Stars
A benchmark for evaluating AI agents on realistic business workflows
τ²-Bench-Verified is a corrected and verified version of the original τ²-bench benchmark. This release addresses issues discovered in the original dataset where task definitions, expected actions, …
τ-Bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains
Microsoft SEAL is an easy-to-use and powerful homomorphic encryption library.
Programmatic memory for long-horizon LLM agents: the harness appends everything to one log, and the agent searches it with code. 97.4% on ARC-AGI-3 (arXiv:2607.20064)
Get Android app updates straight from the source.
Mobile and Web client for Codex and Claude Code, with realtime voice, encryption and fully featured
SkillOpt is a text-space optimizer that trains reusable natural-language skills for frozen LLM agents through trajectory-driven edits, validation-gated updates, and deployable best_skill.md artifacts.
A library of creative canvas components. Real HTML with WebGL effects running over it. React, Vue, Svelte, vanilla.
LiteRT, successor to TensorFlow Lite. is Google's On-device framework for high-performance ML & GenAI deployment on edge platforms, via efficient conversion, runtime, and optimization
LiteRT-LM is Google's production-ready, high-performance, open-source inference framework for deploying Large Language Models on edge devices.
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
An idiomatic, lean, fast & safe pure Rust implementation of Git
Using system APIs directly with adb/root privileges from normal apps through a Java process started with app_process.
Hiera: A fast, powerful, and simple hierarchical vision transformer.
NVIDIA Isaac GR00T N1.7 - A Foundation Model for Generalist Robots.
Ongoing research training transformer models at scale
v1 of Asimov, an open-source humanoid robot
Conditional Memory via Scalable Lookup: A New Axis of Sparsity for Large Language Models
Ghidra is a software reverse engineering (SRE) framework
Structured state space sequence models
mini cli search engine for your docs, knowledge bases, meeting notes, whatever. Tracking current sota approaches while being all local
Bimo is an open-source bipedal robotics platform with a Python API, fully 3D printable, and an Isaac Lab environment implementation with working sim-to-real transfer.
A fully open-source humanoid arm for physical AI research and deployment in contact-rich environments.