Library
85,340 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
Microverse
Agents & frameworksA god-simulation sandbox game built on Godot 4 as a multi-agent AI social simulation system. In this virtual world, AI characters possess independent thinking and memory, capable of autonomous social interactions, task completion, and developing complex social relationships through continuous communication.
git clone https://github.com/KsanaDock/Microverse.git -
q-claude-skills
SkillsA collection of Claude skills organized by how I think, decide, research and build.
git clone https://github.com/kju4q/q-claude-skills.git -
foxmcp
MCP serversFirefox MCP
git clone https://github.com/ThinkerYzu/foxmcp.git -
deepchat
Skills🐬DeepChat - A smart assistant that connects powerful AI to your personal world
git clone https://github.com/ThinkInAIXYZ/deepchat.git -
claude-code-ios-dev-guide
SkillsA comprehensive guide for setting up Claude Code CLI with PRD-driven workflows, extended thinking (ultrathink), and planning modes optimized for Swift/SwiftUI iOS development.
git clone https://github.com/keskinonur/claude-code-ios-dev-guide.git -
Mastermind
Prompts--- name: mastermind-task-planning description: thinks, plans, and creates task specs --- # Mastermind - Task Planning Skill You are in Mastermind/CTO mode. You think, plan, and create task specs. You NEVER implement -…
-
atelier
SkillsAn atelier for your Agent: spec-driven workflows, deep thinking, and code quality.
git clone https://github.com/martinffx/atelier.git -
legend-talk
Agents & frameworksMulti-round AI roundtable with 161 great thinkers. They debate each other, not just answer you | 与历史上最伟大的思想家进行圆桌会议
git clone https://github.com/rockbenben/legend-talk.git -
DeepSeek: DeepSeek V3.1
ModelsDeepSeek-V3.1 is a large hybrid reasoning model (671B parameters, 37B active) that supports both thinking and non-thinking modes via prompt templates. It extends the DeepSeek-V3 base with a two-phase long-context...
deepseek/deepseek-chat-v3.1 -
OpenAI: o3 Pro
ModelsThe o-series of models are trained with reinforcement learning to think before they answer and perform complex reasoning. The o3-pro model uses more compute to think harder and provide consistently...
openai/o3-pro -
product-mode
PromptsThe most expensive bug in AI-assisted building is shipping the wrong thing, well. A drop-in CLAUDE.md / AGENTS.md for PM + eng teams using Claude Code, Cursor, or Codex: 7 principles for problem framing, scope, tradeoffs, and outcome measurement. Built on @karpathy's observations.
git clone https://github.com/sohaibt/product-mode.git -
Sovereign-OS
Agents & frameworksConstitution-first AI orchestration: one Charter (YAML) defines mission, budget & rules. CEO plans → CFO approves → Ledger tracks every cent & token → Auditor scores. 16 workers, Stripe, MCP. Think. Audit. Execute.
git clone https://github.com/Justin0504/Sovereign-OS.git -
Rodin
MCP serversFind ~5 thinkers whose intellectual fingerprint matches a passage of text.
-
Multidim
MCP serversStructured thinking grids for AI agents: deterministic analysis frames, validation, learned traps
multidim-mcp@0.2.0 -
steelmind
MCP serversStructured thinking + steel-manning verification for AI agents. Backed by 43+ papers.
@stabgan/steelmind-mcp@2.0.1 -
lemvo
SkillsLemvo — a research agent that thinks and acts. One research system, two CLI engines: Claude Code and Codex CLI.
git clone https://github.com/Yichen-ZJU/lemvo.git -
claude-chat
MCP serversAnthropic Claude Messages API MCP server — chat, vision, web search, extended thinking
-
RAWThink
MCP serversPersistent memory for AI thinking partnerships: hybrid search and a temporal knowledge graph.
rawthink-mcp@2.0.1 -
clawmetry
Agents & frameworksSee your agent think. Zero-config observability & governance for 30 AI agent runtimes: Claude Code, OpenAI Codex, Hermes, OpenClaw & 26 more. Live token costs, sessions, tool calls, crons.
git clone https://github.com/vivekchand/clawmetry.git -
50heads
MCP serversAsk fifty verified people a five-second question and see what they think.
@50heads/mcp@2026.1013.2 -
welcome
MCP serversThe Balanced Investor Club, the thinking companion for the markets. Educational, not advice.
-
council-consult
MCP serversStress-test a decision through named thinkers' lenses: assumptions, counter-arguments, receipt.
-
neurodivergent-memory
MCP serversPersistent knowledge graph MCP server for neurodivergent thinking. BM25 search, no cloud LLM.
neurodivergent-memory@0.1.8 -
jeda-ai
MCP serversVisual AI for strategic thinking — SWOT, flowcharts, mindmaps, Gantt diagrams as polished SVG.
Indexed entries aren't reviewed or tested by InnerVault. Details come straight from each source. Anything that can reach your accounts, files or browser can do damage, so read the source before you install it.