Library
85,340 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
uncut
SkillsThe lossless, headless coding agent harness. One 7 MB static binary, four tools, plain stdin/stdout, no silent cuts.
git clone https://github.com/Balanov/uncut.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 -
delegate-local
SkillsClaude Code skill that delegates summarisation, log triage, and bulk-text tasks to local models. Saves API tokens, keeps content on-device, hardware-aware model auditing.
git clone https://github.com/IsmaelMartinez/delegate-local.git -
snotra
SkillsOpen-source desktop agent built around your folder — asks before it acts. Cloud or local models.
git clone https://github.com/kkrafft1999/snotra.git -
A local Model Context Protocol (MCP) server integration to search actor filmographies, match movie soundtrack albums, and generate curated Spotify playlists.
git clone https://github.com/Chiru144/Spotify-MCP-Web-And-MCP-Server.git -
web-mcp-bridge
SkillsBrowser extension & Python WebSocket bridge to connect web-based AI interfaces with local Model Context Protocol (MCP) servers.
git clone https://github.com/AstraxOf/web-mcp-bridge.git -
ai-watermark-scrambler
SkillsScramble statistical AI text watermarks by rewriting with a local model (vLLM, Ollama), and strip C2PA, EXIF, XMP and invisible Unicode. Agent skill plus Python CLI.
git clone https://github.com/novatechflow/ai-watermark-scrambler.git -
automated-data-analyst
SkillsThe math arm for LLMs: compute and check numbers from CSV and Excel data with pandas, SciPy and statsmodels, each with its calculation. Tool calling for Claude, Codex and local models (Ollama, vLLM, llama.cpp, LM Studio), Kaggle-style AutoML with --explain, and paper tables and figures.
git clone https://github.com/saineshnakra/automated-data-analyst.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.