superpowers
An agentic skills framework & software development methodology that works.
Category preview
Open-source AI capabilities for coding, testing, debugging, code review, and delivery workflows.
An agentic skills framework & software development methodology that works.
Developer workflow project for checking task state, code/agent collaboration, permissions, and delivery boundaries.
Model serving runtime for checking serving behavior, resource use, API compatibility, and rollback boundaries.
LLM application framework for checking model, prompt, tool, retrieval, and chain integration boundaries.
An open-source AI agent that brings the power of Gemini directly into your terminal.
Lightweight coding agent that runs in your terminal
Vector retrieval project for checking embedding storage, query semantics, RAG integration, data boundaries, and rollback.
🙌 OpenHands: AI-Driven Development
Frontend agent and generative UI project for checking React/Angular integration, app actions, UI state, and UX boundaries.
MCP tool integration project for safely connecting external tools, services, or data sources to an AI host.
MCP tool integration project for safely connecting external tools, services, or data sources to an AI host.
MCP tool integration project for safely connecting external tools, services, or data sources to an AI host.
Spec-driven development (SDD) for AI coding assistants.
Prettier is an opinionated code formatter.
Customer and team operations project for checking CRM/low-code data models, permissions, workflows, and rollback.
Aider capability pack for terminal-based AI pair programming, codebase editing, model setup, repo workflows, and safe verification steps.
Find vulnerabilities, misconfigurations, secrets, SBOM in containers, Kubernetes, code repositories, clouds and more
DSPy: The framework for programming—not prompting—language models
MCP tool integration project for safely connecting external tools, services, or data sources to an AI host.
Vector retrieval project for checking embedding storage, query semantics, RAG integration, data boundaries, and rollback.
Vector retrieval project for checking embedding storage, query semantics, RAG integration, data boundaries, and rollback.
Vector retrieval project for checking embedding storage, query semantics, RAG integration, data boundaries, and rollback.
Developer workflow project for checking task state, code/agent collaboration, permissions, and delivery boundaries.
Find, verify, and analyze leaked credentials
Concise, consistent, and legible badges in SVG and raster format
Vector retrieval project for checking embedding storage, query semantics, RAG integration, data boundaries, and rollback.
MCP tool integration project for safely connecting external tools, services, or data sources to an AI host.
MCP tool integration project for safely connecting external tools, services, or data sources to an AI host.
LLM application framework for checking model, prompt, tool, retrieval, and chain integration boundaries.
Agent SDK project for checking tool calls, state, handoffs, traces, evaluation, and permission boundaries.
Toolkit for linearizing PDFs for LLM datasets/training
Data and AI pipeline project for checking inputs, outputs, state, latency, recovery, and deployment boundaries.
From workspace to agent memory
MCP tool integration project for safely connecting external tools, services, or data sources to an AI host.
Open Machine Learning Compiler Framework
Instructor capability pack for reliable JSON, Pydantic response models, typed extraction, validation retries, and provider-portable LLM workflows.
E2B capability pack for isolated sandboxes where AI agents can safely execute code, process data, run commands, and manage files.
Vector retrieval project for checking embedding storage, query semantics, RAG integration, data boundaries, and rollback.
Convert any URL to an LLM-friendly input with a simple prefix https://r.jina.ai/
MCP tool integration project for safely connecting external tools, services, or data sources to an AI host.
Incremental engine for long horizon agents 🌟 Star if you like it!
Developer workflow project for checking task state, code/agent collaboration, permissions, and delivery boundaries.
Observability and evaluation project for turning logs, quality metrics, drift, or experiment results into reviewable signals.
Build, Manage and Deploy AI/ML Systems
Self-evolving memory OS for LLM & AI Agents: ultra-persistent memory, hybrid-retrieval, and cross-task skill reuse, with 35.24% token savings
Prevent cloud misconfigurations and find vulnerabilities during build-time in infrastructure as code, container images and open source packages with Checkov by Bridgecrew.
The easiest way to serve AI apps and models - Build Model Inference APIs, Job queues, LLM apps, Multi-model pipelines, and more!
Self-evolving memory across Agent and platform. The one portable memory layer for every agent they use - Claude Code, Codex, OpenClaw, Hermes, and more
MCP tool integration project for safely connecting external tools, services, or data sources to an AI host.
Observability and evaluation project for turning logs, quality metrics, drift, or experiment results into reviewable signals.
MCP tool integration project for safely connecting external tools, services, or data sources to an AI host.
Python & Command-line tool to gather text and metadata on the Web: Crawling, scraping, extraction, output as CSV, JSON, HTML, MD, TXT, XML
Frontend agent and generative UI project for checking React/Angular integration, app actions, UI state, and UX boundaries.
Spec-driven development for large codebases
ZenML 🙏: One AI Platform from Pipelines to Agents. https://zenml.io.
Vector retrieval project for checking embedding storage, query semantics, RAG integration, data boundaries, and rollback.
MCP tool integration project for safely connecting external tools, services, or data sources to an AI host.
MCP tool integration project for safely connecting external tools, services, or data sources to an AI host.
MCP tool integration project for safely connecting external tools, services, or data sources to an AI host.
Enhanced LanceDB memory plugin for OpenClaw — Hybrid Retrieval (Vector + BM25), Cross-Encoder Rerank, Multi-Scope Isolation, Management CLI
AdalFlow: The library to build & auto-optimize LLM applications.
Vector retrieval project for checking embedding storage, query semantics, RAG integration, data boundaries, and rollback.
Easiest and laziest way for building multi-agent LLMs applications.
MCP tool integration project for safely connecting external tools, services, or data sources to an AI host.
Vector retrieval project for checking embedding storage, query semantics, RAG integration, data boundaries, and rollback.
[NeurIPS 2024] OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments
Python & JS/TS SDK for running AI-generated code/code interpreting in your AI app
Official inference library for pre-processing of Mistral models
Build compute kernels and load them from the Hub.
MCP tool integration project for safely connecting external tools, services, or data sources to an AI host.
A collection of useful extensions for Django.
Transform code to support top-level await in normal browsers for Vite.
MCP tool integration project for safely connecting external tools, services, or data sources to an AI host.
MCP tool integration project for safely connecting external tools, services, or data sources to an AI host.
A tool for running automated static analysis on code posted to a Review Board instance.
Vector retrieval project for checking embedding storage, query semantics, RAG integration, data boundaries, and rollback.
12 production-grade skills for AI coding agents — setup, scope, discipline, code review, security, session management. Works with Claude Code, Codex, and Cursor.
MCP tool integration project for safely connecting external tools, services, or data sources to an AI host.
MCP tool integration project for safely connecting external tools, services, or data sources to an AI host.
Python function spy support for unit tests
Agent workspace template for gptme - create persistent autonomous agents that build, learn, socialize, and assist you with whatever you need.
MCP tool integration project for safely connecting external tools, services, or data sources to an AI host.
Filecoin Pin
MCP tool integration project for safely connecting external tools, services, or data sources to an AI host.
Developer workflow project for checking task state, code/agent collaboration, permissions, and delivery boundaries.
Agent SDK project for checking tool calls, state, handoffs, traces, evaluation, and permission boundaries.
MCP tool integration project for safely connecting external tools, services, or data sources to an AI host.
A collection of agent skills for Claude Code, Cursor, and other AI coding tools
Vector retrieval project for checking embedding storage, query semantics, RAG integration, data boundaries, and rollback.
MCP tool integration project for safely connecting external tools, services, or data sources to an AI host.
MCP tool integration project for safely connecting external tools, services, or data sources to an AI host.
Type hints and utility objects for Python and Django projects.
MCP tool integration project for safely connecting external tools, services, or data sources to an AI host.
MCP tool integration project for safely connecting external tools, services, or data sources to an AI host.
MCP tool integration project for safely connecting external tools, services, or data sources to an AI host.
The official CLI for Lark/Feishu open platform
MCP tool integration project for safely connecting external tools, services, or data sources to an AI host.
LLM application framework for checking model, prompt, tool, retrieval, and chain integration boundaries.
MCP tool integration project for safely connecting external tools, services, or data sources to an AI host.
New Relic agent
The official, opinionated, batteries-included toolset for efficient Redux development
An AI web browsing framework focused on simplicity and extensibility.
MCP tool integration project for safely connecting external tools, services, or data sources to an AI host.