AI Agent Frameworks, MCP Servers and SDKs

FableCut is a local video editor for people who want to make cuts themselves and work alongside an AI agent. Both can edit the same project, with agent changes appearing live in the browser.

Atomic is a personal knowledge base for people who want to find connections across their notes and saved reading. It organizes Markdown notes, web clips, and articles into a knowledge graph you can search and explore.

MCPHub is a self-hosted gateway for developers and teams connecting AI clients to multiple MCP servers. It gives them one place to manage shared tools and decide what each user or project can access.

LiveKit Agents is a framework for developers building voice assistants, phone agents and applications that combine speech, video and text. Python and Node.js agents interact with users through LiveKit rooms connected to web, mobile or telephone clients.

DeerFlow is a self-hosted AI agent application for research, coding and content creation on your own infrastructure. It supports local models through Ollama and vLLM, including Qwen3, as well as hosted providers. With a cloud provider, model requests leave your server and may incur provider charges.

deja-vu helps developers and coding assistants recover fixes, decisions and unfinished work from session history already on disk. It can search conversations recorded before installation and carry relevant context between Claude Code, Codex CLI, Cursor and opencode.

llama-cpp-python is for developers adding local LLM inference to Python applications or connecting existing API clients to models on their own hardware. It brings llama.cpp into a Python library and a self-hosted server.

AI Legion is a self-hosted framework for developers who want several AI agents to work together on tasks. The program runs on your own machine through Node.js, while OpenAI's cloud models handle the language processing. It's open source under MIT.

MS Agent is an open source Python agent framework with a self-hosted web server for working on local projects. It's for developers building research assistants and coding workflows that continue across sessions. Code execution and project file work run locally; the default model integration uses ModelScope's API and requires an API key and internet access.

RocketRide is an AI pipeline builder and runtime for developers creating document processing, search, and agent workflows. Its visual editor sits in VS Code, alongside the application code that uses those workflows.

NVIDIA NeMo Agent Toolkit is an open-source Python library for developers building self-hosted servers that expose AI tools and workflows through MCP or A2A. It also measures and evaluates agent workflows across frameworks. Its introductory NVIDIA NIM workflow uses hosted inference and requires an NVIDIA account and API key.

LangChain4j is a Java library for building chatbots, assistants and AI agents that use local models through Ollama. It runs within JVM applications, while Ollama handles model inference on your hardware using a CPU or GPU. You can also connect to OpenAI or Google Vertex AI, in which case model requests go to the remote provider.

Mobile MCP connects AI agents to native iOS and Android apps for testing, form entry and extracting data from screens. Developers and testers can use the same tools across physical devices, simulators and emulators.

Munder Difflin is a desktop app for developers who want coding agents to collaborate on their own machine. You give an orchestrator a request, and it divides the work among agents instead of leaving you to coordinate separate terminals.

Whisper Notes transcribes interviews, lectures and meetings for people who need recordings to stay on their own device. It works without an internet connection or account.

Graphiti is a Python framework for developers building AI agents that need to remember information as it changes. It turns conversations, structured records and unstructured text into a queryable graph with a history of facts.

PocketFlow is a Python framework for developers building AI agents and workflows with their own model connections. Its utility examples include an Ollama function for local LLM calls. Developers supply that function rather than using a built-in model wrapper. Cloud API examples send model requests to their providers. FastAPI examples show chat applications with streamed responses and background jobs.

smolagents is a Python AI agent library for developers building software that uses tools and calculations to complete tasks. Its CodeAgent writes and executes Python actions, combining tool calls with loops and conditional logic.

Oh My Subagents coordinates Codex and Claude agent teams for developers and researchers handling coding, investigations or independent code review. It saves delegated work and progress so teams can resume interrupted tasks.

UQLM is a Python library for developers and researchers assessing the reliability of LLM answers. Its confidence scores estimate the likelihood of errors or hallucinations; they don't verify that an answer is factually correct.

Prompty is a prompt format and developer toolkit for building AI applications. It keeps prompt text, model settings, inputs and tool definitions in a portable Markdown file that developers can share across editors and language runtimes.

Marginalia is a research agent for people whose papers, notes and working files are spread across a mixed document library. It reads relevant parts of the original files before writing answers with citations.

Marketing Studio is a local rendering engine with a Claude Code plugin for developers and product teams creating launch materials from an app repository. It keeps generated media and review records alongside the product's code.

Damru is a self-hosted Python framework for developers doing mobile web scraping, automation testing, or browser fingerprinting research. It controls Chrome inside a containerized Android environment; physical Android phones aren't supported.

ScrapeGraphAI extracts data from websites and documents based on a plain-language request. Developers can use its self-hosted Python library or call a separate managed cloud API.

HyperResearch is a research agent for Claude Code and OpenAI Codex that produces cited reports and keeps sources for later questions. It's for researchers who want to review the evidence behind a report and reuse their collected material.

QuantDinger is a self-hosted AI trading platform for independent traders, Python strategy authors, and small teams. It brings research, strategy development, testing, and trade execution into one workspace while keeping strategy code and broker credentials under the operator's control.

GrapeRoot is a local MCP context tool for developers using AI coding assistants on projects that require repeated file exploration. It selects relevant code before each prompt reaches the assistant and remembers earlier work.

RepoRelay makes Git repositories searchable by AI coding assistants across projects and versions. It's for developers who want a shared code index on their own infrastructure, accessible from different editors.

QuickDesk is a remote desktop app that lets AI agents operate other computers through a built-in MCP server. Developers and administrators can automate desktop tasks while watching the agent's actions and intervening when needed.

Presenton is an AI presentation maker for teams turning reports and source documents into decks, and developers adding slide generation to their apps. It can reuse an existing PowerPoint design so generated presentations follow your own layouts.

LLM Wiki is a desktop AI knowledge base for people building a research library or personal reference collection. It creates lasting, linked pages from your documents and updates them as your sources change.

BrowserWing is a local browser automation tool for developers and AI agent users who need repeatable website tasks and structured data. It lets you record a workflow once and make it available to agents as a reusable action.

Curator is a Python library for developers building LLM training datasets or extracting structured records from existing data. It supports pipelines that generate data in stages and process many model requests.