Library
88,222 resources from 11 public sources. 54 checked by hand. The rest are indexed automatically and not reviewed.
Results
Looks like a goal we have a starting path for: I want to research potential clients
-
geml
SkillsGEML is a lightweight markup language with uniform, addressable blocks and standard verbs. Easy for humans to read, safe for agents to mutate.
Source for geml (opens github.com) git clone https://github.com/geml-spec/geml.git -
mcp-geo
MCP serversTrack brand citations across seven AI search surfaces. Free OSS/self-host; optional EUR 99 client-ready audit.
Source for mcp-geo (opens github.com) git clone https://github.com/AKzar1el/mcp-geo.git -
Tellurion
Agents & frameworksMission control for AI coding agents. Watch Claude Code, Codex, Gemini and a dozen more work live in one macOS terminal: live status, an editor that follows their edits, undo for any turn, approvals from your phone and local models. 20+ built-in tools, all on the site below. Built on Ghostty.
Source for Tellurion (opens github.com) git clone https://github.com/steventsvik/Tellurion.git -
gomaa
MCP serversGomaa — Autonomous Agent Memory OS. Persistent memory system for AI agents with Obsidian vault integration, hybrid RRF search, knowledge graphs, security gates, and MCP server.
Source for gomaa (opens github.com) git clone https://github.com/M4F-S/gomaa.git -
tale
SkillsOpen-source project workspace for teams and AI agents. Assign tasks, coordinate agents in persistent sandboxes, and review results together. Self-hosted or managed cloud.
Source for tale (opens github.com) git clone https://github.com/tale-project/tale.git -
SkillFM LLM Cost Optimizer
MCP serversLLM cost optimizer for OpenAI, Anthropic, token usage, BYOK, and SkillFM Beacon audits.
Source for SkillFM LLM Cost Optimizer (opens github.com) @skillfm/llm-cost-optimizer-mcp@0.1.0 -
llm-wiki-mcp
MCP serversMCP server for Karpathy-style LLM wikis: persistent markdown your agent grows over time.
Source for llm-wiki-mcp (opens github.com) llm-wiki-mcp@0.1.1 -
LLM Sandbox
MCP serversSecurely run LLM-generated code in isolated containers across 7 languages and 3 container backends.
Source for LLM Sandbox (opens github.com) llm-sandbox@0.3.43 -
LLM Prover
MCP serversLLM evaluation: compare models on cost and quality, score outputs, run benchmarks, analyse agents.
-
Narev LLM Pricing
MCP serversLLM pricing, provider and gateway rates, pricing tiers, and inference cost calculations.
-
pidog-embodiment
MCP servers🐕 Give your AI a physical body — speak German/French/English, it understands locally (Ollama or zero-LLM keyword mode) and acts. MCP server included: Claude Code/Desktop as the robot's brain. Brain/Body over HTTP for SunFounder PiDog, robot cars, any hardware. No cloud. Try it without a robot: install.sh --mock
Source for pidog-embodiment (opens github.com) git clone https://github.com/rockywuest/pidog-embodiment.git -
awesome-claude-code
SkillsAwesome Claude Code And Agent Tools
Source for awesome-claude-code (opens github.com) git clone https://github.com/cooler333/awesome-claude-code.git -
Orca-AI-Incident-Archive
MCP serversAn open database of real-world AI agent incidents.
Source for Orca-AI-Incident-Archive (opens github.com) git clone https://github.com/Continuum-AI-Corp/Orca-AI-Incident-Archive.git -
Nosis
Agents & frameworksNosis is a lightweight personal agent runtime: per-session execution boundaries with OS-level sandboxing, computer use, a full built-in toolset, Skill / Plugin / MCP extensions, one runtime shared by GUI and TUI, and file-persisted sessions, plans, and memory.
Source for Nosis (opens github.com) git clone https://github.com/EvannZhongg/Nosis.git -
claude_code_vs
Tools & appsBring Claude Code to Visual Studio 2026: A native diff with accept/reject, a live debugger Claude can drive autonomously, Roslyn code navigation, and Test Explorer integration. The IDE half of Claude Code's integration protocol. Community-built, unofficial.
Source for claude_code_vs (opens github.com) git clone https://github.com/firish/claude_code_vs.git -
llms-txt-validator
MCP serversValidate a site's llms.txt against the spec: fetches every linked URL, scores it 0-100.
-
claude-ros2-skills
SkillsClaude Code skills for ROS 2 Jazzy — establish the unknowns first, verify against the installed system, prove the result ran.
Source for claude-ros2-skills (opens github.com) git clone https://github.com/Leehyunbin0131/claude-ros2-skills.git -
topcited-skills
SkillsTopCited Agent Skills: SEO/GEO knowledge, the TopCited API, and a guided visibility workflow — installable into Claude Code and other agents.
Source for topcited-skills (opens github.com) git clone https://github.com/TopCited/topcited-skills.git -
nimblebrain
MCP serversSelf-hosted platform for MCP Apps and agent automations — tools, interactive UIs, scheduled runs, multi-agent delegation.
Source for nimblebrain (opens github.com) git clone https://github.com/NimbleBrainInc/nimblebrain.git -
tolato
MCP serversAI agent for server management — chat in natural language to run commands, monitor metrics & probe network across your fleet. Self-hosted, MCP-ready. Go + Vue.
Source for tolato (opens github.com) git clone https://github.com/momaek/tolato.git -
consensus-mcp
MCP serversOfficial Consensus MCP server. Semantic search over 400M+ research papers, including all of PubMed, for Claude, ChatGPT, Cursor and any MCP client.
Source for consensus-mcp (opens github.com) git clone https://github.com/Consensus-NLP/consensus-mcp.git -
agent-skills
SkillsFive SKILL.md files that give AI agents UX expertise: evaluate interfaces, detect UX smells, audit AI interfaces, check flows. For Cursor, Windsurf, Claude Code and kx
Source for agent-skills (opens github.com) git clone https://github.com/uxuiprinciples/agent-skills.git -
TokenSqueezer LLM Token Compressor
MCP serversx402-gated LLM token compressor: strip filler, collapse JSON, densify prose. Paid in USDC.
Source for TokenSqueezer LLM Token Compressor (opens github.com) @nodeproxy/tokensqueezer@0.1.1 -
Cheapest LLM API
MCP serversCompare LLM API prices, search models and providers, and access reviewed benchmark results.
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.