# melandlabs/openloomi

OpenLoomi is an open-source AI coworker. It connects your work tools, understands what you’re working on, and tells you what needs your attention, why it matters, and what to do next. It’s your open-source Attention Agent.

Repository: https://github.com/melandlabs/openloomi
Canonical: https://ross.abutalabs.com/products/openloomi
Homepage: https://openloomi.ai/
Language: TypeScript
License: Apache-2.0
License Family: permissive
Topics: agent, ai, claw, harness-engineering, llm, llm-model, mcp, memory, security, skills, context-engineering, graph, promt-engineering, gmail, message, slack, telegram, whatsapp, loop-engineering, attention-agent
Last push: 2026-08-31T05:13:36+00:00

## Health v2 (maintenance only)
Score: 82/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 100, release rhythm 100, longevity 10
- inputs: {"age_days": 145, "days_push": 2, "days_rel": 2, "gap_med": 0.0, "n_releases_24m": 27}
- flags: young
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1020, forks 46 (observed 2026-09-01T02:14:04.085639+00:00)

## What it is
OpenLoomi is an open-source desktop AI coworker ('Attention Agent') that connects your work tools (Slack, Gmail, Telegram, WhatsApp, etc.), builds a context graph of your people, projects, and decisions, and surfaces decision cards for what needs your attention. It runs locally with memory, skills, and a Loop engine, and can also plug into agent runtimes like Claude Code and Codex.

## Use cases
- stop missing overdue replies and deadlines across messaging apps
- search my work history across Slack, Gmail, and Notion from one place
- get a morning to-do brief and end-of-day recap automatically
- draft context-aware replies to emails and messages with AI
- connect Claude Code or Codex to my work context
- triage sales and customer messages into one unified inbox
- build a personal memory of decisions and follow-ups across tools

## When to choose
- you want a self-hosted, open-source AI assistant with cross-tool context and memory
- you juggle many messaging/email platforms and want proactive nudges instead of checking each app
- you already use Claude Code or Codex and want to give them persistent work context
- privacy matters - data is processed locally or encrypted, not stored on servers

## When to avoid
- you need a mature 1.0 product - it is pre-1.0 with possible breaking changes between minor versions
- you only need a simple chatbot without tool connectors or memory
- your required platform connector is still listed as 'Soon' or disabled
- you want a fully cloud-hosted managed service rather than a local desktop app

## Facets
- artifact type: application
- maturity: active
- function: agent-framework, mcp, rag, chatbot, workflow-automation, scheduling, search-engine, plugin-system
- domain: developer-tools, large-language-models, self-hosted
- platform: windows, self-hosted
- tags: attention-agent, ai-coworker, context-graph, personal-memory, connectors, decision-cards, claude-code-plugin, codex-plugin, unified-inbox, ai-agents, automation, macos, linux, desktop, typescript

## Member repositories
- melandlabs/openloomi (main) score 82

## Provenance
- Observed fields: from GitHub, fetched 2026-09-01T02:14:04.085639+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T07:09:18.232754+00:00, confidence not recorded.
  - readme: https://github.com/melandlabs/openloomi (fetched 2026-09-01T02:14:04.085639+00:00, sha 7fc4bc87685c)
  - homepage: https://openloomi.ai/ (fetched 2026-08-29T13:09:32.984887+00:00, sha 6e5cdbffe997)
  - site_page: https://openloomi.ai/docs (fetched 2026-08-29T13:09:32.994265+00:00, sha f30392782077)
  - site_page: https://openloomi.ai/docs/connectors (fetched 2026-08-29T13:09:32.996316+00:00, sha 60b43885366a)
  - site_page: https://openloomi.ai/docs/changelog (fetched 2026-08-29T13:09:32.998483+00:00, sha a6df49324b6a)
- Data as of 2026-08-30T08:39:29.467469+00:00.