-
Amazon
- New York
- shownx.github.io
- https://orcid.org/0000-0003-3814-7203
Lists (5)
Sort Name ascending (A-Z)
Stars
[EMNLP2026] "VideoAgent: All-in-One Agentic Framework for Video Understanding and Editing, and Remaking"
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.
Trajectory2Gym: Decision-Grounded Compositional Interaction Synthesis for Tool-Use Agents. Official code, training tools, and examples.
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…
DeepSeek Harness: Everything is a Plugin.
LightCraft: An open-source non-destructive photo editor written from scratch in pure Rust
Miles is an enterprise-facing reinforcement learning framework for LLM and VLM post-training, forked from and co-evolving with slime.
JEPA-Anything: Learning Predictive Models across Different Worlds
Uni-Agent is a framework for training long-horizon agents.
Next generation e2e testing framework for web and mobile apps.
Open source evals for physical AI. Run any LLM/VLA on any arm/humanoid against any real/sim benchmark.
RLAnything (ICML 2026) & AutoTool (ICML 2026), DemyAgent: Open-Source RL for LLMs and Agentic Scenarios
MiMo Code: Where Models and Agents Co-Evolve
Terminal-Bench-Science: Evaluating AI agents on research workflows across scientific domains
🪢 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…
This project includes code for using the AsyncWebRL and WebGym frameworks to train web agent models.
The absolute trainer to light up AI agents.
SWE-Bench Pro: Can AI Agents Solve Long-Horizon Software Engineering Tasks?
A Practitioner's Guide to M(eow)ti Turn Agentic ReinfOrcement learning
A streamlined and customizable framework for efficient large model (LLM, VLM, AIGC) evaluation and performance benchmarking.
A self-improving RLM agent for coding workflows and long-running autonomous tasks.
Orchard-Agentic is a collection of open-source work on agentic modeling
Framework for evaluating and improving agents
A persistent workspace for development work that self-improves and continues beyond one session.
A standard API for single-agent reinforcement learning environments, with popular reference environments and related utilities (formerly Gym)