langchain-ai/deepagents

Source
GitHub
First trending
Category
Agents
GitHub stars
29,495
Main language
Python
Website
docs.langchain.com/deepagents (opens in a new tab)

This page introduces an external open-source repository. It is not an HDATF product.

langchain-ai/deepagents

What it does

An open source agent harness on LangGraph that works with any tool-calling model. It includes sub-agents with isolated context, a pluggable filesystem, context summarization, persistent memory, skills, MCP tools and human approval of tool calls.

How it helps ATF

It covers ground similar to Harness, so it is worth comparing on checkpointed state, long context management, sub-agents and human approval of tool calls. Its pluggable memory backends are also a reference for memory across sessions.

License

MIT Permissive. Commercial use and changes are allowed if the copyright notice is kept.

More in this category

  • THU-MAIC/OpenMAIC
    OpenMAIC generates interactive multi-agent classroom courses from a prompt. Its agent workbench plans, builds and revises course pages from uploaded materials, with server-backed sessions that can be cancelled, resumed and steered.
  • TauricResearch/TradingAgents
    TradingAgents is a multi-agent LLM framework for financial trading. Agents in roles such as research manager, trader and portfolio manager use macro data, sentiment and price data to reach trading decisions.
  • aiming-lab/AutoResearchClaw
    AutoResearchClaw is a staged pipeline that takes a research idea from chat to a written paper, either autonomously or with a human co-pilot. Its experiment stages route work to domain-specific agents, such as physics, biology and statistics executors.
  • HKUDS/CLI-Anything
    CLI-Anything builds command line interfaces that let AI agents operate existing software. CLI-Hub is a registry for browsing, installing and managing community-built CLIs, and the project demos show agents producing CAD builds, 3D scenes, diagrams and subtitles.
  • agentscope-ai/agentscope
    AgentScope is a framework for building and running LLM agents that relies on the model's own reasoning and tool use instead of rigid prompts. Recent versions add realtime voice agents, the A2A protocol and multi-agent pipelines.

Only repositories in the ranked Trendshift lists are included, and the lists are used only to find candidates. We do not copy their ranks. Descriptions, licenses and star counts come from each GitHub repository. The notes are our own reading. We have not tested these projects, and a place on a trending list does not prove quality.

View on GitHub (opens in a new tab)