Moadim.io
Moadim is an open-source loop engine that schedules and runs AI agents (Claude, Codex, Hermes, NanoClaw, Pi) against a repository or task on a recurring schedule in isolated workbenches with watchdogs and built-in HTTP/MCP interfaces.
Moadim.io is developer tools software teams evaluate for business operations. Use this page to review pricing, integration signals, and the best alternatives before you commit.
Profile facts come from the vendor source. AiMatch labels unknown pricing or API details instead of estimating them.
Review official source →Used in These Packs
Quick Overview
Best for: Business Operations
What it does
Developer Tools software for decision-makers comparing workflow fit and alternatives.
Best fit
Business Operations
Pricing snapshot
Free
Next step
Compare Moadim.io with similar tools before you shortlist it.
Compare this tool before you shortlist it
Review alternatives, pricing posture, and workflow fit side by side.
Moadim.io
Moadim is an open-source, self-hosted daemon that runs scheduled loops of AI agents against code or other tasks. A loop is defined by a prompt, a schedule, and an agent (Claude, Codex, Hermes, NanoClaw, or Pi), and each scheduled tick launches the agent in a fresh, isolated workbench where a watchdog kills hung runs and the session is reaped when finished. The product targets developers and teams who want automated, repeatable agent workflows and loop engineering rather than manually invoking models.
The daemon runs locally on Unix-like systems (macOS and Linux), requires tmux for its per-run isolation, and can be installed as a system service (launchd/systemd) so loops survive reboots and logins. The server exposes REST endpoints, an OpenAPI/Swagger UI, MCP-compatible endpoints, an iCal feed, and a bundled web UI for managing loops.
Moadim is an open-source loop engine for AI agents — runs Claude, Codex, Hermes, or Pi on a schedule, over MCP and REST.
Own this listing?
Claim this page for a one-time $29 to add pricing, features, screenshots, verified owner details, and a clearly labeled 30-day category position after the profile is live.
Claim this listing for $29Key Features
Loop-driven agent runs
Each loop pairs a prompt, a schedule, and a named agent (Claude, Codex, Hermes, NanoClaw, Pi) and launches that agent on every tick.
Isolated workbench per run
Every tick launches the agent in a fresh, isolated tmux workbench with a watchdog that kills hung runs and reaps sessions so runs cannot leak state.
Local scheduler and persistence
Moadim's portable in-process scheduler fires loops locally—no hidden queue or cloud—and can be registered as a launchd or systemd service to survive reboots.
HTTP REST, OpenAPI and Swagger UI
Every loop is a documented HTTP endpoint with an OpenAPI schema and Swagger UI baked into the daemon; REST endpoints such as /api/v1/routines are provided.
MCP tool compatibility
Loops are available as MCP tools and MCP-compatible agents can call the same operations via the daemon's MCP interface.
Multiple agent backends
Built-in agents include Claude, Codex, Hermes, NanoClaw (queues a one-shot task), and Pi; Claude has an additional python3 requirement for pre-seeding unattended trust and MCP-approval state.
iCal feed and web UI
The daemon provides a web UI and an iCal feed for scheduled loops, making schedule visibility and management available out of the box.
Pricing
Open source under the MIT license — free to use, modify, and self-host. There is no paid tier and no account to create.
Use Cases
Continuous repository automation
Run agents against your codebase on a schedule to perform tasks such as automated code review, maintenance tasks, or periodic analysis.
Agent orchestration and loop engineering
Define repeatable agent workflows (prompts + schedules + agents) to move from ad-hoc prompting to engineered, production-like loops.
MCP tool integration
Expose loops as MCP tools so MCP-compatible agents can invoke Moadim-managed routines programmatically.
Queueing one-shot tasks
Use NanoClaw agent support to queue one-shot tasks in a configured agent group while other agents run inside the isolated workbench.
Integrations
Claude / Codex / Hermes / Pi
Built-in agent backends that Moadim can run on each loop tick.
NanoClaw
Queues a one-shot task in a configured agent group rather than running inside the workbench.
MCP
Loops are exposed as MCP tools; MCP-compatible agents can call the same operations via the daemon.
HTTP / OpenAPI / Swagger
Every loop is a documented HTTP endpoint with OpenAPI schema and a Swagger UI baked into the daemon.
launchd / systemd
Service registration for macOS and Linux to keep the daemon running across reboots.
Benefits
Limitations
Frequently Asked Questions
Is Moadim free? What's the license?
Is it self-hosted or a cloud service?
Which agents does it support?
Which operating systems are supported?
How is each run isolated?
Getting Started
- 1 Step 1: Install Moadim: cargo install --locked moadim (or use cargo binstall moadim or npm install -g moadim).
- 2 Step 2: Start the daemon: run moadim which starts the server in the background (default http://localhost:5784/).
- 3 Step 3: Register persistent service: run moadim install to register a launchd (macOS) or systemd (Linux) service so loops survive reboots. Ensure tmux is on your PATH and python3 is available if using the Claude agent.
Support
docs
Documentation is linked from the site (Docs) for usage and configuration guidance.
repo
GitHub repository referenced from the site for source code, issues, and contributions.
package
Published on crates.io and also installable via cargo binstall or npm (site references crates.io and install options).
API
The daemon exposes REST endpoints with OpenAPI schema and a Swagger UI baked into the server (e.g., /api/v1/routines) and also exposes MCP-compatible endpoints.
Compare Moadim.io with similar tools
See how it stacks up against alternatives
Related Tools
View all 111 →
Docs.dev Your Own Hosted Docs Platform in Minutes
Docs.dev is a deployable documentation template that runs as a Cloudflare Worker in your account, using your GitHub repo as the source of truth and agent-powered drafting (e.g., Claude Code or Codex) to generate reviewable docs branches that your team publishes via commit.
Bullet · Fast, by design.
Bullet is a fast coding agent and developer tool that routes, searches, and executes code-focused tasks with a tight loop to minimize latency — offered as a macOS download and currently available in private beta.
statuslin.es
statuslin.es is a community gallery of Claude Code status lines—copyable, previewed scripts and themes for terminal/status-bar displays that show Claude model stats (tokens, cost, limits), git info, and other runtime metrics.
dmx
dmx is an open-source, AI-native engineering harness that runs as an MCP server and wraps AI-driven development workflows in structured, versioned loops with human gates, validators, and persistent job state to make AI-assisted engineering reproducible and governed.
Make Sense of Any GitHub PR
MakeSense (powered by LiveReview) gives a concise, easy-to-understand explanation of any public GitHub pull request, classifies issues by severity across security/maintainability/performance/correctness, and includes a short quiz to check understanding — ready in under 30 seconds.
Premium Alternatives
OTP Inspired actor supervisor based full stack templates
ShipStacks provides production-grade, OTP-inspired full-stack SaaS templates that include supervisors/actor patterns, auth, payments, uploads, AI chat and agent playbooks, and Docker-ready deployment in multiple languages and frameworks.
ratio1
Ratio1 is a blockchain-powered, decentralized AI operating system and edge/cloud computing platform that enables rapid development and deployment of AI apps, a tokenized GPU compute marketplace, and node-based infrastructure via Node Deeds and the $R1 utility token.
startkit-ai
StartKit.AI is a purchasable, production-focused Node.js boilerplate that provides a complete SaaS app and pre-built AI modules to help developers ship AI startups quickly, including demos for chat, PDF, images, RAG, authentication, payments, and integrations with AI providers.
Finetunefast
FinetuneFast provides finetuning boilerplates, inference templates, and deployment tooling to accelerate building and shipping ML models (text-to-image, LLMs, RAG, TTS) — aimed at developers, indie makers and businesses who want production-ready examples and fast time-to-deploy.
runpod
Runpod is an AI Developer Cloud that provides on-demand GPU infrastructure—Pods, Serverless endpoints, and multi-node Clusters—enabling teams to experiment, train, fine-tune, deploy, and scale AI workloads across 31 global regions with support for 30+ GPU SKUs.