Search

✊ Let your agent grind 24x7 fully autonomously

Multi-agent AI debate engine. 4 LLMs debate any topic via OpenRouter. Structured rounds, adversarial scoring, final report with confidence rating.

Intelligent LLM agent cost optimization runtime — semantic caching + graduated budget enforcement

Autonomous debugging engine — trace-to-code correlation via AST analysis and LLM synthesis

CLI tool for AI agents to manage tasks on BotBoard

Pre-install & runtime security gate for AI agent skills — blocks dangerous skills and monitors tool calls

Praxis CLI — Install and manage AI agent skills

A lightweight CLI-based coding agent

Research Management Service built with LangChain TypeScript — intelligent research with RAG caching, SearXNG web search, and LLM summarization

The runtime your AI agents deserve. Process management, memory bus, tool routing, message passing, and scheduling for autonomous agents.

Spec-Driven Development protocol for AI agents. One command to govern them all.

pspec (picospec) is the smallest specification toolkit for solo developers and AI agents

Universal Claude Task Manager — SDD-based task pipeline subagent system for Claude Code CLI

TraceOps — record and replay LLM agent traces for deterministic regression testing — framework-agnostic, pytest-native

Collective research memory for AI agents. Search before you research, contribute when you're done.

Autonomous agent primitives for the Vercel AI SDK — permissions, cost tracking, server-side interrupts

Bulwark Vercel AI SDK integration — secure AI tool calls with Bulwark auth

OpenClaw memory plugin backed by memory-decay engine

Multi-agent coordination framework for OpenClaw - orchestrate teams of specialized agents

Multi-agent collaboration skill — orchestrate AI agent teams via ACP with structured protocols, role-specialized councils, and plan-first workflows. Works with any ACP-compatible agent: Claude Code, Codex, OpenCode, Gemini, Cursor, Copilot, OpenClaw, and