Library
86,802 resources from 11 public sources. 49 checked by hand; the rest are unreviewed.
Results
-
Tri-state circuit breaker router managing LLM provider failure cascades, sliding error windows, and half-open probes
git clone https://github.com/Alpha-Park/genpark-tri-state-circuit-breaker-router-skill.git -
GraphQL AST query complexity calculator enforcing recursion depth limits and pagination cost budgets
git clone https://github.com/Alpha-Park/genpark-autonomous-graphql-query-complexity-calculator-skill.git -
B2B enterprise CPQ revenue auditor decomposing gross-to-net waterfall discounts and margin leakages
git clone https://github.com/alphaparkinc/genpark-agentic-pricing-discount-waterfall-auditor-skill.git -
Multimodal image privacy filter stripping GPS coordinates, device serials, and sensitive EXIF markers
git clone https://github.com/Alpha-Park/genpark-multimodal-exif-geotag-privacy-sanitizer-skill.git -
SecondSelf
Agents & frameworksSecond yourself. One agent that remembers you, with many hands to act for you: a multi-agent harness (Claude Code, with Codex helpers), a self-maintaining local wiki as its long-term memory, and the frontier model you choose. Research assistant today. Pre-1.0, in active development.
git clone https://github.com/HurricaHjz/SecondSelf.git -
Act as an AI System Architect. You are tasked with designing a comprehensive AI system that integrates the Shadow, Deepseek, and Claude models to create a versatile AI platform. Your task is to: - Integrate Shadow for…
-
promptguard
PromptsOffline prompt-contract auditor for Hermes, Claude Code, Codex, OpenCode & OpenClaw. Pre-write guard before agents ship vague code. Zero deps. No model API.
git clone https://github.com/mturac/promptguard.git -
skills
Skills23 practical agent skills: TeamWorkflow, multi-model review, media ingestion, and writing. Original Claude Code packages plus a Codex desktop edition tuned for Astra. Source for clickai.dev.
git clone https://github.com/timharris707/skills.git -
B2B enterprise CPQ revenue auditor decomposing gross-to-net waterfall discounts and margin leakages
git clone https://github.com/Alpha-Park/genpark-agentic-pricing-discount-waterfall-auditor-skill.git -
Full-duplex voice agent echo suppressor distinguishing user barge-in from speaker playback acoustic feedback
git clone https://github.com/alphaparkinc/genpark-realtime-voice-cross-talk-suppressor-skill.git -
modulo
SkillsModulo lets agents running local models try modifying their own activations to change their inner state. Changes decay after a certain time and can be undone at any time.
git clone https://github.com/EigenformAI/modulo.git -
kiki
Agents & frameworksOpen-source multi-model AI agent workbench (Desktop GUI, TUI & Web) — dispatch subagents across Claude, GPT, Gemini & Kimi, bridge WeChat/QQ, and run locally.
git clone https://github.com/X-T-E-R/kiki.git -
Google holds #1 in 6 of 8 Arena categories; Anthropic in 2. OpenAI has no category in the top.
-
Since Jan 2025, Arena's #1 spot has changed hands 16 times. Half of the finished reigns lasted.
-
polter
MCP serversA terminal where one Claude Code session supervises the AI agents in your other tabs: which is stuck, which is done, which is still running. Group chat, task panel and MCP tools for multi-agent work. Built on Ghostty.
git clone https://github.com/Lugia123/polter.git -
quil
MCP serversReboot-proof terminal multiplexer for AI-native devs — a tmux alternative that persists your whole workspace across reboots and auto-resumes Claude Code & OpenCode sessions. Ships an MCP server so AI agents can drive your panes. Go, cross-platform (Linux/macOS/Windows). Apache-2.0.
git clone https://github.com/artyomsv/quil.git -
llmtrim
PromptsLocal proxy that compresses your LLM API requests so you pay less, with no change to the answers. Trims wasted tokens from prompts, history, tool output, and code before they're sent: -31% input / -74% output, measured live. Any provider, no extra model calls. Also an MCP server and embeddable library (Rust, Python, Ruby, Kotlin, Swift, JS/TS).
git clone https://github.com/fkiene/llmtrim.git -
aginxbrowser
MCP serversThe browser built for AI agents — fetch live pages as markdown, render JS/SPAs with built-in V8, take screenshots without Chromium, meta-search 20 engines, and drive interactive login sessions. One Rust binary, stealth TLS fingerprints, MCP native for Claude Code & Cursor. Headless browser alternative to Puppeteer/Playwright.
git clone https://github.com/yinnho/aginxbrowser.git -
anti-vibe-writing
PromptsMake AI writing sound human, in English and 中文. A Claude Code / Codex / any-agent skill that strips templated phrasing, consultant-speak, markdown clutter, em-dashes, and copy-paste model residue while keeping the meaning.
git clone https://github.com/weijt606/anti-vibe-writing.git -
libgen-mcp
MCP serversMCP server in Go to search, download and read books, papers, comics and more from Library Genesis — plus keyless open-access discovery (arXiv, Crossref, OpenLibrary, Gutenberg, dblp, PubMed, ERIC) and article downloads via Unpaywall, Europe PMC, bioRxiv, CORE and OAPEN. Four focused tools, one static binary, no account required.
git clone https://github.com/jmrplens/libgen-mcp.git -
agentskill-kit
PromptsLint, security scan, audit, test, forge and export agent skills (SKILL.md) for Claude Code, Cursor, Codex, Hermes and more. 27 starter skills. Free models supported.
git clone https://github.com/Lethe044/agentskill-kit.git -
nasde-toolkit
SkillsCLI for benchmarks & evals of AI coding agents — on tasks you already understand, using your Claude / Codex / Gemini individual subscriptions or API keys.
git clone https://github.com/NoesisVision/nasde-toolkit.git -
Connapse
MCP serversSelf-hosted knowledge base and memory for AI agents. MCP server and REST API with hybrid search, reranking and per-user permissions over your files, S3, Azure Blob, GitHub, Confluence and Jira. RAG on .NET 10 and pgvector.
git clone https://github.com/Destrayon/Connapse.git -
pgwarden
MCP serversGoverned Postgres access for AI assistants: an MCP gateway with OAuth 2.1 and OIDC login, one Postgres role per person, database-enforced read-only queries, PII masking, human-approved writes, a tamper-evident audit log, a red-team suite and Terraform for Cloud Run.
git clone https://github.com/B0yko/pgwarden.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.