Search

CLI for the Engineering Loop Standard: scaffold engineering-loop.json, persistent project memory, and multi-tool AI agent adapters.

ArchadiAgent — an original, provider-agnostic TypeScript SDK for building tool-using, multi-agent LLM systems with guardrails, memory, tracing and structured output.

AWARE - Autonomous Compliance Infrastructure for AI Agents

Python SDK for Mosaic Sandbox (MAR)

TypeScript SDK for building CrisisMode recovery agents

An LLM client for SimVX games, and the interfaces for building agents on it.

LangChain tools for generating privacy-safe synthetic financial data for Latin American fintech applications.


AI Agents Developement Kit. For fast, smart agents developed in fraction of time of other libraries. Designed for delightful UI assemblies gorgeous UX. Made by RavenAlliance

BDB Invoice & Receipt Scraper Suite for headless automation, cross-platform Uber & AliExpress tax invoice fetcher, receipt PNG-to-PDF normalizer, and PDF accounting analyzer

A self-hostable notification layer for AI agents — they report what they did and what needs you; you read one feed and click out to where the work lives.

Secure local execution agent for Brinqz Cloud

Python SDK for mink — sandboxed AI coding agent

Onion-architected, autonomous Claude Code session runner and full Anthropic SDK CLI — never blocks on a human, distinguishes rate limits from exhausted credits, and resumes safely across usage windows.

A method for agents to talk to each other — fire-and-forget messaging between Claude Code sessions over NATS.

One source of truth for your AI agent instructions. Generate and validate AGENTS.md, CLAUDE.md, .cursorrules, Copilot, Gemini and Windsurf instruction files from a single file.

AgentForge is an installable multi-agent workspace for coding, reasoning, research, data analysis, creative work, and custom orchestration.

Multi-Agent LLM Behavioural Experiment Comparison. A lightweight testbed for multi-agent LLM experiments. Under development.

Eval suites that tell you when they've gone blind: coverage, detection power and judge-depth for LLM agent evaluation.

A production-shaped agent SDK: typed tools, time-travel context, self-healing tool calls, saga rollback, and dynamic tool synthesis.