OpenLoomi is an open-source desktop AI coworker that connects work tools, gathers context, and highlights decisions or actions needing attention. It is for people managing work across multiple apps, and its catalogue add-ons extend the resident desktop for agent frameworks such as Claude Code, Codex, OpenCode, Hermes, and OpenClaw.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/melandlabs/openloomiWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/plugins/melandlabs/openloomi/claude)<a href="https://agentmods.dev/plugins/melandlabs/openloomi/claude"><img src="https://agentmods.dev/badge/plugins/melandlabs/openloomi/claude/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/plugins/melandlabs/openloomi/claude"><img src="https://agentmods.dev/badge/plugins/melandlabs/openloomi/claude.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
openloomi scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
{
"name": "openloomi",
"version": "0.9.0",
"description": "Connect Claude Code to your local OpenLoomi runtime. One-command install, mirror Claude's lifecycle onto the Loomi Pet, and auto-archive every Stop into your OpenLoomi memory. Talks to your local OpenLoomi over HTTP and the OpenLoomi helper CLI. AI provider config is owned by OpenLoomi itself — this plugin never reads or pushes API keys.",
"author": { "name": "OpenLoomi" },
"homepage": "https://openloomi.ai",
"repository": "https://github.com/melandlabs/openloomi/tree/main/plugins/claude",
"license": "Apache-2.0",
"keywords": [
"openloomi",
"memory",
"pet",
"anthropic",
"claude-code",
"local-first",
"loops"
],
"commands": "./commands",
"skills": "./skills"
}
What it installs
The manifest is a name and a version. 11 skills, 10 commands, 8 hooks travel with it, and installing the plugin installs all of them — 1,448 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill openloomi-memory A 74 tokens
- Skill openloomi-api A 106 tokens
- Skill openloomi-connectors A 113 tokens
- Skill openloomi-pet A 110 tokens
- Skill openloomi-feature-guide A 138 tokens
- Skill openloomi-install A 124 tokens
- Skill openloomi-tour B 117 tokens
- Skill openloomi-loop B 171 tokens
- Skill openloomi B 155 tokens
- Skill openloomi-hooks B 108 tokens
- Skill composio C 31 tokens
- Command setup A 23 tokens
- Command memory A 26 tokens
- Command pet A 24 tokens
- Command usage A 13 tokens
- Command status A 15 tokens
- Command loop B 34 tokens
- Command hooks B 14 tokens
- Command help A 8 tokens
- Command tour B 29 tokens
- Command connect C 15 tokens
- Hook Stop A not measured
- Hook Notification A not measured
- Hook PostToolUse A not measured
- Hook PreToolUse A not measured
- Hook SessionStart A not measured
- Hook SubagentStart A not measured
- Hook SubagentStop A not measured
- Hook UserPromptSubmit A not measured
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 21 lines scan A fb6f32edc601
openloomi is a plugin published in the GitHub repository melandlabs/openloomi (1,037 stars, last pushed 24d ago), licensed Apache-2.0. Its token cost is not measured: this kind of file is read by the harness, not the model. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other plugins, from other repositories
hebb-mind
Neuroscience-inspired long-term memory for Claude Code — auto-captures and recalls cross-session context.
understanding-graph
A persistent medium for fluid, emergent understanding.
tencentdb-agent-memory
Four-layer long-term memory (L0→L1→L2→L3 Persona) with hybrid FTS5+vector recall + L2 scene-navigation. CLI: tmem (status, search, projects, migrate-fragments, recall, scene, scenes, changelog, persona, sync, config, daemon, atoms, sessions, write-l1, write-scene, write-persona, mark-done, init). Run /memory-init…
agent-wiki
Agent-driven knowledge base with immutable raw sources, mutable wiki pages, BM25 search, code analysis, and self-checking lint. Use when managing knowledge bases, importing documents, writing wiki pages, or parsing source code.
humanizer
Rewrite AI-sounding text so it reads like the writer without changing what it says.
nextjs
Official Next.js skills: adopt and optimize Cache Components, adopt Partial Prefetching, and verify runtime behavior against a running dev server.