AI Agent Frameworks, MCP Servers and SDKs

Skill Cabinet is a local browser catalog for people whose agent skills are spread across Claude, Codex, Cursor, Hermes, and other tools. It helps you inspect installed skills and manage overlapping copies in one place.

unleashd, listed as Buddies in its repository, is a local workspace for developers coordinating multiple coding agents. It keeps each agent's identity and memory across conversations, so a team can continue work with earlier context.

only-cli is a local web browsing CLI for AI agents that need to read websites without filling their context with raw HTML or screenshots. It suits coding assistants such as Claude Code and Codex that look up documentation, inspect repositories or read online discussions.

Polywise is a self-hosted system for people who want AI agents to work with saved research, notes, and project context. It keeps that material available across conversations so you don't have to explain the same work each time.

AstrBot is an AI chatbot platform for personal assistants, customer support bots and team automation inside messaging apps. You can host it on your own computer or server and choose a local or cloud model backend.

data-to-paper is an open-source Python framework for researchers who want AI agents to work through a dataset and draft a scientific paper whose numerical claims they can check. Its defining feature is traceability: readers can click a value in the manuscript and follow it back to the specific analysis code that produced it.

NoteDiscovery is a note-taking app for personal wikis, technical notes and small teams that want to keep their knowledge base on their own computer or server. It stores notes as ordinary Markdown files, so you can bring in an Obsidian vault or use the same files in other editors.

LobeHub is an AI agent workspace for individuals and teams assigning ongoing work to multiple assistants. It keeps agents, their tasks and shared material together, with hosted and self-hosted options.

Context+ is a local MCP server for developers who want coding assistants to find relevant code and understand the effects of a change across a large project. It works with Claude Code, Cursor, VS Code, Windsurf and OpenCode.

10xProductivity extends a coding agent into a personal assistant for work that spans messages, tickets and documents. It's aimed at people working within company restrictions on new automation platforms, using the accounts and permissions they already have.

Code Cortex MCP is a local MCP server that helps AI coding agents understand how a codebase fits together. It indexes functions, classes, call paths and service connections, so agents can answer relationship questions without repeatedly searching individual files. It builds on codebase-memory-mcp.

Browser MCP connects AI applications to your everyday browser so they can automate tasks in services you're already signed into. It's for people who want browser automation through their AI assistant without opening a separate browser session.

PaddleNLP is a Python toolkit for developers training and deploying language models on their own infrastructure. Built on PaddlePaddle, it covers pretraining, fine-tuning, model compression and inference across several accelerator families.

Desktop Commander lets AI assistants work with files and programs on your computer or a server you own. It's for developers, people handling documents, and server owners who want their assistant to act on a machine and read the results directly.

UFO³ is a self-hosted AI agent framework for developers and researchers automating tasks across Windows, Linux and Android devices. Its Galaxy coordinator splits a request into connected tasks, assigns them to suitable devices and tracks work that depends on results from another machine. The Python project is open source under the MIT license.

Archestra Community Edition is a self-hosted AI platform for teams managing access to company tools and models. It gives coding assistants, internal agents, and staff chat a shared place to enforce policies and track activity.

Bionic GPT is a self-hosted AI agent platform for internal teams building workflows around company knowledge and business systems. It supports tasks that involve several steps, tools and files while retaining context across the work.

CocoIndex is an open-source AI indexing framework for developers processing codebases and documents on their own hardware. Its code indexing example uses sentence-transformers for embeddings and writes to pgvector or LanceDB, giving it a concrete role in preparing searchable context for agents and LLM apps.

Perfect Memory AI keeps a searchable record of screen activity and meetings on Mac and Windows. It's for people who want to recover a page, presentation or conversation without remembering which app contained it.

MCP Reference Servers gives developers examples for connecting AI applications to tools and data. Maintained by the MCP steering group, these are educational implementations, not production-ready servers.

Browser4 is a browser automation engine for developers building AI agents, web research tools, and data collection workflows. It controls real Chrome browsers and handles interactive pages that require clicks, forms, or JavaScript before their data is accessible.

RAG-Anything is a Python framework for developers building question-answering systems over documents that mix prose with visual or structured content. Built on LightRAG, it suits research papers, technical manuals and financial reports where answers depend on figures, tables or formulas.

tRPC Agent Go is an open-source framework for developers building agent services with local automation in Go. It can execute skill scripts in an isolated workspace and includes deployable HTTP servers for agent interfaces. The documented OpenAI and DeepSeek workflows require a provider API key, so running the service yourself doesn't make those model calls local.

Transformers.js is a JavaScript library for developers adding on-device AI to web apps. It runs models in the browser, so processing inputs doesn't require a separate inference server.

WebBrain is an AI browser agent for people who want to ask questions about pages or delegate web tasks from a sidebar. It works in your existing browser, including signed-in tabs, and starts in read-only Ask mode.

Screenpipe records computer activity so people can revisit past work and give AI agents context from screens and conversations. Capture history stays on your device by default.

Pydantic DeepAgents is a terminal coding assistant and Python framework for developers who want to use or build their own AI agents. Both share a Pydantic AI foundation for carrying out tasks across files and tools.

Sandbox Agent lets developers control coding agents from their own applications through a shared API. It's for teams building agent-powered software that needs remote sessions and isolated code execution without a separate integration for each agent.

QMD searches Markdown notes, meeting transcripts, documentation and knowledge bases on your own machine. It's for people who want to find material by its wording or meaning, and make that search available to an AI agent.

Workflow SDK is for developers building apps and AI agents whose tasks need to keep their progress across pauses and failures. It adds durable execution to TypeScript and JavaScript functions so teams don't have to build their own queues and retry logic.

Agent Squad is a framework for developers building assistants that divide work among specialized AI agents. It handles agent selection and conversation context so users can switch topics without starting a separate chat.

Pi Messenger connects Pi coding agent sessions working in separate terminals on the same project. It's for developers who want agents to divide work, share progress and avoid conflicting edits.

OpenLore helps developers keep AI coding agents grounded in large or unfamiliar repositories. It maps code relationships and retains architectural decisions so agents can find relevant context and check proposed changes.

Obelisk makes past coding agent sessions searchable for developers who need to recover decisions or revisit earlier work. A desktop browser and an agent skill give people and coding assistants access to the same local history.