# Memdoor

> Lightweight open-source coding and automation agent in one CLI binary for macOS, Linux and Windows. Run it locally or over SSH, headless from scripts, CI or cron, with multi-step YAML workflows, approval gates and a decision model that trims token use. Bring your own key or a local model.

- Page: https://vibetoolrank.com/tools/memdoor/
- Markdown: https://vibetoolrank.com/tools/memdoor.md
- Official: https://memdoor.ai/
- Category: Coding Agents (CLI & Cloud) (https://vibetoolrank.com/best/terminal-agents/ · https://vibetoolrank.com/best/terminal-agents.md)
- Pricing: Free and open source (Apache 2.0): the agent, the decision model and workflows. Pro is $10/month for phone remote control and workflow state kept on memdoor.ai. Every model call runs on your own key
- Free tier: Yes: the CLI, decision model and workflows are free; bring your own model key (for example OpenRouter) or run a local model with memdoor connect local. No account needed
- Last checked: 2026-11-04

## Agent test

- Overall: **9.1/10** (outcome 10, speed 8, cost 10, DX 6, reliability 10)
- Tested: 2026-11-04 · Runs: 3 runs · Edition: Memdoor CLI v1.788.0 with OpenRouter free model cohere/north-mini-code:free (BYOK, $0)
- Summary: Memdoor fixed our seeded cart discount bug in 3 of 3 headless runs (35–47s each) with a free OpenRouter model, never touched the test file, and printed its own test receipt. Cost $0. Overall 9.1 (outcome 10, speed 8, cost 10, DX 6, reliability 10). DX lost points because the default free-model auto-pick hit an OpenRouter 403 and pinning a model needed environment variables.
- Evidence: docs/tests/memdoor/RESULTS.md

## Pros / cons

- Pro: Fixed the seeded bug in 3/3 runs with a free model
- Pro: Single binary, no account, clean --json output for scripts and CI
- Pro: Ends each run with a receipt showing the tests it ran before and after
- Pro: Did not modify the test file in any run
- Con: Default free-model auto-pick failed with an OpenRouter 403 in our test
- Con: Pinning a specific model needed AI_GATEWAY_* environment variables
- Con: Slower than paid-model agents (35–47s per run on a free model)

## Sources

- https://memdoor.ai/
- https://github.com/guregodevo/memdoor
- https://github.com/guregodevo/memdoor/releases

Methodology: https://vibetoolrank.com/methodology/