AI Agent / Finance

Moxie

Open-source, local-first money agent that finds waste, drafts cancellation or dispute actions, and only proceeds with user approval. It emphasizes consent, a tamper-evident audit trail, and bring-your-own-key operation.

Clear28/30
Useful24/30
Specific15/20
Complete15/20
Moxie screenshot

Why it was accepted

The page clearly presents an AI-powered product with a concrete use case: finding subscriptions, duplicate charges, and missed refunds, then drafting actions for approval. The README gives enough detail for a useful public listing, including workflow, sample-data demo, local-first operation, and the current scaffold status.

Weakness

The repository is still early-stage, and several core integrations are stubbed, so the page does not show a working path for real bank, OCR, or email ingestion yet.

Review status

60 days ago #1255 ↓ -2

Last evaluated 60 days ago. Current rank #1255. Down 2 spots in the rankings.

Score history

82

Related listings

Ami screenshot
#107 Ami
89

AI Agent / Personal Productivity

Ami is a local, open-source AI agent that connects to apps and tools with your own tokens, keeps a universal to-do list, and runs busywork on your behalf. It includes copilot chat and graph memory, and runs on your machine with local data storage.

Thio's Universal Agent screenshot

AI Agent / Computer Use / Desktop Automation

A Windows desktop agent that lets AI interact with any app through visual GUI control, with a portable single-EXE build and support for ChatGPT, Gemini, and Claude.

Hestia screenshot
#688 Hestia
85

AI Agent / Home Assistant

A local-first, self-hosted home assistant that runs a local LLM as a single brain for Home Assistant, voice, memory, reminders, media control, and other scoped tools.

Autodidact screenshot
#961 Autodidact
84

AI Agent / Self-improving assistant

Open-source local-first AI agent that routes between local and cloud LLMs, learns from escalations, and stores knowledge for future queries. The repo includes a quickstart, setup modes, and a concrete explanation of how it ingests docs and improves over time.