Library
85,340 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
EGC
MCP serversEGC gives every AI coding agent the same brain. Shared memory, skills, and live context across Cursor, Claude Code, Copilot, Aider, and 29 AI coding tools with zero configuration. Every tab, terminal, and AI stays automatically synchronized. One brain. Everywhere.
git clone https://github.com/Fmarzochi/EGC.git -
llmslim
MCP serversLong-term memory for AI agents with no LLM call: an MCP server and Claude Code plugin, plus local-first context compression for LLM apps.
git clone https://github.com/Thanatos9404/llmslim.git -
CorvinOS
SkillsSelf-hosted agentic OS — a Vibe-Engineering platform for Builders. Connect Claude Code Agent to Discord, Telegram, WhatsApp, Slack & Email. EU AI Act 2026 & GDPR compliance by architecture.
git clone https://github.com/CorvinLabs/CorvinOS.git -
agentic-os
PromptsGovernance framework for AI coding agents. It runs them through a five-step workflow (plan, build, review, test, ship) where no step counts as done without evidence. Drop-in rules and guardrails for Claude Code, Codex, Cursor, Copilot, and Antigravity, via AGENTS.md.
git clone https://github.com/KbWen/agentic-os.git -
tachibot-mcp
MCP serversMulti-model AI orchestration with 31 tools, YAML workflows, and 5 token-optimized profiles.
tachibot-mcp@2.0.5 -
YouTube Data
MCP serversYouTube MCP server for token-optimized, structured data using the YouTube Data API v3.
@kirbah/mcp-youtube@1.1.16 -
kirbah-mcp-youtube
MCP serversProvide token-optimized, structured YouTube data to enhance your LLM applications. Access efficien…
-
StackOne
MCP serversGive AI agents 30,000+ safe, token-optimized actions across Workday, SAP, Oracle + hundreds more.
-
nab
MCP serversToken-optimized HTTP client for LLMs: fetches any URL as clean markdown. CLI and MCP server.
nab@0.12.6 -
CoalWash
SkillsMemory washer/defragmenter for AI agent memory: class-B semantic wash (fidelity-gated, blocks any structured-token drop, snapshot+rollback) and class-A byte-identity session estate (ULTRA archive/restore, RE-TIER) - never semantic-edited. Cleans the FAT, never the MEAT. Slows memory-overhead growth; does not eliminate it. Zero-dependency.
git clone https://github.com/TheColliery/CoalWash.git -
CoalTipple
SkillsSafe, quality-gated model+effort router for Claude Code - delegates cheap work down to save tokens, escalates hard/sensitive work up through a verify staircase, never-down gate, and fail-safe Lock, up to a consent-gated fable top rung. Not the cheapest router; the safest one inside Claude.
git clone https://github.com/TheColliery/CoalTipple.git -
DevProjex
MCP serversTurn any folder or Git repo into safe, token-efficient context for LLMs, AI chats, and coding agents like Claude Code, Codex, and Cursor — local-first GUI, TUI, CLI, and a read-only MCP server with Live Context, agent journal, Smart Ignore, secret/PII redaction, Git scopes, and code compression. Windows, macOS, Linux.
git clone https://github.com/Avazbek22/DevProjex.git -
deepcrew
Skills🤿 The cheapest multi-agent workforce that is actually user-friendly: 7.7x more productive and 50x cheaper compared to your ultracode mode, an intelligent multi-agent swarm of Claude Code agents on DeepSeek or other providers, integrated with your own Claude Code or Codex.
git clone https://github.com/KuiyiGao/deepcrew.git -
delegate-router
SkillsClaude Code and Codex CLI skill: an LLM router that delegates bulk, already-decided coding tasks to another model you already pay for (GPT via Codex, Gemini via agy, a Claude Opus subagent), on another subscription first. Benchmark-checked routes, cost per task measured on a bench, cross-model review. The host verifies every diff.
git clone https://github.com/pvjbuilds/delegate-router.git
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.