Search

Apply realistic sensor noise, analog artifacts, and camera metadata to AI-generated images using this custom ComfyUI node suite for research and photorealism.

Generate 3D color LUTs from reference images and apply consistent video color grading using this ComfyUI implementation of the Video Color Grading diffusion model.

A memory store that flags its own conflicts before your agent does.

Obsidian vault knowledge integration for Claude Code and Hermes Agent CLI

SDK middleware for Lore Context — auto-inject memory pre-LLM-call and auto-retain post-LLM-call across OpenAI/Anthropic SDKs.

Deterministic, non-LLM grounding & hallucination classifier for agent loops.

ORBOX — Adaptive Unified Runtime Engine for Contextual Intelligence Systems. Memory-native cognitive runtime that sits between you and any LLM.

Outlook Exchange CLI for humans and AI Agents — manage email, calendar, folders, rules, and contacts from your terminal

CLI for AI agents to collect card payments via Prava

AnoSys SDK for OpenAI Agents — automatic instrumentation and logging for OpenAI Agents SDK

Multi-step DevOps Agent powered by OpenAI - Analyze, Deploy, Monitor, Fix

Manage AI agent configurations with profiles and providers

DhanHQ agent skill for Claude Code, Codex, and Agent Skills-compatible AI agents — live NSE/BSE/MCX trading via Dhan API

AI multi-agent framework — five agents that read your codebase, write real code files, and run your test suite

Monitors DOM structure changes on target websites to protect web scraping pipelines from breaking silently.

A self-orchestrating multi-agent dev pipeline for Claude Code. One orchestrator loop watches a backlog, dispatches specialist agents on demand, and routes work through scan → ticket → implement → review → human-merge. Stack-agnostic; ships an opinionated

L402 Lightning payment middleware for Python — async wrap_with_l402 wrapper for agent tools (CrewAI, AutoGen, LangChain Python). Sibling of @powforge/langchain-l402-middleware on npm.

Claude Code Harness (CCH) — Claude Code substrate adapter for AI King ecosystem (MIT)

Semantic memory for LLM agent calls with an equivalence-first cache architecture.

ReCALL Lite: a lightweight persistent memory layer for LLM applications