Local PDF bank statement parser with AI transaction extraction
StatementLock is a web tool that parses bank statement PDFs entirely in the user's browser. Users download their own PDFs, the AI extracts transactions, and categories are assigned locally by user-defined rules. No data is sent to servers except de-identified text for AI processing, ensuring privacy.
Visit project ↗Entities
Related
Local AI health data analyst using Claude on Garmin SQLite warehouse
A local-first tool that lets users query their Garmin health data via Claude, running analysis on a local SQLite database. It helps users find correlations in their biometric data (e.g., resting heart rate, HRV, sleep) without sending data to the cloud.
Local-first CLI that masks PII and secrets before sending to LLMs
LocalMask is a command-line tool that runs locally to detect and mask personally identifiable information (PII) and secrets before data is sent to large language models. It solves the privacy and compliance problem for developers and organizations that need to use LLMs without exposing sensitive data.
FluxA: AI agent wallet for autonomous API payments
FluxA is a wallet that lets AI agents pay for tools and APIs autonomously within a preset budget and scope. Users set a budget once, approve a scope, and the agent handles payments, generating receipts for each transaction. It solves the problem of manually managing API keys and payment cards for agent-driven workflows.
Produchive: offline desktop activity monitor with local LLM analysis
Produchive is an open-source, offline desktop app for activity monitoring and productivity tracking. It stores all data locally in a JSON file and uses WebGPU to run open-source LLM models on-device for analysis, ensuring privacy. The app helps users who procrastinate on their PC to monitor their activity without their data being sold.
agentsweep CLI scans AI coding agent history files for leaked secrets
A new open-source CLI tool called agentsweep scans history files of AI coding agents (Codex, Cursor, Claude Code, Cline, Aider) for plaintext secrets like API keys, DB URLs, and crypto seed phrases. It uses ~191 detection rules from gitleaks plus a dedicated BIP-39 seed phrase detector, addressing a security risk where pasted secrets persist in agent context and can be re-exposed.
