Toward Autonomous Scientific Discovery

Open-source desktop SQL workspace with 3 built-in database drivers and 26 shipped driver plugins, including SQL Server, DuckDB, ClickHouse and Redis. Built-in MCP server for Claude, Cursor and Devin, SQL notebooks and visual EXPLAIN.

ARIS ⚔️ (Auto-Research-In-Sleep) — Lightweight Markdown-only skills for autonomous ML research: cross-model review loops, idea discovery, and experiment automation. No framework, no lock-in — works with Claude Code, Codex, OpenClaw, or any LLM agent.

39 MCP servers (488 tools) that give AI agents the Iranian web: Digikala, Torob, Divar, Snappfood, Jabama, MrBilit, Paziresh24, Taaghche, laws, tax, crypto, stocks, news and more. Prices in Toman.

36 MCP servers (469 tools) that give AI agents the Iranian web: Digikala, Torob, Divar, Snappfood, Jabama, MrBilit, Paziresh24, Taaghche, qavanin.ir laws, tax, news and more. Prices in Toman.

deepseek harness对话和代码状态回退插件 | DSH — rewind conversation and workspace state, powered by a persistent Change Ledger

Compare multiple skills on the same task and pick the winner.

MCP server for reading, editing, and comparing Word (.docx) and OpenDocument (.odt) files with tracked changes. For Claude, Gemini CLI, Cursor, and any MCP client. Apache-2.0 licensed.

Find the cheapest API for any model and connect it from your AI agent: Grandet Skill and an anonymous MCP server, backed by listed prices from 1,800+ official, inference and relay providers on grandet.ai.

Excel MCP server: let AI (Claude, Cursor, Codex) create and edit Excel files with charts, PivotTables, slicers and formulas. No Excel required.

PhD Research Skills for Claude Code: paper reproduction, experiment design, paper review, result comparison and more.

PhD Research Skills for Claude Code: paper reproduction, experiment design, paper review, result comparison and more.

Claude Code plugin to see, review and iterate on your agent's work without leaving the terminal: show images, play videos, and run visual QA with Playwright recordings and before/after comparisons inside the Claude Code terminal. Works in any terminal that supports the kitty graphics protocol, fully cross-platform on macOS, Linux and Windows.

DeepSeek Harness 的执行迷宫——看 Agent 真实怎么干活：迷宫时间轴 · 数据轨道 · 确定性执行分析 · 多会话对比 | The execution maze for DSH agents: maze timeline, per-step data tracks, deterministic execution analysis, multi-session comparison. Formerly dsh-trace-compare.

Enables MCP hosts to spawn, supervise, and collect results from parallel panels of pinned-model OpenCode v2 agents for delegated tasks, reviews, and cross-model comparisons. Supports per-member roles, models, permissions, follow-up prompts, cancellation, and persisted result retrieval.

Statistics of Russian texts as tools for LLM agents, built on the ruTS library: readability with school grade and reader age, officialese, SEO metrics, verse meter and rhyme, lexical diversity, morphology, syntax, keywords, concordance, collocations and stylometric comparison. Every value comes with a description, a scale reading and warnings when it is unreliable for the text

MCP gateway & OAuth MCP servers. LangGraph agent: memory, eval/tracking, PII guard, context trimming. Docker quick start for enterprise agents.

LLM rankings from public benchmarks, model comparisons and source-linked results. Updated daily.