AgentFlow is a Python library for orchestrating AI coding agents using dependency graphs, supporting parallel fanout, iterative refinement, and remote execution. It integrates with Codex CLI for natural-language pipeline creation.
Agentic Coding Flywheel Setup automates turning a fresh Ubuntu VPS into an AI-powered coding environment with autonomous agents, simplifying complex setups into a single command.
AgentOps provides a Go-based local operating layer for AI coding agents, enabling persistent memory, validation gates, and multi-agent review across vendors with zero cloud dependency.
AgentsMesh offers a self-hosted AI agent orchestration platform with a clean control/data plane split using gRPC+mTLS and WebSocket relay for real-time terminal I/O streaming.
AutoProber is a Python automation stack that controls a flying probe system for PCB analysis, featuring oscilloscope-based safety monitoring and a Flask dashboard.
cass-memory is a TypeScript CLI implementing a three-layer cognitive architecture for AI coding agents, featuring a novel confidence decay system to maintain a reliable, evolving knowledge base.
Claude Code Viewer provides a web UI for real-time monitoring and managing Claude Code sessions with dual authentication modes and PWA mobile support. It handles Anthropic’s SDK restrictions gracefully.
claude-code-harness is a Shell plugin harness for Claude Code that integrates AI agent features without Node.js, relying on specific Claude Code and Opus versions for full capability.
claudemap offers a JavaScript runtime to create and run visual interactive maps for Claude AI agents, with optional Codex assistant integration for enhanced natural language control.
ctx builds a 104K-node knowledge graph to optimize AI skill and agent selection for Claude Code, solving context window bloat with a graph-based recommender and lifecycle management.
ai-sdk-tools offers modular TypeScript packages extending Vercel AI SDK with production-ready patterns like multi-agent orchestration and type-safe streaming artifacts for React apps.
Goose Skills provides 108 reusable AI agent skills for sales, marketing, and competitive intelligence, structured as atomic tools, skill chains, and workflows for coding agents like Claude and Codex.
Kitaru offers a framework-agnostic runtime for autonomous AI agents with durable execution via checkpointing, enabling replay and state preservation to avoid costly restarts on failures.
KohakuTerrarium offers a Python framework to build modular AI agents using a unique algebra for composing multi-agent pipelines, with session persistence and multi-runtime support.
A curated catalog of 20+ LLM agent frameworks and tools organized by agent type and capabilities. Understand architectural differences and trade-offs in LLM agent design.
Octogent adds a local orchestration layer on Claude Code for multi-agent workflows using ’tentacles’ — scoped context directories that isolate work and enable inter-agent messaging.
Open Computer Use enables AI agents to control real computers using specialized Browser, Terminal, and Desktop agents running in isolated Docker VMs. It achieves 82% on the OSWorld benchmark.
OpenClaw Client offers a self-hosted web UI to manage OpenClaw AI agents with streaming response separation, file uploads to agent workspaces, JWT auth, and PWA install.
lenny-skills packages product management knowledge as markdown skills for Claude Code, enabling AI agents to apply frameworks from top product leaders. Install via npx skills CLI.
Scientific Agent Skills extends AI coding agents with 135 domain-specific scientific skills, unifying database queries and multi-step workflows across bioinformatics, chemistry, and clinical research.
