Search

Unified Python interface for invoking AI coding-agent CLIs (claude-code, opencode, codex, gemini, aider, swe-agent) as subprocesses.

Multi-agent consensus protocol — weave votes into fleet decisions with quorum and veto

A pip-installable CLI that scaffolds a learning-environment folder for any LLM agent to operate as an adaptive mentor.

Dynamic Consensus System — multi-agent belief, lock accumulation, consensus

Turn successful AI agent runs into reusable markdown skills

Operating rules for LLM coding agents — reduces silent assumptions, overbuilding, scope creep, contract breaks, premature optimization, fake verification, and unsupervised output

Give any AI agent a physical body — eyes, ears, voice, face. One command install.

Helix — Local-first AI Agent Framework

OpenSandbox support for the Mastra AI agent framework

TypeScript SDK client for the Argentor AI agent framework REST API

AI Agent Framework with multi-provider support and real-time broadcasting

CLI to connect your AI agent to AgentRoulette

Scaffold a multi-agent workflow for generating C4 architecture diagrams using LikeC4 DSL. Optimized for architectural precision and token-cost efficiency.

Multi-model AI agent harness for the terminal

Open Engineer - A diverse multi-model AI agent team for OpenCode

Conversational AI compliance consultant — provenance-aware, deterministic, Claude-powered

Tunnel relay between cloud AI agents and local machines — server relay, local agent, client SDK, JSON-RPC, HMAC signing

Behavioral regression tests for every staged change — AI probes your live app and generates focused e2e tests that verify user flows didn't break

AI agent observability SDK for Node.js — plug-and-play monitoring for your agents

Search and inspect the OpenCode SQLite database from the command line