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
-
ARIS-Movie-Director
SkillsAgentic, long-horizon visual generation: a fuzzy story → a cross-model-audited image-based movie. Brings ARIS's research-wiki + multi-agent debate to multimodal generation (intelligence lives in the agent; the diffusion model just renders). Image-based today, video next.
Source for ARIS-Movie-Director (opens github.com) git clone https://github.com/wanshuiyin/ARIS-Movie-Director.git -
16 Claude Code skills for data engineers: profile a new source, investigate a failed run, review a change, document the platform. Most end in a page you can share.
Source for claude-code-data-engineering-skills (opens github.com) git clone https://github.com/DataWithBaraa/claude-code-data-engineering-skills.git -
kimi-code-mcp
MCP serversMCP server for Claude Code × Kimi Code CLI 2.4.1 — default model k3 (up to ~1M on eligible plans); kimi-for-coding = K2.8 Preview. Delegate bulk reads to Kimi, cut Claude-side tokens.
Source for kimi-code-mcp (opens github.com) git clone https://github.com/howardpen9/kimi-code-mcp.git -
Zhiji LLM Router — Signal Gateway
MCP serversLLM routing and A-share market phase signals via LG framework.
-
bpfix
SkillsMaking eBPF verifier errors as friendly as Rust compiler errors, and let LLM fix it.
Source for bpfix (opens github.com) git clone https://github.com/eunomia-bpf/bpfix.git -
llm-compliance-comparison-mcp
MCP serversLlm Compliance Comparison MCP Server by MEOK AI Labs
Source for llm-compliance-comparison-mcp (opens github.com) llm-compliance-comparison-mcp@1.0.13 -
llm-output-quality-monitor
MCP serversCloudflare Workers MCP server: llm-output-quality-monitor
-
ecotokens
MCP serversToken optimizer for Claude Code Gemini CLI & Qwen Code — compresses shell outputs via PreToolUse hook, tracks USD savings in TUI dashboard
Source for ecotokens (opens github.com) git clone https://github.com/hansipie/ecotokens.git -
curie
SkillsOpen-source, self-hostable platform that turns agents into co-workers. Start with Software Factory: delegate GitHub issues and review pull requests, with model, approval, and cost controls in your infrastructure.
Source for curie (opens github.com) git clone https://github.com/curie-eng/curie.git -
knolo-core
AI repositoriesThe open framework AI agents use to share knowledge with one another. Pack knowledge into a portable, verifiable Knowledge Image, pin it by digest, mount it locally over MCP, and prove what was used. Local-first, deterministic, no vector DB required.
Source for knolo-core (opens github.com) git clone https://github.com/HiveForensics-AI/knolo-core.git -
genpark-hub
SkillsGenPark & OpenClaw Premium Growth Hub, Showcase and Live Skill Generator.
Source for genpark-hub (opens github.com) git clone https://github.com/alphaparkinc/genpark-hub.git -
borer
MCP serversReverse engineering, rebuilt for AI agents. A pure Rust engine your agent drives over MCP.
Source for borer (opens github.com) git clone https://github.com/imjustprism/borer.git -
nativeprompt
PromptsПроверяет промпты и файлы инструкций (CLAUDE.md, AGENTS.md, скиллы) по правилам вашей модели: Claude Fable 5.2, Opus 5.5, Sonnet 5.5, Haiku 5.5, GPT-6 и 6.1, Codex, Gemini CLI. Советует уровень усилий. Каждый совет со ссылкой на документацию вендора. Без API-ключей и зависимостей, офлайн.
Source for nativeprompt (opens github.com) git clone https://github.com/edvardgrishin27/nativeprompt.git -
llm-advisor
MCP serversReal-time LLM/VLM benchmarks, pricing, and recommendations. 300+ models, 5 sources.
Source for llm-advisor (opens github.com) llm-advisor-mcp@0.4.5 -
reins
Agents & frameworksA lightweight agent harness you bolt onto your app so an LLM can operate it — safely, and cheaply.
Source for reins (opens github.com) git clone https://github.com/shamspias/reins.git -
aiwkf
SkillsAgents, skills and plugins I use daily to code with AI. A living Claude Code marketplace, also compatible with Codex.
Source for aiwkf (opens github.com) git clone https://github.com/k8adev/aiwkf.git -
suede-creator-skills
SkillsOpen-source skills for Claude Code and Codex, with an MCP server, a PyPI package and Suede Awesome Everything, a directory that scores AI agent skills 0 to 99. Created by Jason Colapietro, founder and CEO of Suede AI.
Source for suede-creator-skills (opens github.com) git clone https://github.com/JasonColapietro/suede-creator-skills.git -
radin
Skills🐀 agentic software factory for those who have to save tokens
Source for radin (opens github.com) git clone https://github.com/shortcuts/radin.git -
sansheng-write
SkillsClaude Code skill for Chinese long-form & WeChat article production · 中文长文与公众号内容生产
Source for sansheng-write (opens github.com) git clone https://github.com/sanshengai/sansheng-write.git -
AxioDB
MCP serversEmbedded NoSQL Database for TypeScript & AI Agents. Zero-native document database with ACID transactions & in-memory cache — verified on Node.js & Bun.
Source for AxioDB (opens github.com) git clone https://github.com/nexoral/AxioDB.git -
Routara LLM Gateway
MCP serversOpenAI-compatible LLM, image and video APIs via Routara (api.routara.ai).
Source for Routara LLM Gateway (opens github.com) routara-mcp@1.0.1 -
llm-oracle
MCP serversUp-to-date LLM pricing + availability catalog with cited sources for AI agent routing.
Source for llm-oracle (opens github.com) @weiseer/llm-oracle-mcp@0.2.0 -
android-use
MCP serversGive AI agents fast, bounded access to a real Android device or emulator. MCP server and CLI for Claude Code, Codex, Cursor, and more.
Source for android-use (opens github.com) git clone https://github.com/austinintelligence/android-use.git -
agent-fleet-o
Agents & frameworksOpen-source AI agent orchestration platform — self-hosted mission control for autonomous multi-agent systems. Visual DAG workflows, 670+ MCP tools, human-in-the-loop approvals. Works with Claude, GPT-4o, Gemini, Ollama, Codex.
Source for agent-fleet-o (opens github.com) git clone https://github.com/escapeboy/agent-fleet-o.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.