openloomi-api

openloomi-api is a skill for Claude Code from melandlabs/openloomi. It costs 106 tokens per session (4,564 once invoked), scanned A, original, Apache-2.0.

A local HTTP API for OpenLoomi, a desktop app that stores data in a local SQLite database. It provides routes for authentication, memory, AI, retrieval-augmented generation (searching stored information to improve answers), loops, and audit records.

In plain words
What is it for?
Use it to connect code or an agent to OpenLoomi's authentication, memory search, knowledge base, AI, RAG, loop, connector, and audit functions. It also supports the plugin bridge's local port-discovery and authentication handshake.
Why use it?
It gives programs a documented way to work with OpenLoomi's local data and features without treating a remote server as the main source of truth. This keeps the listed application data on the user's machine, apart from the stated external OAuth connection path.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions Codex.

Part of the openloomi plugin — 11 skills, 10 commands, 8 hooks shipped together

Good fit Use it to connect code or an agent to OpenLoomi's authentication, memory search, knowledge base, AI, RAG, loop, connector, and audit functions. It also supports the plugin bridge's local port-discovery and authentication handshake.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/melandlabs/openloomi/openloomi-api
About the project

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.

melandlabs/openloomi · 1,022 stars · on GitHub · openloomi.ai

Install

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.

Any agent
npx skills add melandlabs/openloomi --skill openloomi-api
Clone the repo
git clone --depth 1 https://github.com/melandlabs/openloomi

Made for: Claude Code.

Or install openloomi, the plugin that ships this one along with the rest of its 11 skills, 10 commands, 8 hooks.

Wrote 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.

agentmods badge for openloomi-api

README.md
[![agentmods](https://agentmods.dev/badge/skills/melandlabs/openloomi/openloomi-api.svg)](https://agentmods.dev/skills/melandlabs/openloomi/openloomi-api)
Your own site
<a href="https://agentmods.dev/skills/melandlabs/openloomi/openloomi-api"><img src="https://agentmods.dev/badge/skills/melandlabs/openloomi/openloomi-api.svg" alt="Measured on agentmods" height="20"></a>
Per session 106 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,564 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 6 findings, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • high Rogue Agent · line 174
    Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.
    Fix: Prevent the skill from modifying its own code, SKILL.md, or configuration files. Treat skill files as read-only at runtime.
  • medium Data Exfiltration · line 337
    Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
    Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
  • medium Rogue Agent · line 340
    Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.
    Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
  • medium Data Exfiltration · line 347
    Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
    Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
  • medium Data Exfiltration · line 359
    Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
    Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
  • medium Data Exfiltration · line 371
    Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
    Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00106 $0.04564
Opus 5 $0.00053 $0.02282
Sonnet 5 $0.00021 $0.00913
Haiku 4.5 $0.00011 $0.00456

Measured 8d ago against content hash b60a7e8e72b8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

openloomi-api scanned grade A with 1 finding 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 8d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

### curl Examples
plugins/claude/skills/openloomi-api/SKILL.md · 392 lines

How it starts

The opening of the file, as written. The whole thing — 392 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Note: If you haven't downloaded or installed openloomi yet, please refer to Getting Started for installation instructions.

OpenLoomi API Documentation

API Modules

OpenLoomi ships a local-first HTTP API served from the desktop app (port 3414, fallback 3515). All auth, Memory, AI, RAG, Loop, and Audit data live in a local SQLite database — your data stays on your machine and the OpenLoomi app is the source of truth. The only externally-routed auth path is the Composio OAuth broker that backs the Slack, GitHub, Google, Notion, Linear, HubSpot, LinkedIn, Jira, and Asana Connectors (see openloomi-connectors).

The remote-auth prefix is historical — those routes once proxied to a cloud server; today they are the canonical local endpoints, and the Claude/Codex plugin bridge uses /api/remote-auth/user as a port-discovery + auth-handshake probe.

This reference covers 131 route handlers under 36 top-level /api/* modules. Pair it with openloomi-loop (Loop state, decisions, channels, classifier rules, brief/wrap) and openloomi-memory (Memory search, KB, insights, entities, living connections) for the runtime surfaces used by Chat and Loop.

Functional Modules

Module Base Path Routes Description
Auth /api/auth/*, /api/remote-auth/*, /api/remote-feedback/* 6 Guest session, token, user probe, feedback
AI /api/ai/* 5 Chat, images, audio, embeddings
Audit /api/audit/* 1 Audit log retrieval
Chat Insights /api/chat-insights/* 1 Per-chat insight records
Chronicle /api/chronicle/* 7 Meeting detection, analysis, memories
Contacts /api/contacts/* 1 Contact query
DB Init /api/db/* 1 Bootstrap database
Files /api/files/* 8 File storage, upload, download
Insight Tabs /api/insight-tabs/* 3 Tab CRUD + reorder
Integrations /api/integrations/* 9 OAuth + connected accounts
Listeners /api/listeners/* 1 Listener cleanup
LLM Usage /api/llm/* 1 Usage summary
Loop /api/loop/* 24 Attention loop, decisions, channels, classifier rules
Markmap /api/markmap/* 1 Markmap generation
Memory /api/memory/* 2 Memory search, raw messages
Messages /api/messages/* 4 Send, sync, status, raw
Native /api/native/* 5 Native agent operations, providers, skills
Pet /api/pet/* 1 Pet state mirror
Proxy /api/proxy/* 2 CSS/JS proxy
RAG /api/rag/* 11 Document upload, search, stats
Storage /api/storage/* 4 Disk usage, sessions, cleanup
Workspace /api/workspace/* 11 Artifacts, files, skills, previews

Read the full file on GitHub · 392 lines

Changes

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.

  1. 8d ago First seen · 392 lines · 106 tokens per session scan A b60a7e8e72b8

Subscribe to this mod's changes

openloomi-api is a skill published in the GitHub repository melandlabs/openloomi (1,022 stars, last pushed 8d ago), licensed Apache-2.0. It adds 106 tokens to every session and 4,564 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

stream-feeds-migration

Generate the v2 -> v3 sync mapping for a Stream Activity Feeds app by sampling its live v2 activities and reactions. Use when setting up a Feeds v2 to v3 migration, when asked to build, review, or debug a v3 sync mapping, when someone asks 'what mapping do we need for our app?', or when a migrated activity lands in v3…

GetStream/agent-skills · 150 tokens

magicbase

Use when an HTML micro-app needs MagicBase persistence, window.Magic.db row operations, current-user context through window.Magic.getContext, creators, owners, assignees, permissions, CRUD, forms, surveys, todos, dashboards, filters, statistics, exports, or any saved user data.

dtyq/magic · 63 tokens

review-prs

Review a GitHub pull request in the googleapis/mcp-toolbox repo against the team's reviewer checklist: PR title/description conventions, linked issue, logic errors and unhandled edge cases, breaking changes, test coverage, docs updates, security (input handling), and new dependencies. Use whenever a maintainer asks…

googleapis/mcp-toolbox · 162 tokens

fix-failing-tests

Diagnose a failing test in the googleapis/mcp-toolbox repo and land a fix by reasoning from the actual error: read the failure, reproduce it, shrink it until the cause is forced into the open, then fix the cause. Use this whenever a test or CI job is red, a build breaks after a change, many packages fail at once, or a…

googleapis/mcp-toolbox · 87 tokens

stale-sweep

Sweep the googleapis/mcp-toolbox repo for issues and PRs with no real activity in N days (default 60), sort each by whose silence it is (the author's, ours, or nobody's), and draft the nudge or close comment. Use whenever a maintainer asks for a stale sweep, backlog cleanup, or an SLO check, e.g. "stale sweep", "find…

googleapis/mcp-toolbox · 159 tokens

triage-issues

Triage GitHub issues in the googleapis/mcp-toolbox repo: propose the correct labels (type / priority / product / status), check for duplicates, verify a bug has enough info to act on, and draft a triage comment. Use whenever a maintainer asks you to triage, label, categorize, prioritize, or "look at" an issue (or a…

googleapis/mcp-toolbox · 164 tokens