Library
86,235 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
PhysGym
Datasets & benchmarksA benchmark suite for evaluating LLM-based interactive scientific reasoning.
git clone https://github.com/principia-ai/PhysGym.git -
Actor Pipeline Runner (Chain Actors in One Run)
MCP serversRun up to 25 Apify Actors in order in one call, passing each step's dataset to the next.
-
Extract text, tables and metadata from every PDF linked in a dataset, CSV or Google Sheet.
-
vicoa
Agents & frameworksVicoa is the agentic IDE for running a team of coding agents from desktop, mobile, VPS. Open-source, self-hostable.
git clone https://github.com/vicoa-ai/vicoa.git -
fondue
Skills🫕 One pot, everyone brings a fork, no double-dipping. A team of AI agents that plan, build and review each other's work, with you as the team lead. Spec-driven development and bug hunting for Claude Code.
git clone https://github.com/jsobolewski1/fondue.git -
Roqer
MCP serversAn open-source AI agent for Roblox Studio. Builds, scripts, and playtests in your place using your ChatGPT/Claude subscription or custom API.
git clone https://github.com/S4US/Roqer.git -
casecite
Agents & frameworksCaseCite is an open-source, self-hosted legal RAG caselaw research & document analysis platform.
git clone https://github.com/thomasunise/casecite.git -
console
MCP serversOpen-source, self-hosted AI gateway and control plane: OpenAI-compatible LLM routing, RAG, an MCP hub, guardrails and agent tracing for multi-tenant teams.
git clone https://github.com/Cognipeer/console.git -
seobuild-onpage
SkillsSEOBuild Onpage - The first AI agent that writes pages Google ranks AND LLMs cite. One command in, ranking page out. Built on DeerFlow, powered by 2026 SEO + GEO strategies tested / working. Forensic competitive analysis, 500-token chunk architecture, entity consensus, verification tags. BYOK GSC, DataforSEO. Works w/ OpenClaw, Claude Code, Codex
git clone https://github.com/gbessoni/seobuild-onpage.git -
ollama-benchmark
Datasets & benchmarksOllama based Benchmark with detail I/O token per second. Python with Deepseek R1 example.
git clone https://github.com/LarHope/ollama-benchmark.git -
awesome-jev
SkillsJev demos, projects, SDKs and skills, with source links and a curated X gallery.
git clone https://github.com/Amal-David/awesome-jev.git -
ephemora-cell
MCP serversEphemeral, stateless, capability-bound execution for untrusted AI and agent-generated code.
git clone https://github.com/MichaelS1011/ephemora-cell.git -
GDPevo
Datasets & benchmarksA Benchmark for Evaluating Agent Self-Evolution on Real Business Tasks
git clone https://github.com/Prism-Shadow/GDPevo.git -
BusterX
Datasets & benchmarks[NeurIPS '26] BusterX & [EACL '27 Findings] BusterX++
git clone https://github.com/l8cv/BusterX.git -
lattice
MCP serversBounded repository context and verified patches for Codex and Claude Code. Explicit edit grants, source fingerprints, isolated worktrees, acceptance checks, and reproducible paired benchmarks.
git clone https://github.com/moulwyse/lattice.git -
laya
Agents & frameworksLaya is an open-source, local-first AI notification command center that aggregates Slack, Gmail, GitHub, Jira, Notion, Outlook, Calendar (and more) notifications using local LLMs via Ollama and LM Studio. Supports cloud models via BYOK.
git clone https://github.com/aayushch/laya.git -
Cloud IDS API
Public APIsCloud IDS (Cloud Intrusion Detection System) detects malware, spyware, command-and-control attacks, and other network-based threats. Its security efficacy is industry leading, built with Palo Alto Networks technologies. When you use this product, your organization name and consumption levels will be shared with Palo Alto Networks.
-
canvas-design
SkillsCreate beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.
/plugin marketplace add anthropics/skills -
Carmack-Council
SkillsMulti-agent Claude Code skill for building apps and stuff
git clone https://github.com/SamJHudson01/Carmack-Council.git -
C.R.I.S.P
SkillsCRISP — The missing layer between vibe coding and building something people actually want.
git clone https://github.com/radekamirko/C.R.I.S.P.git -
opencode-primer
PromptsMaster OpenCode, the open-source AI coding agent — setup, agents, skills, plugins, MCP, Zen & headless CI.
git clone https://github.com/wesammustafa/opencode-primer.git -
nightshift
Agents & frameworksAccountable long-running coding shifts for Cursor, Codex, and Claude Code. Safe autonomy, recovery, persistent state, and reviewable results a clear view of what’s done, in progress, parked, or blocked—without scrolling a marathon chat.
git clone https://github.com/orwa-mahmoud/nightshift.git -
glowup-ui
SkillsAn open-source design skill for AI coding agents. Create beautiful apps, transform existing UIs, and refine designs without breaking functionality.
git clone https://github.com/avivgerz-hue/glowup-ui.git -
digital-oracle
SkillsAI agent skill that answers macro questions — housing, gold, BTC, geopolitics — with probability estimates mined from 13 financial data sources (Polymarket, Kalshi, CFTC, SEC & more). For Claude Code / Cursor / Codex / OpenClaw. | 让 AI Agent 从金融数据中挖掘宏观趋势的数字先知
git clone https://github.com/komako-workshop/digital-oracle.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.