World2Agent defines a TypeScript protocol for AI agents to ingest real-world data as pluggable npm sensors, with runtime bridges for Claude Code, Hermes, and OpenClaw.
XcodeBuildMCP exposes xcodebuild operations as MCP tools for AI coding assistants and CLI use, enabling automated iOS/macOS builds, testing, and debugging with a per-workspace daemon on macOS.
OpenShell by NVIDIA offers a Rust-based AI agent sandbox runtime with hot-reloadable YAML policies for filesystem, network, process, and inference controls inside containers.
OpenAlpha_Evolve uses large language models to generate precise code diffs as mutations in an evolutionary algorithm, enabling autonomous iterative code improvement with sandboxed evaluation.
HASH is a Rust-based multi-tenant knowledge graph platform using autonomous AI agents to build and validate data. It combines Rust backend, TypeScript workers, and Docker services with LLM integrations.
Octopoda-OS is a Python library providing persistent memory, loop detection, and audit trails for AI agents. It supports SQLite/PostgreSQL, zero-config runtime, and cloud sync.
TinyAGI is a TypeScript platform for solo operators managing multiple AI agent teams. It uses a SQLite queue with atomic transactions for reliable async task processing and supports multi-channel messaging.
agentic-stack provides a harness-agnostic shared memory layer for AI coding agents, enabling seamless context persistence and migration across tools like Claude Code and Cursor.
Nanobrowser is a TypeScript Chrome extension implementing a multi-agent AI system for browser automation with a unique self-correcting Planner-Navigator architecture, supporting multiple LLMs and local privacy.
site-md uses Next.js middleware to serve clean Markdown to AI agents and HTML to humans, converting HTML on-the-fly without duplicating content. Easy install with minimal setup.
ZenML offers an open-source Python SDK to orchestrate full ML and AI agent lifecycles, integrating popular tools and enabling natural-language MLOps interactions via its MCP server.
A curated repo comparing sandboxing technologies for secure, fast AI agent execution. Covers microVMs, containers, WebAssembly, and more with tradeoffs on security vs speed.
EvoClaw enforces AI agent memory and identity evolution with an 8-validator pipeline ensuring integrity and governance, featuring a tiered memory system and radial mindmap UI.
agent-sat is an autonomous AI agent system where Claude Code learns to solve weighted MaxSAT problems by iterating solver improvements and coordinating via git, solving 220/229 benchmarks.
AgentFlow is a Python library for orchestrating AI coding agents using dependency graphs, supporting parallel fanout, iterative refinement, and remote execution. It integrates with Codex CLI for natural-language pipeline creation.
Agentic Coding Flywheel Setup automates turning a fresh Ubuntu VPS into an AI-powered coding environment with autonomous agents, simplifying complex setups into a single command.
AgentOps provides a Go-based local operating layer for AI coding agents, enabling persistent memory, validation gates, and multi-agent review across vendors with zero cloud dependency.
AgentsMesh offers a self-hosted AI agent orchestration platform with a clean control/data plane split using gRPC+mTLS and WebSocket relay for real-time terminal I/O streaming.
AutoProber is a Python automation stack that controls a flying probe system for PCB analysis, featuring oscilloscope-based safety monitoring and a Flask dashboard.
cass-memory is a TypeScript CLI implementing a three-layer cognitive architecture for AI coding agents, featuring a novel confidence decay system to maintain a reliable, evolving knowledge base.
