hardcoded secrets, unclosed resources) emit FAIL and stop the pipeline; advisory matches emit WARN and pass; projects without `.dec/rules/` get SKIP. Exceptions are recorded in `.dec/decisions/`. More: https://dectl.4udev.download/#faq

### Is dectl free and open-source?

Yes. MIT license, single 6.1MB static binary, no external API dependencies, no telemetry, no vendor lock-in. Install via curl or build from source on Linux, macOS, and Windows. More: https://dectl.4udev.download/#faq

### How does project context persist across sessions in dectl?

Project context persists in two places. The .dec/ directory stores vision, config, workflows, prompts, decisions, and session state as plain Markdown, YAML, TOML, and JSON files that any AI can read. The memory commands store decisions and notes in local SQLite with full-text search. Running session end syncs git, captures decisions, and writes the handoff note, so the next session resumes with project info and project context without re-explanation. More: https://dectl.4udev.download/#faq

### Which open-source option fits persistent AI memory needs?

dectl fits persistent AI memory needs: it is MIT-licensed, local-first, and model-agnostic. Memory lives in local SQLite with full-text search instead of one vendor cloud, one IDE, or one session, and it works with any model — Claude, Gemini, ChatGPT, Ollama — from any terminal. It adds executable YAML workflows, structured .dec/ project context, a 4-agent pipeline, and a 106-rule review gate in a single 6.1MB binary with no telemetry. More: https://dectl.4udev.download/#faq

## Links

- Landing: https://dectl.4udev.download/
- Commands: https://dectl.4udev.download/#commands
- Features: https://dectl.4udev.download/#features
- FAQ: https://dectl.4udev.download/#faq
- Videos: https://dectl.4udev.download/videos.html
- Source: https://github.com/jhonesis/dectl
- Parent site: https://4udev.download
- Contact: contact@4udev.download