AI Client2026
Audits and reduces token waste in LLM sessions by compressing verbose outputs, checkpointing before compaction, and restoring lost context. Runs fully locally with zero telemetry and provides a live token dashboard plus plugins for Claude Code, OpenClaw and Codex.
AI Dataset2026
JSONL dataset of Claude Opus 4.6 chain-of-thought traces paired with high-difficulty math and logic problems for supervised fine-tuning and distillation; exposes step-by-step reasoning to teach process-oriented problem solving and improve math/logic accuracy in smaller LLMs.
AI Agent2026
A 23-skill Claude Code toolkit that composes an LLM-driven virtual engineering team (CEO, designer, eng manager, QA, security, release) into slash-command workflows — includes real-browser QA, a persistent GBrain memory, multi-agent integrations, and team auto-update semantics.
AI Client2026
Turns any codebase, documentation, or knowledge base into an interactive knowledge graph you can explore, search, and ask questions about. Produces node-level summaries, guided tours, and diff impact analysis, and plugs into multiple LLM platforms (Claude Code, Codex, Copilot, Gemini CLI) for query-driven exploration.
MCP Server2026
Curated marketplace of Claude Code plugins maintained by Anthropic, separating its own internally built plugins from vetted community submissions. Browse and install directly inside Claude Code via /plugin install {name}@claude-plugins-official.
AI Agent2026
Evaluates job postings and produces tailored CVs, cover letters, and interview prep using a Claude Code-driven agent workflow. Distinguishes itself with a drafter–reviewer loop, mandatory PDF compilation and ATS text-layer verification, plus extensible portal scrapers and LaTeX templates.
MCP Client2026
A read-only mirror of Anthropic's community plugin marketplace for Claude Cowork and Claude Code, listing vetted third-party plugins in a nightly-synced marketplace.json. Intended for discovering and installing community plugins via the Claude plugin system.
AI Client2026
Compresses LLM/agent replies into a terse “caveman” style to cut output tokens (~65–75%) while preserving technical accuracy. Offers per-agent skills, intensity modes, memory-compression and middleware to lower token cost and extend usable context.
AI Dataset2026
Provides 7,823 single-turn reasoning conversations generated by Anthropic's Claude Opus 4.7 and reformatted into Qwen-style chat templates for supervised fine-tuning (SFT). Includes explicit <think> chain-of-thought blocks and many long reasoning chains (avg ~4k tokens).
AI Dataset2026
Contains 8,124 reasoning conversations (extended-thinking + final responses) generated by Anthropic Claude Opus 4.7 for distillation into open-source LLMs. Each row stores the prompt, thinking trace, final answer and usage metadata; packaged under Apache‑2.0.
AI Dataset2026
Provides 2,405 chain-of-thought reasoning traces generated by Claude Opus 4.7 for hard math, science, and formal problems. Each record pairs a problem with the model's full <think> working and a polished answer; available as parquet splits for non-commercial research under Anthropic's usage policy.