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.
The page clearly describes a real AI-powered product with a specific workflow: local confidence check, cloud escalation, learning, and persistent memory. The README gives enough evidence for a useful listing, including installation commands, usage examples, setup modes, supported file types, and a visible demo-style explanation of the product’s behavior.
The snapshot does not show benchmarks, licensing or maintenance details beyond the repo listing, and it is still hard to tell how well the agent performs in practice or what parts of the learning loop are implemented versus planned.
Last evaluated 114 days ago. Current rank #1065. Down 6 spots in the rankings.
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.
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.
Ardent is a code-first AI agent for business work that runs in a desktop app, writes reusable code in a sandbox, and lets teams share repeatable workflows as “Abilities.”
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.
