Search

CTX (Context Transfer Format) — universal interchange format for LLM web content consumption

LangSmith tracing plugin for opencode — captures sessions, LLM calls, tool calls, reasoning, and context compaction. Trace taxonomy compatible with langsmith-claude-code-plugins.

Auto-Use Computer Use — drives your OS, browser, scours the web, writes your code. One agent, end to end.

The ultimate Claude Code toolkit for Unity — 20 AI agents, 22 slash commands, 41 skills, and safety hooks for AI-assisted Unity game development. Drop-in, production-ready.

Lightweight LLM agent for text moderation with deterministic pipeline: profanity rules → ML → LLM. Production-grade, YAML configurable. Uses glin-profanity + rapidfuzz + detoxify with Qwen LLM agent (llamacpp/Ollama) + RAG. Early-stop logic. Pure Python, CLI/API/SDK.

An infinitely scalable text world for evaluating long-term memory in LLM agents

LangChain callback handler for Noos — pre-delivery halt/warn decisions from an agent's LLM+tool event stream

AI Coding Agent — Free Claude Code alternative powered by Kimi K2.5 + Ollama

Local daemon that runs a scheduled AI heartbeat loop against the Krawler API. Bring your own model (Anthropic, OpenAI, Google, Ollama, OpenRouter).

Claude Code Hook Relay - collects and forwards Claude Code Hook events

ClawCU: a local multi-agent lifecycle manager for OpenClaw and Hermes

CLI to scaffold autonomous orchestrator-driven development agents for Copilot, Claude, Codex, OpenCode, and related coding assistants.

Multi-agent orchestrator with eval-gated quality gates. Spawn parallel agent workers per track, verify output before merging.

Desktop agent for MobileIDE — controls Claude Code from your iPhone via Supabase

PiQrypt cryptographic audit trail bridge for Microsoft AutoGen

Multi-agent cryptographic session for PiQrypt — co-signed A2A handshakes between AI agents

PiQrypt Verifiable AI Agent Memory bridge for LangChain

Lookover audit logging SDK for AI agents — LangChain and LangGraph integrations

Zero-LLM project scanner for AI agents. Produces a compact project map so AI uses 50-100x fewer tokens to understand your codebase.

Browser automation agent loop powered by browserclaw