Official JAX implementation of End-to-End Test-Time Training for Long Context

ISO: Isospectral Optimization for RLVR

slime is an LLM post-training framework for RL Scaling.

A version of verl to support diverse tool use [TMLR 2026]

Kimi Code CLI — The Starting Point for Next-Gen Agents

Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.

Sandboxed code execution for AI agents, locally or on the cloud. Massively parallel, easy to extend. Powering SWE-agent and more.

Benchmarking Agents on Real-World Terminal Tasks

ARIS ⚔️ (Auto-Research-In-Sleep) — Lightweight Markdown-only skills for autonomous ML research: cross-model review loops, idea discovery, and experiment automation. No framework, no lock-in — works…

[WACV 2025] Official implementation of "Online-LoRA: Task-free Online Continual Learning via Low Rank Adaptation" by Xiwen Wei, Guihong Li and Radu Marculescu

A standard SDK for building agent-facing apps across MCP, CLI, React, and AI tool stacks.

Fully autonomous & self-evolving research from idea to paper. Chat an Idea. Get a Paper. 🦞

Official Implementation of "Visual Agentic Memory: Online Long Video Understanding via Online Indexing, Hierarchical Memory, and Agentic Retrieval"

GUISpector: An MLLM Agent Framework for Automated Verification of Natural Language Requirements in GUI Prototypes

Prompt, run, edit, and deploy full-stack web applications. -- bolt.new -- Help Center: https://support.bolt.new/ -- Community Support: https://discord.com/invite/stackblitz

[ASE 2025] Benchmarking MLLM-based Interactive Webpage Code Generation from Interactive Prototyping

Scalable toolkit for efficient model reinforcement

Runnable ClaudeCode source code

OpenClaw-RL: Train any agent simply by talking

We introduce BabyVision, a benchmark revealing the infancy of AI vision.

Structural Reasoning About Program Correctness in Natural Language

Latest Linux kernels merged with Google BBR v3. Compiled .deb packages available. Ideal for high-bandwidth networking in all latency and packet loss environments.