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.
npx agentmods add commands/melandlabs/openloomi/connectgit 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/commands/melandlabs/openloomi/connect)<a href="https://agentmods.dev/commands/melandlabs/openloomi/connect"><img src="https://agentmods.dev/badge/commands/melandlabs/openloomi/connect.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00015 | $0.00773 |
| Opus 5 | $0.00008 | $0.00387 |
| Sonnet 5 | $0.00003 | $0.00155 |
| Haiku 4.5 | $0.00002 | $0.00077 |
Grade C, and why
connect scanned grade C with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
> (`curl -fsSL https://composio.dev/install | bash`) [y/N] Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
> (`curl -fsSL https://composio.dev/install | bash`) [y/N] How it starts
The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/openloomi:connect
Walk the user through three independent opt-in steps. Each step is gated by an explicit y/N from the user. NOTHING happens silently.
Step 1 — Verify composio skill readiness
Before asking the user anything, detect whether composio is already
in place. Two pieces must both exist for Step 1 to be a no-op:
# 1. CLI on PATH?
command -v composio >/dev/null 2>&1
# 2. Skill shipped in this plugin?
test -f "${CLAUDE_PLUGIN_ROOT}/skills/composio/SKILL.md"
Then branch on the combined result:
- Both present → print one line
(
composio ready: CLI on PATH, skill loaded from plugins/claude/skills/composio/) and continue straight to Step 2. No y/N. - CLI missing only → ask:
Composio CLI not on PATH. Install it via the official installer? (
curl -fsSL https://composio.dev/install | bash) [y/N] On y, run that command. Never runnpm install -gwithout consent. - Skill missing only → ask:
The composio skill isn't shipped in this plugin (
plugins/claude/skills/composio/SKILL.mdmissing). Restore it (e.g.git pullor reinstall the plugin)? [y/N] On y, defer to whatever restore flow the user picks; do not regenerate skill content here. - Both missing → ask the CLI-missing question; the skill ships with the plugin and will come back when the plugin is restored, so one y/N is enough.
After Step 1 resolves (no-op or install), continue to Step 2.
Step 2 — Enable screen memory
Tell the user:
OpenLoomi Desktop's user profile / preferences page has a "Chronicle" section that controls Screen Memory. Turn it on to let Loomi summarize what you're looking at. Open the Preferences page now? [y/N]
Only on explicit y/N: print the navigation hint
OpenLoomi Desktop → Preferences → Chronicle → Screen Memory
and continue.
Do NOT print any openloomi://... URL. The plugin codebase does
not register a deep-link scheme for this entry — only the navigation
hint above is real.
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.
- 5d ago First seen · 78 lines · 15 tokens per session scan C ff6c7f0a594a
connect is a command published in the GitHub repository melandlabs/openloomi (1,021 stars, last pushed 5d ago), licensed Apache-2.0. It adds 15 tokens to every session and 773 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other commands, from other repositories
awesome-chatgpt
Search awesome-ChatGPT-repositories for open-source GitHub repositories related to ChatGPT and LLMs.
commit
智能生成 Git 提交信息并提交.
/release
Release a new version — updates CHANGELOG, pyproject.toml, creates git tag, and pushes.
speckit.archive
Archive a feature specification into main project memory after merge, resolving gaps and conflicts.
pr
Handle the full workflow from current branch state to an open, CI-monitored pull request.
AGENTS
Per-command agent-optimized usage and structure guide.