InnerVault

Library

86,802 resources from 11 public sources. 49 checked by hand; the rest are unreviewed.

Results

6,896 results with any of your words Clear search and filters
  1. Tri-state circuit breaker router managing LLM provider failure cascades, sliding error windows, and half-open probes

    Stale GitHub, Alpha-Park 7 ★Updated 29 days ago

    git clone https://github.com/Alpha-Park/genpark-tri-state-circuit-breaker-router-skill.git
  2. GraphQL AST query complexity calculator enforcing recursion depth limits and pagination cost budgets

    Stale GitHub, Alpha-Park 7 ★Updated 24 days ago

    git clone https://github.com/Alpha-Park/genpark-autonomous-graphql-query-complexity-calculator-skill.git
  3. B2B enterprise CPQ revenue auditor decomposing gross-to-net waterfall discounts and margin leakages

    Stale GitHub, alphaparkinc 7 ★Updated 24 days ago

    git clone https://github.com/alphaparkinc/genpark-agentic-pricing-discount-waterfall-auditor-skill.git
  4. Multimodal image privacy filter stripping GPS coordinates, device serials, and sensitive EXIF markers

    Stale GitHub, Alpha-Park 7 ★Updated 24 days ago

    git clone https://github.com/Alpha-Park/genpark-multimodal-exif-geotag-privacy-sanitizer-skill.git
  5. SecondSelf

    Agents & frameworks

    Second 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.

    Stale GitHub, HurricaHjz 148 ★MITUpdated 6 days ago

    git clone https://github.com/HurricaHjz/SecondSelf.git
  6. 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…

    Indexed prompts.chat (CC0 prompt collection), unstabaple@gmail.com CC0-1.0

  7. promptguard

    Prompts

    Offline prompt-contract auditor for Hermes, Claude Code, Codex, OpenCode & OpenClaw. Pre-write guard before agents ship vague code. Zero deps. No model API.

    Stale GitHub, mturac 76 ★MITUpdated 3 months ago

    git clone https://github.com/mturac/promptguard.git
  8. skills

    Skills

    23 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.

    Stale GitHub, timharris707 44 ★MITUpdated 15 days ago

    git clone https://github.com/timharris707/skills.git
  9. B2B enterprise CPQ revenue auditor decomposing gross-to-net waterfall discounts and margin leakages

    Stale GitHub, Alpha-Park 7 ★Updated 24 days ago

    git clone https://github.com/Alpha-Park/genpark-agentic-pricing-discount-waterfall-auditor-skill.git
  10. Full-duplex voice agent echo suppressor distinguishing user barge-in from speaker playback acoustic feedback

    Stale GitHub, alphaparkinc 7 ★Updated 24 days ago

    git clone https://github.com/alphaparkinc/genpark-realtime-voice-cross-talk-suppressor-skill.git
  11. modulo

    Skills

    Modulo 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.

    Indexed GitHub, EigenformAI 41 ★Updated yesterday

    git clone https://github.com/EigenformAI/modulo.git
  12. kiki

    Agents & frameworks

    Open-source multi-model AI agent workbench (Desktop GUI, TUI & Web) — dispatch subagents across Claude, GPT, Gemini & Kimi, bridge WeChat/QQ, and run locally.

    Indexed GitHub, X-T-E-R 59 ★MITUpdated today

    git clone https://github.com/X-T-E-R/kiki.git
  13. Google holds #1 in 6 of 8 Arena categories; Anthropic in 2. OpenAI has no category in the top.

    Stale Official MCP Registry, com.modevc Updated 31 days ago 1 note

  14. Since Jan 2025, Arena's #1 spot has changed hands 16 times. Half of the finished reigns lasted.

    Stale Official MCP Registry, com.modevc Updated 31 days ago 1 note

  15. polter

    MCP servers

    A 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.

    Stale GitHub, Lugia123 20 ★MITUpdated 14 days ago

    git clone https://github.com/Lugia123/polter.git
  16. quil

    MCP servers

    Reboot-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.

    Stale GitHub, artyomsv 27 ★Apache-2.0Updated 13 days ago

    git clone https://github.com/artyomsv/quil.git
  17. llmtrim

    Prompts

    Local 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).

    Indexed GitHub, fkiene 274 ★MPL-2.0Updated 6 days ago

    git clone https://github.com/fkiene/llmtrim.git
  18. aginxbrowser

    MCP servers

    The 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.

    Stale GitHub, yinnho 40 ★Apache-2.0Updated 32 days ago

    git clone https://github.com/yinnho/aginxbrowser.git
  19. Make 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.

    Indexed GitHub, weijt606 135 ★MITUpdated 3 days ago

    git clone https://github.com/weijt606/anti-vibe-writing.git
  20. libgen-mcp

    MCP servers

    MCP 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.

    Stale GitHub, jmrplens 29 ★MITUpdated 15 days ago

    git clone https://github.com/jmrplens/libgen-mcp.git
  21. agentskill-kit

    Prompts

    Lint, 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.

    Indexed GitHub, Lethe044 51 ★MITUpdated 5 days ago

    git clone https://github.com/Lethe044/agentskill-kit.git
  22. nasde-toolkit

    Skills

    CLI for benchmarks & evals of AI coding agents — on tasks you already understand, using your Claude / Codex / Gemini individual subscriptions or API keys.

    Stale GitHub, NoesisVision 14 ★MITUpdated 34 days ago

    git clone https://github.com/NoesisVision/nasde-toolkit.git
  23. Connapse

    MCP servers

    Self-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.

    Indexed GitHub, Destrayon 23 ★MITUpdated yesterday

    git clone https://github.com/Destrayon/Connapse.git
  24. pgwarden

    MCP servers

    Governed 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.

    Stale GitHub, B0yko 23 ★Apache-2.0Updated 12 days ago

    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.