All AI agent resources

An MCP server that lets AI coding agents search, discover, and evaluate skills from the SkillFlow marketplace.

Skyvern automates browser workflows with language models and computer vision, including logging into portals, filling forms, downloading user-requested files, and extracting structured data.

An open-source encyclopedia where agents generate, revise, and review knowledge articles, then explore connected topics through a knowledge graph.

Hugging Face's lightweight agent framework, including code agents that write and execute Python actions.

SnapRender is a screenshot API for agent workflows, with a remote MCP server and SDK integrations for capturing websites as images or PDFs.

solveathome is an MIT-licensed framework for running a swarm of AI agents owned by different people against one open problem, with public transcripts, peer review by other contributors' agents, and a small group of trusted reviewers who decide what is accepted.

A self-hosted server for personal AI agents with persistent private memory, shared wiki, delegated agents, scheduled work, and web, shell, and browser tools across terminal, browser, and mobile clients.

An open-source Go client for the hosted Sonzai Mind Layer API, providing agent runtimes with memory context, turn persistence, and voice services.

A self-custodial Spark Bitcoin wallet skill for AI agents, supporting BTC transfers, Lightning invoices, L402 payments, token operations, and merchant purchases with payment guardrails.

Stagehand adds natural-language act, extract, and observe APIs to Playwright for browser automation.

An open-source browser API and sandbox that provides managed browser sessions for AI agents and web automation.

A non-custodial USDC wallet on Base for AI agents, with an MCP server and spending limits enforced below the instruction layer.

A web dashboard and local runtime for orchestrating parallel AI coding agents, with task dispatch and isolated workspaces.

A GPS-aware mobile web app that discovers nearby landmarks, generates location-based stories with an LLM, and narrates them as users walk.

AWS's model-driven SDK for building agents that use tools through a model-directed loop.

A persistent archaeological exploration game for AI agents, with REST and MCP interfaces for discovering fragments, interpreting finds, and connecting them with other agents.

SUNGLASSES is an open-source local input firewall for AI agents that scans text and files for prompt injection, credential leaks and data exfiltration, and reports both what it matched and what it could not read.

Superagent is an open-source AI assistant framework backed by Y Combinator, facilitating the integration of large language models (LLM) and generative AI into applications, supporting various use cases such as question answering, chatbots, and content generation