AI Agent Frameworks, MCP Servers and SDKs

Weft is a language and framework for developers who want to run AI workflow orchestration on their own machine. Its runtime requires Docker, and its graph editor works in VS Code and compatible forks. Self-hosting the workflow doesn't make its model calls local: the included WhatsApp support bot uses OpenRouter for inference.

Vexa is a meeting bot and transcription API for developers adding meeting features to products and teams connecting calls to AI agents. Its bots join Google Meet, Microsoft Teams and Zoom to capture the conversation.

DB-GPT is a self-hosted AI data assistant for teams analyzing business data and developers building data applications. It connects plain-language questions to database queries and code-based analysis.

DSH AgentTeams coordinates AI agents inside DeepSeek Harness for coding, research and review tasks. A lead agent assigns work to specialists and combines their results, while you can review the proposed team before execution.

rerankers is a Python library for developers building search and retrieval systems. It ranks candidate documents against a query and lets you compare reranking approaches through a shared interface.

AutoRAG Agent searches documents and connected archives where they already live, then reads the relevant sources to produce answers with file, page or line references. It runs on macOS, Windows and Linux and suits people researching information spread across local files, messages and notes.

Ollama Python is a client library for developers adding model conversations to Python applications. It connects to a running Ollama service for local use or to Ollama's cloud service for larger models.

PYTHIA monitors world events and generates forecasts for people tracking global risks and developers building AI agents that need current-world context. It combines Osiris's globe and live feeds with MiroFish's forecasting approach and local Ollama models.

Gauntlet Loop is an AI agent skill for people who want generated websites, writing or software judged against a specific example. It writes a prompt that asks an agent to build, compare and revise work against a reference you choose.

AgentRQ lets people assign work to AI agents, follow their progress and answer requests for decisions from a browser, phone or desktop app. Agents run on computers you own; the task dashboard can run on your server or the hosted service.

OpenBrowser is a self-hosted browser automation agent for people who need visual judgment and interaction across web pages. Its server and Chrome extension run locally, but the documented Qwen setup sends model requests to DashScope's cloud API and requires an API key and internet access. Browser execution stays local; model processing uses the remote provider.

Ringer coordinates parallel AI coding agents on your machine. It's for developers who want to divide implementation work among workers and judge the results with executable checks.

KaaS is a self-hosted AI knowledge base for personal research and teams preserving knowledge across role changes. It turns notes, documents and transcripts into wiki articles you can read, edit and query.

RAGFlow helps teams build AI agents that answer questions using their own documents. It extracts content from complex files and retrieves supporting material that readers can check.

Activepieces is a self-hosted automation platform for teams that want AI agents and app workflows on their own servers. It runs with Docker or Kubernetes, alongside a managed cloud offering. Self-hosting controls where the app runs; connections to Anthropic, OpenAI, AWS Bedrock or Google Gemini still send model requests to those providers using your credentials.

NLM Memory collects coding conversations into one searchable store on your machine. It's for developers who switch agents or editors and need earlier reasoning to remain available when decisions change.

bb-browser gives AI agents access to your local Chrome session, including the website accounts you're already signed into. It's for people building agents that need to work with authenticated websites without a separate API integration for each service.

NVIDIA Object Oriented Agents (NOOA) is a Python framework for developers building AI agents in their own projects. It supports local models through Ollama and vLLM via LiteLLM, with Qwen3 examples for both backends. It also supports Anthropic and OpenAI models, which send requests to those remote providers.

Unstructured is a document processing library for developers preparing files for LLM applications. It turns text documents and images into structured output that applications can work with.

SpecShip is a workflow extension for Kiro that coordinates AI agents through planning, implementation, review and pull request preparation. It's for developers who want agent work checked against written requirements and tests.

MemOS gives AI agents persistent memory across conversations and tasks. Developers can use it for assistants that recall preferences, support history or earlier work, with on-device, self-hosted and hosted storage options.

MemSearch gives coding assistants searchable project history across sessions. It's for developers who want to recover earlier fixes, revisit design decisions or continue work in another agent.

Browser Use is an AI browser agent for developers automating tasks across websites. It can work through pages and forms to complete jobs such as booking an appointment.

AWS MCP Servers connects coding assistants and AI agents to AWS documentation, infrastructure tools, and cloud services. It's for developers who want their assistant to work with AWS resources and service-specific guidance.

XAgent is an experimental self-hosted AI agent for multi-step coding, research and data-analysis tasks. It plans subtasks, revises plans as work progresses and dispatches actions to agents. A command-line interface and browser UI let you guide a run or provide missing information.

OpenShorts turns podcasts, interviews and other long videos into short clips for TikTok, Instagram Reels and YouTube Shorts. It's for creators and social media teams who want AI to select excerpts and prepare them for posting.

Pi Boomerang is an extension for developers using the Pi coding agent on long autonomous tasks. It reduces the history carried into later prompts by replacing completed work with a handoff summary, while keeping file changes on disk.

TrailSnap is a self-hosted AI photo album for people and families who want to organize their pictures and retrace past trips. It connects photos with places and travel records so you can find a particular memory or review a whole journey.

Stakpak is an open source AI agent for developers and DevOps teams managing production apps on their own machines or servers. It works interactively in a terminal or runs continuously to investigate problems, take corrective action and ask for human help.

RankLLM is a Python toolkit for search researchers and developers who want to compare how AI models reorder retrieved documents by relevance. Its main focus is listwise reranking, where a model considers several candidates together. It supports local inference and optional cloud APIs, and it's open source under the Apache 2.0 license.

ktx gives analytics agents shared metric definitions and business context before they answer questions or write SQL. It's for teams that need agents to reuse approved calculations rather than invent their own each time.

Hive coordinates AI agents for teams processing batches of leads, tickets, repositories or documents. A persistent lead agent, called a queen, develops a method on one item before assigning parallel workers, with human approval before the group starts.

MCP Gateway & Registry gives platform teams a shared catalog and access gateway for the tools their AI agents and coding assistants use. It addresses scattered server connections, credentials and access policies across an organization.

Pydantic AI is a Python SDK for developers building agents into their applications. It uses Pydantic validation to give application code structured results and check the arguments agents pass to tools.