Skip to content
View ShownX's full-sized avatar
🐶
Focusing
🐶
Focusing

Block or report ShownX

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
Showing results

[EMNLP2026] "VideoAgent: All-in-One Agentic Framework for Video Understanding and Editing, and Remaking"

Python 2,049 255 Updated Jul 22, 2026

A small, fast decision model, or system one model, for agentic workflows. Pick between options or rate on a scale faster than an LLM, with a calibrated confidence on every decision.

Python 1,204 131 Updated Nov 16, 2026

Trajectory2Gym: Decision-Grounded Compositional Interaction Synthesis for Tool-Use Agents. Official code, training tools, and examples.

Python 66 2 Updated Oct 24, 2026

Test your prompts, agents, and RAGs. Red teaming/pentesting/vulnerability scanning for AI. Compare performance of GPT, Claude, Gemini, DeepSeek, and more. Simple declarative configs with command li…

TypeScript 27,324 2,784 Updated Nov 16, 2026

DeepSeek Harness: Everything is a Plugin.

TypeScript 282,299 34,956 Updated Nov 13, 2026

LightCraft: An open-source non-destructive photo editor written from scratch in pure Rust

Rust 16,074 6,120 Updated Nov 16, 2026

Miles is an enterprise-facing reinforcement learning framework for LLM and VLM post-training, forked from and co-evolving with slime.

Python 3,321 626 Updated Nov 16, 2026
Python 238 24 Updated Oct 10, 2026

JEPA-Anything: Learning Predictive Models across Different Worlds

Python 407 29 Updated Sep 18, 2026

Uni-Agent is a framework for training long-horizon agents.

Python 729 157 Updated Nov 16, 2026

Next generation e2e testing framework for web and mobile apps.

TypeScript 13,953 753 Updated Nov 16, 2026

Open source evals for physical AI. Run any LLM/VLA on any arm/humanoid against any real/sim benchmark.

Python 764 112 Updated Nov 11, 2026

RLAnything (ICML 2026) & AutoTool (ICML 2026), DemyAgent: Open-Source RL for LLMs and Agentic Scenarios

Python 664 58 Updated Jun 12, 2026
Python 1 Updated Aug 27, 2026
Python 8 1 Updated Oct 16, 2025

MiMo Code: Where Models and Agents Co-Evolve

TypeScript 13,786 1,479 Updated Nov 16, 2026

Terminal-Bench-Science: Evaluating AI agents on research workflows across scientific domains

Python 916 562 Updated Nov 14, 2026

CLI runbook for agent long run.

Python 1,606 171 Updated Nov 10, 2026

🪢 Open source AI engineering platform: AI Gateway, agent observability, evals, and prompt/skill management, built on OpenTelemetry. One open platform for every AI call and every agent. Self-host or…

TypeScript 37,500 4,240 Updated Nov 16, 2026

This project includes code for using the AsyncWebRL and WebGym frameworks to train web agent models.

Python 52 4 Updated Jun 9, 2026

The absolute trainer to light up AI agents.

Python 18,964 1,724 Updated Nov 12, 2026

SWE-Bench Pro: Can AI Agents Solve Long-Horizon Software Engineering Tasks?

Python 565 105 Updated Sep 22, 2026

A Practitioner's Guide to M(eow)ti Turn Agentic ReinfOrcement learning

Python 85 12 Updated Jan 16, 2026

A streamlined and customizable framework for efficient large model (LLM, VLM, AIGC) evaluation and performance benchmarking.

Python 3,701 574 Updated Nov 16, 2026

A self-improving RLM agent for coding workflows and long-running autonomous tasks.

Rust 22,776 2,528 Updated Nov 16, 2026

Orchard-Agentic is a collection of open-source work on agentic modeling

Python 562 45 Updated Nov 7, 2026

Framework for evaluating and improving agents

Python 7,110 2,219 Updated Nov 16, 2026

A persistent workspace for development work that self-improves and continues beyond one session.

Python 4,958 1,048 Updated Nov 16, 2026

A standard API for single-agent reinforcement learning environments, with popular reference environments and related utilities (formerly Gym)

Python 12,828 1,542 Updated Nov 12, 2026
Next