ai-agents

Contract-first multi-agent software engineering. Contracts before code. Tests as law. Agents that can't cheat.

Natural language shell interface — a local-first agentic TUI powered by a bundled LLM

Track OpenAI, Claude, Gemini and OpenAI-compatible models then give solutions to improve your agent system.

An agentic coding and automation assistant, supporting both local and cloud LLMs

Claude Code hooks + learning loop integration

The bloat moat! - A lightweight LLM and Agent interaction library

AI-Agent-friendly database CLI for seekdb / OceanBase

A structured multi-agent framework for coordinated AI collaboration

Execution security for Python AI agents — seatbelt for LangChain, CrewAI, and plain Python.

Local RAG library — ingest files and SQLite, query semantically, pipe results into any AI agent

KISS Agent Framework - A simple and portable agent framework for building and evolving AI agents

AI agent for any LLMs

K9 Audit with Hook Connector — for Claude Code and hook-compatible agents

Runtime containment kernel for LLM agents. Enforces budget, step, retry, and circuit-breaker limits before the model call.

DDD-friendly Python agent template for LangGraph and LangChain applications.

Multi-agent session handoff framework for Claude Code and Codex CLI

Production-ready AI agent framework purpose built for Vertex AI

AgentFolio identity, trust & reputation tools for OpenAI Agents SDK

Shared versioned state for multi-agent AI workflows

Local-first AI project management agent — reads your repo, documents it, watches for changes, builds LLM prompts.