autodidact is an open-source, self-learning AI agent that dynamically routes tasks between local and cloud models based on confidence. It learns from escalations and supports hybrid inference for developers building adaptive AI systems.
autodidact sits in PulseGate's Autonomous agents & workflows category. It focuses on enabling AI agents to self-learn and dynamically choose between local and cloud models for optimal performance. autodidact is an open-source project aimed at AI developers. autodidact is open source under the MIT license. It ships for the command line, and it can be self-hosted.
It is developed by BuffaloTechRider, and it first shipped in 2026. Development happens publicly on GitHub with 19 stars and 138 commits in the last 90 days. Among its 4 catalogued features are self-learning agent, hybrid inference, and confidence-based routing.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Closest matches by what these projects do