Provides 207k+ LLM-generated agent trajectories of code edits and tool interactions for training and evaluating software-engineering agents. Collected via OpenHands and SWE-agent using Qwen3.5-122B and MiniMax-M2.5, multilingual across nine languages and released under CC BY 4.0.
Generates editorial-quality diagrams as self-contained HTML files with inline SVG across 27 visual types; includes brand onboarding, agent-skill integrations (Claude Code, Codex, Pi), draw.io/Mermaid import, and static-first output with optional accessible motion.
A healed 64-layer 'frankenmerge' that stacks two Qwen3.5-derived finetunes into an ~18B GGUF model for multilingual text generation, reasoning, and reliable code/frontend output. Healed with a 1000-step QLoRA to reduce layer-boundary artifacts and targeted to run on 12–16 GB GPUs.
Connects an LLM to a real browser over an editable CDP websocket so the agent can drive clicks, navigation, and generate missing helper code during tasks. The harness self-heals by writing reusable helpers, supports local or cloud browsers, and can optionally record sessions for debugging.
Orchestrates multiple LLM-backed agents locally using tmux and per-role git worktrees, converting role prompts into coordinated development workflows. Key features: configurable two-/four-/six-pack workflows, a durable handoff protocol, per-role backend selection and observable terminals.
Runs goal-driven penetration tests by orchestration of an LLM agent and an MCP toolchain to perform reconnaissance, vulnerability discovery, exploitation, and structured PoC/report generation; supports multiple LLM providers and local MCP integrations; for authorized security testing only.
Turns natural-language design briefs into deliverable web pages, app prototypes, slide decks, animations, and infographics. Its multi-direction workflow, brand-asset rules, and design checks help coding agents produce more distinctive visual work.
Monitors and detects risky behavior in enterprise AI agents via high-fidelity telemetry, security benchmarking, and a two-tier detector. Comprises ADR Sensor, ADR-Bench, and ADR Detector; deployed in production at Uber and validated on public benchmarks.
A 27B multimodal causal language model with a vision encoder and native long-context support (262,144 tokens). Optimized for repository-level coding agents and multimodal understanding; includes preserved "thinking" traces, multi-token prediction (MTP), and deployment recipes for vLLM / SGLang / Transformers.
FP8-quantized 27B multimodal Qwen3.6 model weights in Hugging Face Transformers format — supports image/text/video inputs, native 262k token context (extensible to ~1M), and is compatible with vLLM/SGLang/KTransformers for efficient local serving and research.
A curated collection of production-ready Agent Skills that turn tasks—presentation production, image generation, local KB retrieval, article assembly, and web-design—into agent-loadable skill folders. Uses a SKILL.md contract, supports multiple agent runtimes (Claude Code, Cursor, Codex), and offers modular install paths with pinned release zips.
Runs a local-first AI agent runtime that drives your desktop and automates workflows — browsing, file edits, approved shell commands, document extraction, and scheduled tasks — while integrating local or cloud LLMs (llama.cpp/TurboQuant) and embedding as an HTTP service or Tauri sidecar.