Reusable AI skills and capabilities for agent workflows
GitHub Actions
Tool for testing llm prompts against multiple LLMs.
broskees
OpenCode plugin that injects a live codebase structural map into the system prompt
patrickjm
A mock OpenAI API server for testing LLM applications
das_enema
Lightweight, composable LLM nodes for TypeScript
arnavdadarya
Core library for building type-safe LLM applications with structured input/output signatures, automatic validation, and reasoning patterns within TypeScript
...moreduc.dao.98d
Check all your AI subscription quotas in one command. Supports OpenAI, Github Copilot, Anthropic, Z.ai, and Minimax. More platforms coming soon.
...morepatriceckhart
Chat with Pi AI to control your browser — summarize pages, fill forms, check mail, and save routines.
pointsharp
An Antora extension to generate llms.txt files for LLM consumption following llmstxt.org specification.
adamavenir
An LLM scripting language for orchestrating workflows and building agents with infrastructure-level defense against prompt injection
...moreGitHub Actions
Qwen OAuth authentication plugin for OpenCode with multi-account rotation and API translation
GitHub Actions
OpenClaw Opik exporter — sends LLM traces to Opik
simonouyang
Deterministic 10-K filing analyzer — command-driven vs intent-based invocation. Proves that intent-based invocation is probabilistic; command-driven invocation is deterministic and auditable.
...moreisdk
llama.cpp LLM Provider - OpenAI Compatible
GitHub Actions
A template for LLM development integrating AI tools, TypeScript, Zod validation, and development utilities like Vitest and Rslib.
...morecahidarda
A Semantic cache built on top of Upstash Vector DB
aphoristicartist
Node.js bindings for Infiniloom - AST-aware code context engine for RAG and vector databases. Tree-sitter parsing, PageRank ranking, BLAKE3 content-addressable chunks, 27+ tokenizers.
...moredavesienk
Plan it, Build it, Run it — structured development workflow for Claude Code
kmbro
A TypeScript library for extracting structured and grounded information from text using LLMs
GitHub Actions
Give your OpenClaw agent lasting memory: structured facts, semantic search, auto-capture & recall, decay, optional credential vault. Part of Hybrid Memory v3.
...moredonnfelker
OpenClaw plugin that cuts LLM costs 40-80% by routing prompts to the cheapest capable model. 15-dimension classifier, super fast local routing, automatic fallback chain.
...moreGitHub Actions
CLI for contextio: LLM API proxy with redaction and logging
p-matrix
Real-time safety monitoring plugin for OpenClaw agents
GitHub Actions
Debug and log LLM API requests/responses with streaming support. Works with OpenAI, Anthropic, and compatible APIs.
gordonb
Letta-style persistent memory blocks for Pi coding agents