Tag
Wealthfolio is an open-source personal finance app for tracking investments, net worth, and financial goals with local-first data storage and optional broker sync. It offers privacy-focused features and can be self-hosted or used across multiple devices.
Routed is an open-source, local-first hybrid router for AI agent skills that runs offline on CPU using a combination of dense embeddings, BM25, and exact matching to route prompts in under 20ms without API calls. The tool supports major agentic environments including Cursor, Claude Code, and MCP servers, and just released v1.1.0 with multilingual support and an MCP server mode.
Keen Bean is a macOS app that captures meeting audio locally to draft notes, tasks, specs, and diagrams in real-time without adding a bot to the call. It keeps data on-device as Markdown and JSON, targeting consultants and founders who need private, actionable meeting artifacts.
Rion Wu open-sourced wechat-intelligence-hub, a local-first, privacy-focused tool that uses Codex to analyze WeChat chat histories, generate daily summaries, track business opportunities, and suggest replies without sending messages or storing data remotely.
Open Design is a tool that treats AI coding agents like Claude Code and Codex as design engines, enabling direct output of landing pages and presentations with local deployment and export options.
Apache Maka, an AI agent workspace incubating at the Apache Software Foundation, has released a version with growing community involvement, featuring local-first design and tool execution capabilities.
The paper introduces LoopCAT, a local-first, open-source computer-assisted translation environment for educational use, and proposes a framework to enhance technological agency in translation students.
Vellium v1.1.0 introduces live voice chat with local STT/TTS using Whisper and TeraTTSv2, and simplifies llama.cpp setup for easier integration with local AI models.
Sesame is an open-source, local-first password manager that stores passwords, 2FA codes, and recovery details locally on the user's device, featuring security checkups and support for multiple import formats.
Revalvo is a local-first workbench for prompt engineering and LLM evaluation that allows running prompts against multiple models in parallel, scoring responses, versioning prompts, and batch-testing datasets.
Screenpipe is an AI tool that records computer screen, audio, and activity to provide historical data for AI agents through MCP. It is local-first and source-available, with a promotional offer on launch day.
ChannelOS is a local-first Windows TV system that turns existing media into programmable channels, offering a cable-style TV guide and on-demand viewing without cloud services or accounts.
LatticeDB is an embedded property-graph database that integrates vector and full-text indexing into a single-file format, enabling graph traversal, similarity search, and BM25 search in one query layer for local applications.
OpenLogi is a local-first, open-source alternative to Logitech Options+ for managing Logitech devices.
Wealthfolio is an open-source, privacy-focused personal wealth management tool that supports local data storage, enabling unified management of multiple asset types such as stocks and funds, along with performance analysis.
OpenLogi is an open-source, local-first tool written in Rust for configuring Logitech mice over HID++, offering button remapping, DPI control, and per-app profiles without requiring an account or telemetry.
Actual Budget is a privacy-focused, local-first budgeting app that uses envelope budgeting methodology and offers features like multi-device sync and bank integration.
Nous Research and Teknium announced that their Hermes Agent has surpassed 2,500 GitHub contributors, showcasing the power of community-built, open-source AI agents that prioritize local privacy and capability.
Canon is a local-first CLI tool that automatically injects project decisions into AI coding agents like Claude Code and Cursor to prevent them from re-adopting rejected approaches.
TraceMotive v0.3.0 is an open-source local-first debugger that can compare AI agent runs and identify the first evidence-supported divergence between good and bad executions.