Open-source alternatives to Node DeepResearch

Deep Searcher is an open-source retrieval-augmented generation engine that indexes private documents into a vector database and uses large language models to answer complex questions with cited reasoning. It functions as both a command-line interface and a web API research tool, enabling users to load data and generate comprehensive reports by combining indexed private information with LLM-powered analysis. The system distinguishes itself through a plugin-based provider architecture that supports multiple embedding models, LLM providers, vector databases, and file loaders as interchangeable c

This project is a Model Context Protocol server that connects large language models to web scraping and crawling tools. It functions as a bridge, allowing LLM clients to utilize a web crawling engine and scraping utilities to extract and process web data. The server integrates a markdown web converter that transforms dynamic web pages and PDF documents into clean markdown to optimize consumption by AI models. It also provides a browser automation interface for controlling headless sessions and bypassing access restrictions. The system covers broad capabilities including large-scale website d

ollama-python is a Python client for interacting with large language models. It provides an interface for sending prompts to receive text and chat completions, as well as a dedicated client for generating numerical vector embeddings from text. The project includes a wrapper that emulates the OpenAI API, allowing applications built for that standard to interact with local models. It also provides a non-blocking asynchronous client for executing concurrent requests. The library covers the full model lifecycle, including the ability to pull, create, list, and delete models within a local enviro

TaskWeaver is an LLM agent framework that interprets natural language requests and executes them as Python code, SQL queries, or shell commands. It functions as a conversational code interpreter that maintains stateful data structures across turns, generating executable code from user prompts within a session-based environment. The system is designed as a self-hosted AI agent platform that can be deployed in Docker, managing sessions and providing a web UI for data analytics and automation tasks. The framework distinguishes itself through a role-based multi-agent architecture that divides the

OptiLLM is an AI reasoning and optimization framework that functions as an API proxy to enhance the response quality of large language models. It intercepts requests to apply inference-time reasoning logic and output refinement before returning results to the client. The project distinguishes itself through a combination of inference-time search trees for logical verification and an anonymization pipeline that removes personally identifiable information from prompts. It further extends model capabilities by orchestrating external tools, including real-time code execution and autonomous web re

mistral.rs is an inference engine for large language models that runs locally and exposes models behind OpenAI and Anthropic-compatible APIs. It serves as a multi-model serving platform, capable of loading several models in a single server process with per-request routing and on-demand loading and unloading. The engine supports multimodal inference, processing text alongside images, video, audio, and speech inputs, and includes a quantized model deployment runtime that reduces memory use and speeds up inference on consumer hardware. The project distinguishes itself through an agentic tool exe

FastDeploy is a high-performance deployment framework for large language models, vision models, and multimodal models. It provides the infrastructure to launch model services that process combined image, video, and text inputs, exposing these capabilities through a standardized, OpenAI-compatible API for chat and text completions. The project distinguishes itself through advanced inference pipeline engineering and GPU optimization. It employs speculative decoding, tensor parallelism, and a disaggregated execution model that separates prefill and decode phases across different hardware resourc

Sglang is a high-performance inference engine and serving system designed for large language and multimodal models. It provides a programmable interface for orchestrating complex generation workflows, enabling developers to coordinate multi-turn dialogues, tool invocations, and reasoning chains through a domain-specific language. The platform is built to support production-scale deployments, offering an OpenAI-compatible API that allows for integration with existing application ecosystems. The system distinguishes itself through a disaggregated architecture that separates compute-intensive pr

Firecrawl is a headless browser automation tool and web crawling engine designed to extract structured data from the web. It functions as an API that transforms raw website content and documents into clean markdown and JSON formats to serve as context for large language models. The project distinguishes itself by using natural language prompts to translate human instructions into targeted data extraction tasks and browser actions. It can execute interactive page navigation, such as clicking and scrolling, and perform automated web research to retrieve structured data without manual interventi

omlx is a local inference server designed to run large language models, vision models, and embedding models on Apple Silicon. It provides a private alternative to industry-standard AI endpoints by hosting a local API gateway that mirrors OpenAI and Anthropic specifications. The system distinguishes itself through specialized hardware optimizations, including continuous batching for high throughput and a tiered caching system that offloads memory blocks to SSD. It also functions as a Model Context Protocol host, enabling the integration of local models with external tools, agents, and structur

Yao is an LLM agent framework and low-code web app builder designed for orchestrating autonomous AI agents. It provides a platform to design, deploy, and coordinate agents with specialized personas that can plan tasks, utilize external tools, and execute multi-stage pipelines. The project distinguishes itself through a Model Context Protocol server for connecting assistants to external binaries and HTTP services, and a gRPC remote execution engine that allows agents to manage remote servers and devices. It includes a model-agnostic provider bridge that supports dynamic switching between vario

This project is a Model Context Protocol server that provides large language models with neural web search and webpage content extraction capabilities. It implements a standardized interface to expose research tools and resources to compatible clients. The server integrates a neural search engine to retrieve real-time internet data using semantic embeddings rather than keyword matching. It includes specialized utilities for company intelligence and reasoning-based deep research, enabling the collection and synthesis of organizational data and professional profiles. The system covers a broad

ollama-js is a JavaScript client library and API wrapper that provides a programmatic interface for interacting with and managing large language models. It enables the execution of models in both local and cloud-based environments, facilitating the generation of conversational text and the management of model lifecycles. The project distinguishes itself by offering specialized tools for model administration, including the ability to download, create, and remove models, as well as the capacity to define custom model blueprints and prompt templates. It also provides a vector embedding client fo

This project is a web-based user interface and multi-model API gateway for interacting with various large language model providers and local inference services. It functions as a retrieval-augmented generation chatbot for private document questioning, a manager for model fine-tuning, and an autonomous agent framework. The system distinguishes itself by integrating an autonomous assistant mode that uses web search and external tools to solve complex, multi-step tasks without manual prompting. It also features an API gateway capable of rotating multiple authentication keys to balance usage and

This project is a server implementation of the Model Context Protocol designed to function as an AI knowledge retrieval tool. It acts as a semantic search engine and web scraping framework that indexes technical documentation from web sources, local files, and archives, making this information directly accessible to AI coding assistants for context-aware research and querying. The system distinguishes itself through a hybrid search architecture that combines vector-based embeddings with full-text retrieval to improve the accuracy of documentation lookups. It features a modular pipeline for co

This project is a framework for developing multimodal AI agents that function as programmable participants in real-time communication rooms. It enables the construction of agents that can see, hear, and speak by integrating speech-to-text, large language models, and text-to-speech pipelines to facilitate low-latency, natural conversations. The system is distinguished by its advanced orchestration of real-time media and conversational flow, including support for full-duplex speech, preemptive response generation, and sophisticated interruption management. It further differentiates itself throu

InternVL is a vision-language model framework that fuses a visual encoder with a large language model to translate image features into textual tokens for reasoning. It provides a system for multimodal inference and dialogue, enabling the processing of images and text to answer questions or generate descriptions. The project is distinguished by its high-resolution image processing, which uses dynamic tiling to maintain detail for images up to 4K resolution, and its chain-of-thought visual reasoning for solving complex mathematical and spatial problems. It also supports temporal frame sampling

Intel XPU LLM Acceleration Library is a toolkit designed to accelerate large language model inference and finetuning on Intel CPUs, GPUs, and NPUs. It provides a distributed inference engine for scaling models across multiple accelerators, a multimodal model runtime for vision and speech tasks, and a low-bit model quantization tool for converting weights into INT4, FP8, and GGUF formats. The project features a parameter-efficient finetuning framework that enables model adaptation using QLoRA and DPO on Intel hardware. It distinguishes itself by providing specialized optimizations for Intel XP

PraisonAI is an autonomous AI agent platform that coordinates multiple LLM-powered agents for research, planning, and execution of complex workflows. It functions as a multi-agent orchestration framework, a workflow builder, and a Model Context Protocol server, while also providing retrieval-augmented generation through vector knowledge bases. Agents can interact via CLI, web, or standardized protocols with sandboxed code execution. The platform distinguishes itself with a rich set of agent communication protocols, including A2A, REST, WebSocket, voice and telephony integration, and MCP, allo

WebLLM is a library for executing large language models directly within web browsers. It provides a framework for building conversational artificial intelligence applications that perform inference locally, ensuring user data privacy by eliminating the need for external server dependencies. The project distinguishes itself by leveraging browser-native graphics APIs to perform intensive machine learning computations on the client side. It maintains application responsiveness by offloading heavy model tasks to background threads and ensures continuous operation through service workers that func

Langroid is a multi-agent orchestration framework and tool integration suite designed for building complex AI applications. It serves as a multi-modal integration layer that connects diverse local and remote language models with an agentic retrieval-augmented generation system. The project distinguishes itself through a collaborative message-exchange paradigm, allowing specialized agents to delegate tasks hierarchically and coordinate via structured communication. It features an advanced state management system for conversational AI, including the ability to rewind and prune conversation hist

Serge is a self-hosted web chat interface for running large language models locally using the llama.cpp inference engine. It loads GGUF-format model files directly on your own machine, removing the need for internet connectivity or external API keys, and streams responses to the browser in real time via WebSocket connections. The project is packaged for containerized deployment using Docker and Docker Compose, with a Traefik reverse proxy that handles HTTP and WebSocket routing along with automatic TLS certificate management. Ready-made Kubernetes manifests are also provided, enabling deploym

The simplest way to run LLaMA on your local machine

Kilocode is an autonomous engineering platform designed to orchestrate AI agents for complex software development tasks. It functions as a comprehensive system for automating coding, testing, and repository management by integrating directly with your codebase and terminal. The platform provides a unified gateway for model orchestration, allowing for the management of agentic workflows, event-driven automation, and persistent session state across distributed development environments. The platform distinguishes itself through its federated task management and policy-based access control, which

Shell GPT is an AI-powered command-line interface that generates shell commands and source code from natural language prompts. It serves as a terminal-based tool for automating technical tasks, producing executable commands, and generating code snippets directly within the shell. The tool distinguishes itself through a read-eval-print loop for interactive chatting and the ability to maintain stateful conversational history via named sessions. It supports flexible backend routing, allowing users to connect to cloud-based APIs or local language model hosts for offline operation and data privacy

Open Deep Research is an AI-powered web research agent that combines a reasoning model with live web search and data extraction to perform deep, multi-source investigations on any topic. It operates through a dual interface, offering both a command-line tool and a Model Context Protocol server, allowing developers to integrate web capabilities directly into AI agents and coding assistants. The project distinguishes itself by orchestrating an iterative research loop where a reasoning model plans steps, interprets search results, and guides subsequent web interactions. It uses Firecrawl for scr

Firecrawl is a web data extraction platform designed to convert unstructured web content into clean, LLM-ready formats like markdown or JSON. It functions as an autonomous web crawler and scraper, capable of mapping entire domains, performing recursive navigation, and executing complex data gathering tasks. By leveraging headless browser orchestration, the system handles dynamic, JavaScript-heavy pages to ensure comprehensive data capture. The platform distinguishes itself through its focus on agentic workflows, providing a programmatic interface that allows autonomous agents to perform live