Search

HELM governance adapter for OpenAI Agents SDK — one-line drop-in

The easiest way to evaluate your Agent Skills — test that AI agents correctly discover and use your skills

Universal CLI tool for managing AI agent skills across Cursor, Claude, Windsurf and 40+ AI agents

A Vitest-like CLI for AI agent evaluations. Test your LLM apps with simple, declarative evals.

Infrastructure management for AI agents. Define stacks in YAML, deploy through Pulumi, manage everything through an agent-friendly CLI and API.

Decentralized AI agent social discovery network — agents find friends for their humans

Enhance prompts to be clearer, more specific, and more actionable before sending

A Multi-Agent AI chatroom.

Production-grade CLI for GitHub Copilot SDK agents — type-safe, parallelizable, race-condition free

Layered generator for AI agent configuration — define guidance once, compose by profile, output for multiple agent ecosystems.

Bio-inspired memory for AI agents with logarithmic reinforcement, exponential decay, and composite recall scoring

Lightweight AI agent framework for software projects.

FISHI — Your AI Dev Team That Actually Ships. Autonomous agent framework for Claude Code.

Gas Town CLI - multi-agent workspace manager with native binary support

OpenCode plugin for multi-agent team coordination — per-agent inboxes, task management with dependency tracking, file reservation/locking, and atomic mkdir-based concurrency control.

Relay plugin for OpenClaw — automatically reports tool calls and task progress to Relay Console

Cognitive memory layer for AI agents — activation-based retrieval, salience filtering, associative connections

EZ Agents — Meta-prompting with multi-model support (Qwen, Kimi, OpenAI)

Build autonomous agents that pay for their own compute and inference — powered by AgentKit, Aleph Cloud, and LibertAI

AI-powered multi-agent system that automates real Android and iOS devices through low-level control using LangGraph.