Search

LLM application: 🧑‍🏫 AI Agent Framework Crash Courses

LLM application: 🧠 DevPulse AI - Multi-Agent Signal Intelligence

LLM application: 🛡️ Trust-Gated Multi-Agent Research Team

LLM application: Gemma 3 Fine-tuning

LLM application: Llama 3.2 Fine-tuning

AI-native documentation scanner for JS/TS projects — gives AI agents persistent memory across sessions

Autonomous context-engineered development system with SQLite brain. 5 agents, 14 commands, per-task fresh context, 70-90% fewer tokens.

Cloudflare Workers AI model: Workers AI Models

A self-improving personal agent with memory, messaging integrations, and sandboxed tool execution. [#opensource](https://github.com/NousResearch/hermes-agent)

Five governance questions for your AI agent system. Identity, restraint, accountability, memory, charter. Zero dependencies.

Multi-agent system — multiple Claude Code instances collaborating via messaging

tmux setup for AI agent workflows — Catppuccin theme, pane title sync, clipboard integration, and multi-agent orchestration scripts

Adversarial debate pipeline for code review — Critic, Tester, and Advocate agents debate changes while a Judge produces an actionable checklist

Make your AI agent evolve automatically through iterative harness optimization.

Local-first parallel AI agent swarm runner, built on pi-agent

One-command CLI for AI agents to submit apps and people into Ipe Hub.

Cross-platform notification system for AI agents (Claude Code, Gemini CLI) with ntfy.sh support

Composable chat UI components for Polpo AI agents

CLI tool for Yandex Tracker — for humans and AI agents

Testing and evaluation platform for LLM agents — hybrid metrics, multi-agent simulation, and iterative prompt improvement.