Reusable AI skills and capabilities for agent workflows
GitHub Actions
TokenLab provider for Vercel AI SDK, built on the OpenAI-compatible provider.
yimuchen
n8n node for Feishu (Lark) Bot integration
sunwu51
Hono server that proxies llm request
pullbay
n8n node for Pullbay API - App Store, Google Play, DuckDuckGo and more
John Hopfensperger
It ain't langchain.
bochaco
Privacy-first decentralized storage SDK with pluggable adapters
Digvijay Waghela <[email protected]>
Domain-specific RAG embedding model for Data Science & ML documentation retrieval
Apoorva Verma
LlamaIndex VectorStore for MySQL 9's native VECTOR type — works with ShannonBase, self-hosted MySQL, and MySQL HeatWave.
doedja
Kenari provider for the Vercel AI SDK. One Rupiah wallet, one kn- key, the whole kenari model catalog.
GitHub Actions
LangChain.js integration for the Taguru long-term semantic memory server
outo-llms contributors
Deploy local LLMs behind your own managed API server - vLLM or llama.cpp in isolated environments, with API keys, workspaces, and usage tracking.
...moreGitHub Actions
n8n community node for the Bing Copilot AI Answers API on Apify: Microsoft AI answers, cited sources, and brand-mention tracking for AEO.
...moreAI Anytime
Directional ablation (abliteration) toolkit for open-source language models: extract, ablate, and optimize the removal of refusal / behavioral directions in the residual stream.
...moreJohn Chen
A localhost-only OpenAI Chat Completions proxy for Codex app-server
balacode
Opinionated rules and skills kit for AI coding agents — guided capability-aware install, AGENTS.md-first rules, skills via skills.sh, flexible Mental continuity layer.
...morelakbud
Retry + timeout + cache wrapper for OpenAI-compatible LLM chat completion calls (OpenAI, Groq, etc).
Archmonger
A gateway that exposes local Wyoming services via OpenAI-compatible API endpoints
Antony <[email protected]>
A fast, honest, self-hosted RAG engine — hybrid dense+sparse retrieval, streaming, provider fallback, and real token usage reporting. BYOK, no vendor lock-in.
...moreVodala Chakshu <[email protected]>
Intelligent prompt compression for LLMs — cut token costs without losing meaning
GitHub Actions
Control plane for agentic development
Drone Labours Dev Team <[email protected]>
Common shared library for the dolabour project
Muhammad Awais Bin Adil <[email protected]>
Forensic lineage detection for open-weight LLMs: fingerprint a model from its weights and find out what it really descends from.
...moreGitHub Actions
Cross-CLI agentic skills — install once, use with 45+ compatible AI coding tools
rudrendu_paul_packages
Zero-config, cross-platform SEO and GEO (generative engine optimization) checks for local projects and multi-site agency fleets, in pure TypeScript with no Python or headless-browser dependency.
...more