1.HKUDS / Vibe-Trading
"Vibe-Trading: Your Personal Trading Agent"
+8,085 stars
from 29,294 · score 9.00
Trending repositories
Ranked by Attention Score: stars gained over the last 90 complete days
20 repositories by Attention Score · Aug 5, 2026 – Nov 2, 2026 (UTC)
2.agentscope-ai / agentscope
Build and run agents you can see, understand and trust.
+6,734 stars
from 28,391 · score 8.82
3.bytedance / deer-flow
An open-source long-horizon SuperAgent harness that researches, codes, and creates. With the help of sandboxes, memories, tools, skill, subagents and message gateway, it handles different levels of tasks that could take minutes to hours.
+6,181 stars
from 78,658 · score 8.73
4.AhmadHassan-BTed / AutoSwarm-Shadow-Adapter
Zero-modification Human-in-the-Loop adapter for OpenOPC's agentic DAG runtime.
+5,293 stars
from 14 · score 8.57
5.wshobson / agents
Multi-harness agentic plugin marketplace for Claude Code, Codex, Cursor, OpenCode, GitHub Copilot, Google Antigravity, and Pi
+3,856 stars
from 38,225 · score 8.26
6.HKUDS / nanobot
Your lightweight open-source personal agent.
+3,577 stars
from 46,155 · score 8.18
7.microsoft / agent-framework
A framework for building, orchestrating and deploying AI agents and multi-agent workflows with support for Python and .NET.
+1,958 stars
from 12,524 · score 7.58
8.FoundationAgents / MetaGPT
🌟 The Multi-Agent Framework: First AI Software Company, Towards Natural Language Programming
+1,781 stars
from 69,345 · score 7.49
9.zhayujie / CowAgent
Open-source personal AI assistant & Agent Harness. Plans tasks, runs tools and skills, self-evolves with memory and knowledge. Multi-agent, multi-model, multi-channel. Lightweight, extensible, one-line install.
+1,709 stars
from 46,026 · score 7.44
10.google / adk-python
An open-source, code-first Python toolkit for building, evaluating, and deploying sophisticated AI agents with flexibility and control.
+1,182 stars
from 20,892 · score 7.08
11.cft0808 / edict
🏛️ 三省六部制 · OpenClaw Multi-Agent Orchestration System — 9 specialized AI agents with real-time dashboard, model config, and full audit trails
+915 stars
from 16,124 · score 6.82
12.deepset-ai / haystack
Open-source AI orchestration framework for building context-engineered, production-ready LLM applications. Design modular pipelines and agent workflows with explicit control over retrieval, routing, memory, and generation. Built for scalable agents, RAG, multimodal applications, semantic search, and conversational systems.
+891 stars
from 26,011 · score 6.79
13.WenyuChiou / ai-research-skills
Universal SKILL.md catalog for research workflows: literature review, research design, project memory, manuscript writing, and cross-agent delegation for Claude Code, Codex, Gemini, Cursor, OpenClaw, and generic AI clients.
+348 stars
from 187 · score 5.86
14.Lumiwealth / lumibot
Python trading framework with AI agents that actually place the trade. Backtest, paper and live trade on 12 brokers: stocks, options, futures, forex, crypto and prediction markets.
+327 stars
from 1,867 · score 5.79
15.ag2ai / ag2
AG2 (formerly AutoGen): The Open-Source AgentOS.Join us at: https://discord.gg/sNGSwQME3x
+234 stars
from 4,805 · score 5.46
16.learnsyslab / gym-pybullet-drones
PyBullet Gymnasium environments for single and multi-agent reinforcement learning of quadcopter control
+105 stars
from 2,089 · score 4.66
17.Toni-SM / skrl
Modular Reinforcement Learning (RL) library (implemented in PyTorch, JAX, and NVIDIA Warp) with support for Gymnasium/Gym, NVIDIA Isaac Lab, MuJoCo Playground and other environments
+23 stars
from 1,078 · score 3.18
18.futuresearch / futuresearch-python
Forecast what will happen, including outcomes of your decisions.
+8 stars
from 49 · score 2.20
19.WenyuChiou / agent-collab-skills
Claude Code marketplace for multi-agent collaboration — task splitter, output reconciler, adversarial debate, shared memory, acceptance gate. Composes with codex-delegate / gemini-delegate.
+8 stars
from 23 · score 2.20
20.anthony-chaudhary / dos-kernel
Catch your AI agents when they lie about what they shipped — verifies claims against git instead of believing the agent.
+2 stars
from 18 · score 1.10