Packages

[](https://oathe.ai/report/aplaceforallmystuff/the-antislop)

Token Usage Leaderboard - The Kardashev Scale for AI Devs

coremltools is a Python library that converts and manipulates machine-learning models into Apple Core ML format, including reading/writing/optimizing Core ML models and (on macOS) verifying conversions via prediction.

A skill for AI agents to send iMessages via [Blooio](https://blooio.com) with automatic fallback to RCS or SMS when iMessage is unavailable.

Claude Code skill that automates end-to-end GitHub Pages deployment — git init to live URL, zero manual steps.

[🇨🇳 中文文档](./README_CN.md)

A Claude Code skill that delegates tasks to an OpenCode "intern" agent via [ACP (Agent Communication Protocol)](https://agentclientprotocol.com/overview/introduction). This enables Claude Code to offload tasks to a secondary AI agent running in [OpenCode](https://OpenCode.ai/docs/acp/) using any model you like.

[](LICENSE)

Quantum-Loop is a Claude Code plugin plus scripts that implements a spec-driven autonomous coding loop: it turns a one-line feature description into structured PRD/spec artifacts, builds an execution dependency DAG, runs TDD/quality checks with two-stage review gates, enforces “fresh verification evidence” (Iron Law), and iterates with retry/failure logging until stories pass and then performs cross-story integration before committing changes.

skill-fetch is a cross-platform tool/skill that searches multiple registries for AI coding agent skills, scores and ranks results, applies security scanning/integrity hashing, and installs selected skills into supported agent environments (e.g., Claude Code, Cursor, Codex, Gemini CLI, Windsurf, Amp).

llm is a Python library and command-line tool for interacting with large language models (both via remote APIs like OpenAI/Anthropic/Gemini and via locally installed/self-hosted models through plugins). It supports running prompts from the CLI, managing API keys, chat, embeddings, structured extraction (schemas), tool execution, and logging to SQLite.

OWL is an open-source Python multi-agent framework built on top of CAMEL-AI to orchestrate collaborative agent workflows for real-world task automation. It supports tool use across many domains (e.g., online search, browser automation via Playwright, document parsing, multimodal analysis, code execution) and integrates Model Context Protocol (MCP) tool calling plus additional toolkits (including MCP toolkits, file/terminal capabilities, and various domain-specific toolkits).

Trae Agent (trae-cli) is a Python CLI framework for LLM-based, general-purpose software engineering tasks. It runs an agent loop with a configurable tool ecosystem (e.g., file editing and bash execution), supports multiple LLM providers, can record detailed trajectories for debugging, and optionally integrates MCP servers for additional tool/model context.

DeerFlow (2.0) is an open-source long-horizon “super agent” harness that orchestrates sub-agents, memory, and sandboxed execution to perform complex tasks over minutes to hours, with extensible skills/tools and support for configurable model providers (Python/Node ecosystem) and integrations like MCP servers and messaging (IM) channels.

Hive is a Python runtime harness for AI agents in production. It supports goal-driven agent development (a coding “queen” generates an agent graph/code), then executes that graph with features like state isolation, checkpoint-based crash recovery, cost enforcement/degradation, real-time observability via streaming, and human-in-the-loop pause/intervention nodes. It also advertises integration through MCP tools and tool/agent SDK-wrapped nodes, with support for multiple LLM providers via LiteLLM-compatible interfaces.

Provides an “agent skill” (reference documentation files) to help AI agents write, review, and reason about modern Android Jetpack Compose best practices, including state management, effects, navigation, theming, accessibility, and performance.

SimpleMem is a Python memory framework for LLM agents that stores, compresses (semantic lossless compression), and retrieves long-term memories using semantic/lexical/symbolic indexing. It supports cross-session/persistent memory and can be used via MCP (cloud-hosted and/or run locally with Docker) and via Python integration with OpenAI-compatible LLM/embedding backends.

TensorRT-LLM is an open-source Python/C++ toolkit for building and running optimized LLM inference on NVIDIA GPUs. It provides a Python API to define models and build high-performance inference runtimes/engines, along with serving/orchestration components and performance-focused optimizations.

Google Calendar integration for OpenClaw/Clawd agents

Nelson is a Claude Code skill/plugin that provides a structured, risk-tiered orchestration framework for coordinating multi-agent coding sessions. It defines “sailing orders,” forms a squadron of roles (admiral/captains/red-cell), runs tasks via checkpoints (“quarterdeck rhythm”), enforces risk-tier controls (“action stations”), and produces auditable decision logs (“captain’s log”) plus recovery procedures (“damage control”).