Tag

Cosmos-Framework

End-to-end Python framework for training and serving NVIDIA's Cosmos world models (Cosmos3), integrating distributed training (FSDP/TP/CP/PP), DCP/safetensors checkpoints, dataset adapters, multiple inference backends, online serving, and agent skills.

Qwopus3.6-27B-v2-MTP

Fine-tuned reasoning model that speeds up structured multi-step outputs using Multi-Token Prediction (MTP) from a Qwen3.6-27B base. Produces more concise, faster generations for coding, DevOps, math, and constrained-format tasks; experimental community release for research and evaluation.

Fara1.5-27B

Automates end-to-end web workflows from browser screenshots by emitting pixel-grounded actions (click, type, scroll, visit, search). Vision-first multimodal agent fine-tuned from Qwen3.5-27B with critical-point safety checks; intended for sandboxed, human-supervised deployments.

Kun

Local-first AI agent workspace that unifies coding, writing, design, research and automation under one runtime shared between a desktop GUI and a terminal TUI. Features Agent Graph for long-running, auditable workflows, multi-provider model support, and local-by-default data storage.

Kimi Code CLI

Terminal-native AI coding agent that reads and edits code, runs shell commands, searches files, fetches web pages, and determines next steps from interactive feedback. Delivered as a single-binary TUI with video input, subagents, a plugin marketplace, and IDE (ACP) integration.

Defending Code Reference Harness

Runs a multi-stage, Claude-powered pipeline to find, verify, triage, and generate patches for code vulnerabilities, plus interactive skills for threat modeling and customization. Default harness targets C/C++ memory bugs using ASAN inside Docker/gVisor; autonomous runs execute target code and require sandboxing.

Qwen3.7 Max Pi Traces

Provides raw newline-delimited JSON agent traces where assistant responses were generated by qwen/qwen3.7-max, captured with Teich; includes 47 JSONL files, an embedded tools schema snapshot, and conversion guidance for supervised fine‑tuning and distillation.

Keye-VL-2.0-30B-A3B

Performs hour-scale video understanding and fine-grained temporal localization while exposing agent-style multimodal tool/code/search abilities. Built on a sparse-attention long-context architecture (DSA) and a specialized inference stack—best used in GPU-backed research or production evaluation.

ADHD — a skill for coding agents

Spawns parallel, isolated LLM reasoning frames, then scores, clusters and prunes ideas to avoid premature convergence. Packaged as a reusable Claude/Codex agent skill with CLI and TypeScript APIs for ideation, design decisions and fuzzy debugging.

Gajae-Code

Runs an external, reviewable coding-agent harness that turns intent into repeatable software work: clarifies requirements, builds reviewed plans, executes in tmux-backed sessions, and collects durable verification. Ships Telegram/Discord delivery, a research REPL, and optional desktop-control tools; beta-stage.

Skill0.5: Joint Skill Internalization and Utilization for Out-of-Distribution Generalization in Agentic Reinforcement Learning

Combines internalizing general skills with task-specific skill utilization via a difficulty-aware router to improve in-distribution and out-of-distribution performance for agentic RL. Uses privileged distillation for hard tasks and diagnostic probing for easy tasks; evaluated on ALFWorld and WebShop.

A Matter of TASTE: Improving Coverage and Difficulty of Agent Benchmarks

Proposes TASTE, an automatic pipeline that synthesizes challenging agent benchmark tasks by sampling and evolving valid tool-sequence patterns; uses an adaptive contrastive n-gram model and LLM validity judgments to produce τ^c-Bench with broader tool-use coverage and higher difficulty.