affaan-m/ECC
ECC is a comprehensive agent harness performance optimization system providing skills, instincts, memory, security, and research-first development for various AI agent harnesses including Claude Co...
deepset-ai/hayhooks
Hayhooks is a Python service that deploys and serves Haystack pipelines and agents. Its primary job is to expose a pipeline as a REST API with little boilerplate, but it also runs as a Model Context Protocol server, so every deployed pipeline and agent becomes an MCP tool available to clients such as Cursor and Claude Desktop. The same MCP interface covers the Hayhooks core API itself, which means pipelines can be deployed, undeployed, listed and run by chatting with an MCP client. Alongside MCP it can expose pipelines over the A2A protocol with auto-generated agent cards, so other agents can discover them and delegate tasks through hayhooks a2a run, and it can act as an OpenAI-compatible chat completion backend with streaming for Open WebUI. An optional Chainlit chat interface can be embedded and started with a flag, and optional OpenTelemetry tracing records deploy, run and undeploy activity across both REST and MCP, with a dashboard served from a local live trace buffer. A deployment is a directory containing a pipeline_wrapper.py that subclasses BasePipelineWrapper. The setup method builds the Haystack pipeline or agent, run_api_async defines the POST endpoint whose request model is validated automatically by Pydantic from the method signature, and run_chat_completion_async returns a streaming generator for the OpenAI-compatible endpoint. Pipelines can also be deployed from YAML definitions rather than wrapper code. Deployment is done with hayhooks pipeline deploy-files, and the server starts with hayhooks run and listens on port 1416 by default. Installation is a plain pip install, with extras for a2a, chainlit and tracing, and Docker images are published. It is aimed at teams already building with Haystack who need their pipelines and agents reachable from HTTP clients, chat interfaces and MCP-capable development tools without writing a separate service for each channel.
https://github.com/deepset-ai/hayhooks
Also in Agent Platforms
open-webui/open-webui
Open WebUI is a self-hosted, extensible AI platform supporting multiple LLM runners and OpenAI-compatible APIs with advanced features like Retrieval Augmented Generation, model building, and offline deployment.
Mintplex-Labs/anything-llm
AnythingLLM is an all-in-one AI application with full MCP compatibility that enables intelligent chat interactions with documents using various LLMs, multi-user support, and no-code AI agent building capabilities.
aaif-goose/goose
goose is an open-source, extensible AI agent providing desktop, CLI, and API interfaces for code, workflows, and general tasks, featuring broad LLM provider compatibility and connection to MCP exte...
HKUDS/nanobot
nanobot is an ultra-lightweight, open-source, self-hosted personal AI agent framework in Python, offering a WebUI, tools, memory, MCP integration, multi-agent workflows, automation, and chat app co...
zhayujie/CowAgent
CowAgent is an open-source, multi-model AI assistant and Agent Harness designed for autonomous task planning, tool execution, and continuous learning, featuring native Model Context Protocol (MCP) ...
sickn33/agentic-awesome-skills
This project provides an installable GitHub library and npm installer for over 1,900 agentic skills and playbooks, designed to enhance AI coding assistants like Claude Code, Gemini CLI, Cursor, and...
danny-avila/LibreChat
LibreChat is an open-source enhanced ChatGPT clone that integrates multiple AI models and supports the Model Context Protocol (MCP) for advanced AI assistant features including no-code agents, secure code execution, multimodal interactions, and customizable conversation management.