Directory / Coding agent / Memdoor
Memdoor
Lightweight open-source coding and automation agent in one CLI binary for macOS, Linux and Windows: run it locally or over SSH, cut token use with a decision model, and automate CI and cron jobs with durable, resumable workflows.
💲 Agent, decision model and workflows are free and open source (Apache 2.0), using your own model API key. Pro $10/mo adds phone remote control and hosted workflow state on memdoor.ai. Source: memdoor.ai (checked Nov 1, 2026).
Pros & cons
👍 Pros
- Single binary, no Docker or Python; headless `memdoor run` returns exit codes for scripts and CI
- Workflow graphs with parallel steps, approval gates and resume-from-failure
- Self-reported 74% fewer input tokens on some codebase questions
👎 Cons
- Small, very new project
- Token savings depend on the task (none reported on edits/fixes)
- Bring-your-own model key required
Latest release
Multi-model team workflow hits HN front page
Memdoor's example 'team-solve' workflow, where five Qwen3.8-27B models work together, was reported to beat a frontier model on LiveCodeBench Hard and reached the Hacker News front page. Source ↗
Ranked in
Alternatives to Memdoor
Claude Code
Coding agentAnthropic's agentic coding tool — understands your codebase, edits files, runs commands, and helps you ship faster.
Cursor
AI code editorAn AI coding agent for building ambitious software — agents turn ideas into code so you can hand off tasks.
AI SDK (Vercel)
Agent frameworkA unified TypeScript SDK for building AI apps with modern streaming, fallbacks, and multi-model support.
Ratings are preliminary editorial opinions. Spotted something out of date? Tell us. Listed here? Get the badge. Some links are affiliate links; they never affect rankings.