Moadim.io – A scheduler for agents
Moadim is an open-source loop engine for AI agents — runs Claude, Codex, Hermes, or Pi on a schedule, over MCP and REST.
Moadim.io – A scheduler for agents launched on September 4, 2026 with 37 votes, #706 of 8,095 launches that month and more than 95% of that year's launches.
In plain words
Moadim is an open-source loop engine that runs AI agents like Claude, Codex, Hermes, or Pi on a schedule via MCP and REST APIs. Users define loops consisting of a prompt, schedule, and agent, which then execute automatically against their repository on each cycle or queue tasks to NanoClaw. Each run executes in an isolated workbench with monitoring. The tool requires Unix-like OS with tmux and can be installed via cargo or npm, with no host cron daemon needed.
written from the facts on this page · September 2026
From the sources
Moadim is a loop engine for AI agents. Define a loop — a prompt, a schedule, an agent — and it runs Claude, Codex, Hermes, or Pi against your repo on every tick, or queues a NanoClaw task, in an isolated workbench with a watchdog on every run. Loop engineering, not prompting by hand. Starts the server in the background at http://localhost:5784/ . Requires a Unix-like OS with tmux — Moadim's portable in-process scheduler dispatches loops, then launches each agent inside a tmux session. No host cron daemon is required. Every loop is also a documented HTTP endpoint, with an OpenAPI schema and Swagger UI baked into the daemon. The same call as an MCP tool, for any MCP-compatible agent connected…from moadim.io
Does a similar job
all alternatives →
Arch2024 · github.com · ▲314Hey HN — I’m Adil from Katanemo (with Salman, Shuguang, and Meiyu) We previously shared an early version of this project as ArchGW. Based on customer feedback, the scope expanded from “LLM routing and model access” into something broader: delivery infrastructure for agentic applications. We renamed it to Plano and reworked the architecture accordingly. The problem On-the-ground AI practitioners will tell you that calling an LLM is not the hard part. The really hard part is delivering agentic applications to production quickly and reliably, then iterating without rewriting system code every…
Auto-Architecture: Karpathy's Loop, pointed at a CPUApr 2026 · github.com · ▲241Contribute to FeSens/auto-arch-tournament development by creating an account on GitHub.
Moltis – AI assistant with memory, tools, and self-extending skillsFeb 2026 · moltis.org · ▲131Hey HN. I'm Fabien, principal engineer, 25 years shipping production systems (Ruby, Swift, now Rust). I built Moltis because I wanted an AI assistant I could run myself, trust end to end, and make extensible in the Rust way using traits and the type system. It shares some ideas with OpenClaw (same memory approach, Pi-inspired self-extension) but is Rust-native from the ground up. The agent can create its own skills at runtime. Moltis is one Rust binary, 150k lines, ~60MB, web UI included. No Node, no Python, no runtime deps. Multi-provider LLM routing (OpenAI, local GGUF/MLX, Hugging…
HiveTermMay 2026 · hiveterm.com · ▲86A native workspace for Claude Code, Codex, Antigravity and Grok. Split panes on the desktop, routines in the agent
More ai this month
the category →
Paintings by AI models: programs run through a simulation of oil paint.
AI · 20d ago · stillwet.art
PixVerse R2▲381A real-time world model you can explore and change
AI · 29d ago · world.pixverse.video
Launched alongside, September 2026
the whole month →
E-ink bird frame for Raspberry Pi - real-time bird detection by audio, fully local AI, rendered as real, hand-cut 1800s bird illustrations. - arnegiacomo/fugleramme
AI · Sep 2026 · github.com
- WI
Special relativity simulator in which light crawls along at a human speed, so Lorentz contraction, aberration and Doppler shift happen at walking pace.
Life & fun · Sep 2026 · rivendell.dmitrybrant.com
Start coding agents, control sessions, review PRs. Anywhere.
Dev tools · Sep 2026 · kilo.ai
