collar

DAG-first AI agent harness — Entity→Target:verb(card). Reads .dag files. Rust router at 3ms.

.dog = human spec format · .dag = agent runtime format · .md = last resort

Collar is forked from NousResearch/hermes-agent, rebuilt as a DAG-first harness. It reads .dag files as its behavioral ground truth. Skills auto-compile from .dog specs into .dag edges. No prose config, no baked-in prompts — just DAG paths.

Created by Justin DiClemente (@logohere).

Install

git clone https://github.com/specdog/collar.git
cd collar
python3 -m venv .venv && source .venv/bin/activate
pip install -e .
npm install -g dotdog

Requires Python >= 3.11.

Quick Start

collar              # interactive chat
collar chat -q "..."  # single query
collar setup          # first-time setup wizard

No API key? Use OAuth

collar auth add openai-codex   # ChatGPT Plus/Pro
collar auth add xai-oauth      # xAI SuperGrok
collar auth add qwen-oauth     # Qwen Plus/Pro
collar auth add nous           # Nous Portal

Then collar model to pick your provider. Or set OPENROUTER_API_KEY in ~/.dag/.env for pay-per-token access to 200+ models.

Architecture

Layer	Source	Format	Loader
System prompt	`dags/*.dag`	DAG-path plain text	`_load_dag_text()`
Skills	`skills/*/SKILL.dag`	DAG-path plain text	`skill_view()`
Projects	`*.dag`	JSON v2/v3	MCP dotdog

Key Numbers

95% compression	383k → 17k (skills)
74% compression	15k → 4k (system prompt)
0 legacy refs	6974+ renamed

Links

GitHub · dotdog · specdog org