Tag

Harness

Turns a domain description into a Claude Code agent team and the skills they use — auto-generates agent definitions and skill files from six pre-defined team-architecture patterns. Best for teams building structured multi-agent workflows on Claude Code.

Codex plugin for Claude Code

Integrates Codex into Claude Code so you can run read-only code reviews, steerable adversarial reviews, and delegate long-running tasks to a local Codex instance via slash commands. Uses the local Codex CLI/app server and Node.js; designed for developers who want seamless handoff between Claude Code and Codex.

Video-Oasis: Rethinking Evaluation of Video Understanding

Provides a diagnostic suite that audits video-understanding benchmarks to find samples solvable without visual or temporal input, filters those shortcuts, and produces a distilled video-native testbed that reveals major capability gaps in current Video-LLMs.

Graphify

Maps a codebase plus docs, PDFs, media and configs into a local, queryable knowledge graph; parses code with a local tree-sitter AST (no LLM), uses configurable backends for semantic extraction of non-code, and outputs graph.json, graph.html and a brief report.

Granite-4.1-8B

An 8B-parameter, instruction-tuned long-context LLM optimized for instruction following, tool-calling, and multilingual dialogue — supports 131072-token context and common NLP tasks such as summarization, QA, code, and RAG.

Zero-to-CAD 100K

Curated 100K subset of geometrically diverse CAD construction sequences sampled from a 1M agentically synthesized corpus — each item includes executable CadQuery scripts, 8 rendered views, STL/STEP exports, and precomputed DINOv3 embeddings for retrieval and benchmarking.

Memtrace

Turns a codebase into a live structural knowledge graph that coding agents can query in milliseconds. Bi-temporal, replay-aware indexing of symbols and relationships performed locally with zero LLM API calls; Rust-native, MCP-native integrations and fast incremental updates.

Zero-to-CAD 1M

Provides one million executable, human-readable CadQuery construction sequences synthesized by an LLM-in-the-loop—each sample includes renders, STL/STEP exports, precomputed DINOv3 embeddings and a FAISS index. Designed for training and benchmarking text/image→3D and CAD-program generation models (Apache-2.0).

SWE-ZERO 12M Trajectories

Provides ~12.29M execution‑free agentic coding trajectories (≈112B tokens) sampled from 122K GitHub PRs to mid‑train code and agent models. Uses bash-only actions (grep, git, sed, etc.) so it scales without Docker; trajectories are unverified and intended for mid-training rather than final SFT.

Open-SWE-Traces

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.

SWE-Hero Trajectories (nvidia/SWE-Hero-openhands-trajectories)

Provides 34k execution-style agent trajectories (11,766 issues) for supervised fine-tuning of code-focused LLMs. Each instance includes multi-step interactions, tool-call records, and final unified diffs; generated with Qwen3-Coder and released under permissive licenses for commercial use.

Terax

Terminal-first developer workspace with an agentic AI side-panel that runs against your API keys or local models. Bundles a native PTY terminal, CodeMirror editor with AI edit diffs, file explorer, git history/graph, and a web preview in a ~7–8MB desktop app with no telemetry.