A privacy-first browser-based collection of everyday utilities and file processing tools.

Vision-Language-Policy model for dynamic robot task planning and autonomous execution.

Context-Activated Memory Reinforcement framework for adaptive memory retention in LLM agents.

OSS credential gateway to keep secrets out of AI agents.

Data-Efficient Post-Training and Experience-Driven Learning for retail humanoid robots.

LLM-enhanced semantic calibration framework for Federated Graph Backdoor Defense.

Unified LLM framework for joint optimization of essay scoring and feedback generation via RL.

Enables Elixir to run in the browser

A lifecycle memory framework for Personal AI focusing on continuity and governance.

A real-world-grounded benchmark and dataset for measuring scientific safety risks in LLMs.

A framework for reliable and adaptive reasoning of LLMs on uncertain knowledge graphs.

A 9MB open-source alternative to Adobe Bridge for Mac

A framework for evaluating planning-phase prompt injection attacks in multi-agent LLM systems.

Diffusion-driven cross-domain policy adaptation for reinforcement learning.

A cost-reduction strategy for LLM APIs pairing query-agnostic compression with cache control.

A live coding environment based on Forth for real-time audio/visual synthesis.

Framework for tracing and attributing errors in Large Language Model memory systems.

A clinician-built open-source benchmark for medical AI safety boundary inspection.

Open-source multi-agent system for automating brain science research.

Ten-dimensional capability-oriented benchmark for assessing MLLM-as-a-judge systems.