Search

Durable iMessage AI agent template. Text your agent, get retryable LLM + tool replies, full observability. Production-ready, deployed on Vercel

An open-source tool to compare NVIDIA's free LLMs side-by-side with streaming responses, judge scoring, and AI-powered model recommendations.

Aiyu Multi-Agent — Lightweight AI Agent Framework with Tools, Plugins, and Multi-Agent Orchestration

My AI engineering team for Claude Code — 64 named specialists I actually use every day. Atlas leads, Rune designs, Forge codes backend, Bastion guards security, Sage tells me to drink water. Deep agent prompts (anti-patterns + 2025 defaults + handoffs + checklists), per-role memory, ASCII activation cards. MIT.

Azure AI Content Understanding Service for banking account opening

🦞 Claws - Local-first, Vercel-native, chat-first agent OS.

PLATO room knowledge integration measurement - Phi computation for tile quality assessment

internOS — Workstreams framework for human-agent collaboration. Coordinate work across projects, tasks, communication threads, and filesystem workstreams for any AI agent framework.

A governance framework designed to prevent drift, ambiguity, and authority confusion when working with LLMs and AI-assisted development. Lightweight, file-based, principal-scoped, copy into any project. Explicit is better than inferred. Fidelity over momentum. Clear pointer semantics.

Agentic LLM injection benchmark — VisorCorpus payload delivery, VisorSD target discovery, HIT/MISS matrix per vector

ISO 27001 ISMS template designed to be instantiated and maintained by an LLM Agent

"Run a safety stress test to simulate an API timeout during a database write."

Headless agent daemon exposing local agent CLIs (Claude Code, Codex) over a Unix socket.

Prave CLI — discover, install, version, test, and ship Claude Skills. The developer platform for the complete Skill lifecycle.

Minimal, extensible tracing library for AI agent execution

OpenAI auto-instrumentation for AgentLens

Distill any procedural Skill (Cursor / Claude / generic SKILL.md) into GEP Genes and Capsules. Gene = compact strategy template. Capsule = auditable record of one real execution.

Audit handler for the Anthropic Claude TypeScript SDK and Claude Agent SDK — tamper-evident, hash-chained, regulator-ready.

A CLI that serves a web UI and bridge server for interacting with ACP-compatible agents

Decentralized infrastructure for autonomous AI agents on 0G Chain