Tongyi Deep Research, the Leading Open-source Deep Research Agent
☆20,028Feb 27, 2026Updated 7 months ago
Alternatives and similar repositories for DeepResearch
Users that are interested in DeepResearch are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- ☆12,681Aug 10, 2026Updated 2 months ago
- verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework☆23,825Updated this week
- Agent framework and applications built upon Qwen>=3.0, featuring Function Calling, MCP, Code Interpreter, RAG, Chrome extension, etc.☆17,164Mar 4, 2026Updated 7 months ago
- DeepResearchAgent is a hierarchical multi-agent system designed not only for deep research tasks but also for general-purpose task solvin…☆3,557May 4, 2026Updated 5 months ago
- Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)☆75,409Updated this week
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- An open-source long-horizon SuperAgent harness that researches, codes, and creates. With the help of sandboxes, memories, tools, skill, s…☆83,687Updated this week
- The Memory Layer for AI Agents - Drop-in memory infrastructure for AI agents and apps. Context that persists. Built for production.☆66,978Updated this week
- The absolute trainer to light up AI agents.☆18,655Updated this week
- A high-throughput and memory-efficient inference and serving engine for LLMs☆93,564Updated this week
- Search-R1: An Efficient, Scalable RL Training Framework for Reasoning & Search Engine Calling interleaved LLM based on veRL☆5,493Nov 13, 2025Updated 10 months ago
- "DeepCode: Open Agentic Coding (Agent Harness & Loop Engineering & Multi-Agent Orchestration)"☆16,696Updated this week
- No fortress, purely open ground. OpenManus is Coming.☆58,611Sep 30, 2026Updated last week
- Local UI to run and train LLMs and diffusion models. Supports GGUF, MLX, Qwen3.8, DeepSeek-V4, MiniMax-H3, Gemma 4, FLUX and more.☆77,772Updated this week
- RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to creat…☆91,998Updated this week
- Managed Database hosting by DigitalOcean • AdPostgreSQL, MySQL, MongoDB, Kafka, Valkey, and OpenSearch available. Automatically scale up storage and focus on building your apps.
- Build Real-Time Knowledge Graphs for AI Agents☆31,640Updated this week
- Build and run agents you can see, understand and trust.☆33,079Updated this week
- Democratizing Reinforcement Learning for LLMs☆5,860Updated this week
- Recursive-Open-Meta-Agent v0.1 (Beta). A meta-agent framework to build high-performance multi-agent systems.☆5,180Feb 16, 2026Updated 7 months ago
- slime is an LLM post-training framework for RL Scaling.☆8,632Updated this week
- MiroThinker is a deep research agent optimized for complex research and prediction tasks. Our latest models, MiroThinker-1.7, achieves 74…☆8,426Jul 6, 2026Updated 3 months ago
- [EMNLP2025] LightRAG: Simple and Fast Retrieval-Augmented Generation☆40,067Updated this week
- Fully Local Manus AI. No APIs, No $200 monthly bills. Enjoy an autonomous agent that thinks, browses the web, and code for the sole cost …☆27,468Oct 2, 2026Updated last week
- A modular graph-based Retrieval-Augmented Generation (RAG) system☆36,289Updated this week
- Open source password manager - Proton Pass • AdSecurely store, share, and autofill your credentials with Proton Pass, the end-to-end encrypted password manager trusted by millions.
- Get started with building Fullstack Agents using Gemini 2.5 and LangGraph☆18,346Jun 14, 2026Updated 3 months ago
- The RL Bridge for LLM-based Agent Applications. Made Simple & Flexible.☆5,828Updated this week
- Agent Reinforcement Trainer: train multi-step agents for real-world tasks using GRPO. Give your agents on-the-job training. Reinforcement…☆10,792Updated this week
- Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3.8, DeepSeek-V4, GLM-5.1, InternLM3, Llama4, ...) and 300+ MLLMs (Qwen3-VL…☆15,811Updated this week
- Build reliable customer-facing AI agents with Parlant: an interaction control harness optimized for controlled, consistent, and predictab…☆18,297Jul 12, 2026Updated 2 months ago
- SGLang is a high-performance serving framework for large language models and multimodal models.☆36,988Updated this week
- The Open-Source Multimodal AI Agent Stack: Connecting Cutting-Edge AI Models and Agent Infra☆39,233Updated this week
- Build, run, and manage agent platforms.☆42,667Updated this week
- Agents that use the browser.☆117,636Updated this week
- GPU virtual machines on DigitalOcean Gradient AI • AdGet to production fast with high-performance AMD and NVIDIA GPUs you can spin up in seconds. The definition of operational simplicity.
- An Easy-to-use, Scalable and High-performance Agentic RL Framework based on Ray (PPO & DAPO & REINFORCE++ & VLM & TIS & vLLM & Ray & Asy…☆10,079Updated this week
- 🙌 OpenHands: AI-Driven Development☆90,584Updated this week
- Qwen3 is the large language model series developed by Qwen team, Alibaba Cloud.☆27,664Jan 9, 2026Updated 9 months ago
- Vane is an AI-powered answering engine.☆37,247Sep 1, 2026Updated last month
- Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.☆81,460Updated this week
- Build Agentic workflows, RAG pipelines, with rich AI model and tool support on one collaborative workspace. Deploy on cloud, VPC, or self…☆158,149Updated this week
- Qwen3-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.☆20,059Jan 30, 2026Updated 8 months ago