Interactive error analysis skill for AI agents. Studies LLM trace datasets, builds a review UI, monitors annotations, categorizes failure modes, proposes new samples.

Pi skills to replicate AmpCode experience - handoffs, modes, permissions, web access

Dynamically spin off side agents in their own tmux windows and git worktrees

A self-improving RLM agent for coding workflows and long-running autonomous tasks.

Gesetz (German for "laws") — a unified code-quality gate that lets you write your own project rules as easily as writing a config file.

Standards for defining and evaluating agent behavior

Eval Harness

A Python sandbox using Wasmtime

LLM agent with exactly one tool (execute_code) that runs Python in Pyodide

Sandbox infrastructure for AI Agents

A HTTP credential proxy and vault for AI agents like Claude Code, OpenClaw, Hermes, custom agents + harnesses, and more.

CLI to control iOS and Android devices for AI agents

Battle-tested Claude Code skills for modern xOS (iOS, iPadOS, watchOS, tvOS) development

Your agent is a security risk, so treat it like one. yoloAI does AI agent sandboxing right.

Orca is the ADE for working with a fleet of parallel agents. Run any coding agent with your own subscription. Available on desktop, mobile and VPS.

The `npx serve` of Apple Simulators.

Run AI agents isolated inside an macOS virtual machine. Configured to run Claude Code, OpenAI Codex, Cursor Agent, Google Gemini.

Portable, lightweight, self-contained virtual machine.

Run multiple agents in parallel sandboxed VMs, with a single command, on your PC or in the cloud

Manage multiple Claude Code, OpenCode agents from either TUI or Web for easy access on mobile. Also supports Mistral Vibe, Codex CLI, Gemini CLI, Pi.dev, Copilot CLI, Factory Droid Coding.

Secure, Fast, and Extensible Sandbox runtime for AI agents.

A benchmark for evaluating AI agents on realistic business workflows

A curated, non-BS library of the best resources for building and evaluating AI agents — papers, blogs, talks, tools, benchmarks. Maintained by BenchFlow.

[NeurIPS'25] Evaluating Program Semantics Reasoning with Type Inference in System F

Model export recipes, Python primitives, and Swift runtime utilities for on-device AI

Framedex — a queryable knowledge base for your video archive

Conductor is an event driven agentic workflow engine providing durable and highly resilient execution engine for applications and AI Agents

A domain specific language to build complex workflows

A multi-hypervisor VM runtime for OCI images, supporting Cloud Hypervisor, Firecracker, QEMU, and Apple Virtualization.framework.