AI Agent Frameworks, MCP Servers and SDKs
Code-level building blocks for AI agents: agent frameworks, LLM client libraries, MCP servers that give agents tools, and memory layers.
Subcategories
A local Claude Code session manager for macOS and Linux with spending limits and optional LLM supervision through Ollama or compatible endpoints.
204Updated 2 weeks agoMIT
macOS · Linux#Distributed execution#Guardrails#Human approval
claudectl manages multiple Claude Code sessions for developers who need to track parallel work and intervene when an agent gets stuck. Its terminal dashboard brings session activity, approvals and spending into one view.
Agent FrameworksCoding Assistants and AgentsGuardrails, Security and SandboxingLLM Observability and TracingMCP Servers and Agent Skills+0
An LLM data extraction library that validates outputs with Pydantic, retries failed responses and supports local backends including Ollama and vLLM.
14.1KUpdated 19 hours agoMIT
#llama.cpp backend#Ollama integration#Streaming inference
Instructor is a library for developers who need to turn text into structured data using an LLM. Its focus is extraction, with typed outputs that applications can use and validation rules that check the model's responses.
LLM Libraries and SDKs+0
An open-source AI canvas runs on macOS, Windows or in a browser, combining handwriting and diagrams with MCP agents and your chosen model API.
2.5KUpdated 3 weeks agoAGPL-3.0
macOS · Windows · Web#Code execution#MCP#Multimodal input
PenEcho is a visual workspace for people working through ideas with handwritten notes, equations and sketches. AI uses the canvas as context and places answers or interactive results beside your work.
AI Notes and Knowledge BasesChat With Spreadsheets and DatabasesMCP Servers and Agent Skills+0
Self-hosted PDF editor with OCR and document workflows. Optional AI chat and classification use a separately hosted engine or Stirling Cloud AI.
96.5KUpdated 1 day ago
macOS · Windows · Linux · Docker · Web#Batch processing#MCP#Multilingual
Stirling PDF is a PDF workspace for editing individual documents and automating larger document workflows. It runs through a browser on your own server, with Docker deployment, or as a desktop application for Windows, macOS and Linux.
AI Workflow AutomationMCP Servers and Agent SkillsOCR and Document Scanning+0
An open-source AI agent framework runs locally, connects to LLM APIs, and automates Chrome or Chromium through Browser Use.
59KUpdated 3 months agoMIT
macOS · Windows · Linux#Agent Skills#Browser automation#MCP
OpenManus is a Python framework for developers who want to run and extend a general AI agent on their own machine. You give it tasks through a terminal, and it connects a language model to tools that can act on those tasks.
Agent FrameworksComputer and Browser Agents+0
Self-hosted AI document search and chat built on Langflow, OpenSearch, and Docling, with editable workflows and an Apache 2.0 license.
4.7KUpdated 3 days agoApache-2.0
Docker · Web#Hybrid search#MCP#Multi-agent workflows
OpenRAG is a self-hosted platform for searching documents and asking questions about them through an AI chat interface. It brings Langflow, OpenSearch, and Docling together for developers and teams that want a document knowledge base with control over its retrieval workflows. It's open source under Apache 2.0 and supports self-managed deployment with Docker or Podman.
AI Search and Deep ResearchAI Workflow AutomationChat With Your DocumentsMCP Servers and Agent SkillsRAG Frameworks and Pipelines+0
A self-hosted bookmark manager with AI tagging through Ollama, full-text and semantic search, and offline reading in its mobile apps.
30.5KUpdated 1 day agoAGPL-3.0
iOS · Android · Docker · Web · Browser Extension#MCP#Multi-user access#Ollama integration
Karakeep is a bookmark manager for people collecting articles, notes, images and PDFs for later use. It keeps saved material searchable and can preserve pages after their original links disappear.
AI Notes and Knowledge BasesAI Search and Deep ResearchMCP Servers and Agent Skills+0
An open-source AI agent memory system for self-hosting on Linux, macOS or Windows, with project memory for coding assistants and an MCP endpoint.
60.9KUpdated 1 day agoMIT
macOS · Windows · Linux · Docker · Web#Git integration#Hybrid search#llama.cpp backend
Hindsight is a memory system for developers whose AI agents need to carry facts and experience across sessions. It combines stored memories into observations and maintains answers to recurring questions as more information arrives.
Agent MemoryMCP Servers and Agent Skills+0
An open-source AI app framework connects to Ollama, Gemini and OpenAI, with self-hosted application logic, tool calling and structured output.
6.6KUpdated 1 day agoApache-2.0
Web#LLM tracing#Multimodal input#Ollama integration
Genkit is Google's framework for developers building AI agents and chatbots into web and mobile apps. It brings model connections, application workflows and testing tools into one framework.
Agent FrameworksLLM Evaluation and TestingLLM Libraries and SDKsPrompt Management and PlaygroundsRAG Frameworks and Pipelines+0
An open-source personal AI app with local model support, app integrations and multi-agent workflows, accessible through desktop, browser and terminal clients.
42.7KUpdated 20 hours agoGPL-3.0
macOS · Windows · Linux · Web#Human approval#LM Studio integration#MCP
OpenHuman is a personal AI assistant for people who want agents to act across their work apps and carry out repeatable tasks. Its orchestration engine manages multiple agents and workflows in one place.
Agent FrameworksAgent MemoryAI Workflow AutomationDesktop Chat AppsPersonal AI Assistants+0
A local Codex plugin assigns coding roles to different models, with optional plan review and authenticated cloud routes for Claude and Kimi K3.
632Updated 4 months agoMIT
Windows#Agent Skills#Guardrails#Human approval
Codex Orchestration is a plugin for developers who want different models to plan, review, design and implement a coding task. It runs locally, but its Claude and Kimi K3 routes require authentication and send task content to cloud services.
MCP Servers and Agent SkillsTerminal Coding Agents+0
An open-source Python library constrains LLM outputs to schemas and grammars, with local model support through Transformers and llama.cpp.
16KUpdated 3 months agoApache-2.0
#llama.cpp backend#MLX#Ollama integration
Outlines is a Python library for developers who need LLM responses in a defined format. It constrains generation to produce structured data for tasks such as extracting service tickets from emails or limiting an answer to allowed choices.
LLM Libraries and SDKs+0
A rulebook for AI coding agents that checks UI, copy, accessibility, responsive layouts, and code comments, with an MIT license.
9.1KUpdated 1 day agoMIT
macOS · Windows · Linux · VS Code · JetBrains#Agent Skills#Guardrails#Human approval
Anti Slop is a set of skills for developers who want AI coding agents to avoid generic interfaces and filler copy. It checks the agent's work while leaving visual direction to you.
Coding Assistants and AgentsMCP Servers and Agent Skills+0
A local finance research app with terminal and web interfaces, cross-market backtests and trade reviews. Uses OpenRouter for AI by default; MIT licensed.
38.2KUpdated 1 day agoMIT
Web#Agent Skills#Code execution#LLM tracing
Vibe-Trading is an installed Python research app with terminal and web interfaces for traders and analysts testing strategies or reviewing trades. The workspace runs on your machine, but its AI requests go to OpenRouter by default. Research also fetches external market data and web content.
AI Bots for Chat AppsAI Search and Deep ResearchMCP Servers and Agent Skills+0
An open-source, self-hosted SQL agent with Ollama support and user-specific data access; the MIT-licensed project is archived.
23.8KUpdated 9 months agoMIT
Web#LLM tracing#Multi-user access#Ollama integration
Vanna is a Python framework for adding database chat to analytics applications and internal tools. The project is archived and no longer maintained.
Agent FrameworksChat With Spreadsheets and DatabasesSelf-Hosted Chat Web UIs+0
An open-source AI agent memory layer that turns task outcomes into editable Markdown skills, with self-hosted and cloud deployment options.
3.7KUpdated 3 weeks agoApache-2.0
#Agent Skills#Code execution#Context compression
Acontext gives AI agents reusable memory from past tasks. It's for developers who want agents to retain successful approaches, mistakes, and user preferences in files they can inspect and correct.
Agent MemoryLLM Libraries and SDKsMCP Servers and Agent Skills+0
A local browser automation driver lets coding agents use Playwright with your existing Chromium profile, signed-in sessions and extensions.
498Updated 3 weeks agoMIT
Browser Extension#Agent Skills#Browser automation#Code execution
Browser Control lets trusted coding agents work in the Chromium-family browser you already use. It's for developers who want browser automation to use their existing accounts and extensions.
Computer and Browser AgentsMCP Servers and Agent Skills+0
A self-hosted visual AI agent builder with knowledge retrieval, human review and application APIs; the project is archived and no longer maintained.
55.6KUpdated 3 months ago
Docker · Web#Human approval#LLM tracing#Multi-agent workflows
Flowise is a visual builder for developers and teams creating AI agents and chatbots from connected workflow blocks. The project is archived and no longer maintained.
Agent FrameworksAI Workflow AutomationRAG Frameworks and PipelinesVisual AI App BuildersWebsite and Support Chatbots+0
A self-hosted Python library for PostgreSQL RAG and semantic search with Ollama support; the open-source project is archived and no longer maintained.
5.8KUpdated 6 months agoPostgreSQL
Docker#Batch processing#Ollama integration#RAG
pgai is a Python library for developers building RAG applications and AI agents around PostgreSQL data. The project is archived and no longer maintained or supported.
LLM Libraries and SDKsRAG Frameworks and Pipelines+0
A Python LLM security toolkit you can deploy as an API to screen prompts and responses. MIT licensed; archived and no longer maintained.
3.2KUpdated 4 months agoMIT
#Guardrails#PII redaction
LLM Guard is a Python security toolkit developers can deploy as a self-hosted API to check prompts and model responses in their applications. It provides screening and sanitization rather than running the application's LLM. The project is archived and no longer maintained, including its associated Hugging Face models.
Guardrails, Security and SandboxingLLM Libraries and SDKs+0
This AI agent framework turns data analysis requests into Python code and runs locally with Docker, using local LLMs or OpenAI.
6.2KUpdated 8 months agoMIT
Docker · Web#Code execution#Multi-agent workflows#Multimodal input
TaskWeaver is an AI agent framework for developers building assistants that analyze data through Python code. The project is archived and no longer maintained.
Agent FrameworksChat With Spreadsheets and Databases+0
A self-hosted MCP gateway combines tool servers behind shared endpoints, controls tool access, and connects to Cursor and Open WebUI.
2.8KUpdated 3 days agoMIT
Docker · Web#MCP#Multi-user access#Single sign-on
MetaMCP is a self-hosted MCP gateway for developers and teams connecting AI clients to multiple tool servers. It lets you manage the tool collections those clients receive through shared endpoints.
MCP Servers and Agent Skills+0
A Python framework for self-hosted AI chat apps. Its standard OpenAI example uses cloud inference; code is Apache 2.0.
12.5KUpdated 3 months agoApache-2.0
Web#LLM tracing#Multi-user access#Streaming inference
Chainlit's Python framework lets developers self-host conversational AI applications and provide a browser chat interface around their own application logic. Its OpenAI assistant example uses the OpenAI Python SDK’s standard connection, sending model requests to OpenAI’s cloud service. Self-hosting the chat server and supplying model inference are separate choices.
AI Bots for Chat AppsLLM Libraries and SDKsSelf-Hosted Chat Web UIs+0
LogotyperGot an idea for an AI tool? I'm Eugene, the designer and developer behind Localhosted. I'll help you build it, from the first sketch to launch.
Start your projectLogotyperGot an idea for an AI tool? I'm Eugene, the designer and developer behind Localhosted. I'll help you build it, from the first sketch to launch.
Start your project
