1.deepseek-ai / deepseek-harness
DeepSeek Harness: Everything is a Plugin.
- cordis
- dsh
- dsh-plugin
- ai-agents
+7,427 stars
from 263,654 · score 8.91
Trending repositories
Ranked by Attention Score: stars gained over the last 7 complete days
41 repositories by Attention Score · Oct 28, 2026 – Nov 3, 2026 (UTC)
2.CopilotKit / OpenBot
Open-source AI coworkers that each get a computer of their own: a browser, files and tools, with every action decided before it happens and recorded after. Bring any AG-UI agent.
- ag-ui
- agent-governance
- ai-agents
- browser-automation
- copilotkit
- generative-ui
- +1 more
+2,639 stars
from 7,383 · score 7.88
3.earendil-works / pi
AI agent toolkit: unified LLM API, agent loop, TUI, coding agent CLI
+1,555 stars
from 118,287 · score 7.35
4.langchain-ai / langgraph
Build resilient agents.
+404 stars
from 44,005 · score 6.00
5.langchain-ai / langchain
The agent engineering platform.
+401 stars
from 148,570 · score 6.00
6.langchain-ai / deepagents
The batteries-included agent harness.
+304 stars
from 30,657 · score 5.72
7.HKUDS / nanobot
Your lightweight open-source personal agent.
- ai-agent
- ai-agents
- openclaw
- agent-framework
- chatbot
- chatops
- +14 more
+280 stars
from 49,519 · score 5.64
8.crewAIInc / crewAI
Framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks.
+276 stars
from 60,184 · score 5.62
9.nuglifeleoji / Sentry
Learning to Recover from LLM Agent Failures at Test Time
+267 stars
from 474 · score 5.59
10.langflow-ai / langflow
Langflow is a powerful tool for building and deploying AI-powered agents and workflows.
- react-flow
- chatgpt
- large-language-models
- generative-ai
- agents
- multiagent
+232 stars
from 156,071 · score 5.45
11.CopilotKit / CopilotKit
The Frontend Stack for Agents & Generative UI. React, Angular, Mobile, Slack, and more. Makers of the AG-UI Protocol
+208 stars
from 38,286 · score 5.34
12.rsi-gear / gear
Scikit-learn for Recursive Self-improvement (RSI). A modular framework for recursive harness evolution.
- meta-learning
- reinforcement-learning
- rsi
- ai-agents
- continual-learning
- infrastructure
- +6 more
+202 stars
from 203 · score 5.31
13.xxPcy / PharmaLLM-Agent
Medical LLM agent and MRI segmentation workspace built on PharmaLLM, with LangGraph, vLLM, and BEU-Net.
+191 stars
from 4 · score 5.26
14.microsoft / agent-framework
A framework for building, orchestrating and deploying AI agents and multi-agent workflows with support for Python and .NET.
+182 stars
from 14,343 · score 5.21
15.openai / openai-agents-python
A lightweight, powerful framework for multi-agent workflows
+143 stars
from 30,338 · score 4.97
16.Shyboy0499 / precondition-library
An agent that compiles git maintenance chores into reusable programs, then decides whether to replay them by running checks rather than by guessing the task looks familiar
- agent-architecture
- git-automation
- llm-agents
- program-synthesis
- research
+121 stars
from 210 · score 4.80
17.FoundationAgents / MetaGPT
🌟 The Multi-Agent Framework: First AI Software Company, Towards Natural Language Programming
- agent
- gpt
- llm
- metagpt
- multi-agent
+114 stars
from 71,038 · score 4.74
18.pydantic / pydantic-ai
How Python does AI. Agents, realtime voice, image generation, embeddings. Every model, every interface, typed end to end.
- agent-framework
- pydantic
- python
- genai
- llm
- harness
- +1 more
+108 stars
from 20,908 · score 4.69
19.xingjian-bai / opal
OPAL: a reactive optimizer. A coding agent rewrites the optimizer while your model trains.
- deep-learning
- llm-agents
- optimizer
- pytorch
+103 stars
from 227 · score 4.64
20.run-llama / llama_index
LlamaIndex is the document processing platform for AI
- agents
- application
- data
- fine-tuning
- framework
- llamaindex
- +4 more
+100 stars
from 52,695 · score 4.62
21.elizaOS / eliza
Open source agentic operating system
+88 stars
from 19,678 · score 4.49
22.uclanlp / OpenVLHarness
Official Code for OpenVLHarness: Real-World Visual Agentic Tool‑Use with Multimodal Memory
- agent-harness
- agentic-ai
- ai-agents
- coding-agent
- deep-research
- grounded-reasoning
- +14 more
+86 stars
from 281 · score 4.47
23.EvannZhongg / Nosis
Nosis is a lightweight personal agent runtime: per-session execution boundaries with OS-level sandboxing, computer use, a full built-in toolset, Skill / Plugin / MCP extensions, one runtime shared by GUI and TUI, and file-persisted sessions, plans, and memory.
- agent-framework
- agent-runtime
- agent-skills
- ai-agent
- ai-assistants
- computer-use
- +12 more
+85 stars
from 16 · score 4.45
24.teraus111 / web3-agent-kit-solana-trading
Build autonomous AI agents that interact with blockchains — in minutes, not months.
+80 stars
from 96 · score 4.39
25.eosphoros-ai / DB-GPT
open-source agentic AI data assistant for the next generation of AI + Data products.
+48 stars
from 20,202 · score 3.89
26.HKUDS / OpenHarness
"OpenHarness: Open Agent Harness with a Built-in Personal Agent--Ohmo!"
+45 stars
from 16,117 · score 3.83
27.VoltAgent / voltagent
AI Agent Engineering Platform built on an Open Source TypeScript AI Agent Framework
+34 stars
from 10,883 · score 3.56
28.openai / swarm
Educational framework exploring ergonomic, lightweight multi-agent orchestration. Managed by OpenAI Solution team.
+28 stars
from 22,079 · score 3.37
29.togethercomputer / HybridAgent
The repository host gives no description.
+20 stars
from 456 · score 3.04
30.microsoft / semantic-kernel
Integrate cutting-edge LLM technology quickly and easily into your apps
+19 stars
from 28,709 · score 3.00
31.smhanov / agentloop
Everything you need for building an agent. A Go library for the LLM tool-calling loop with budgets, hooks, skills, and tracing.
+19 stars
from 120 · score 3.00
32.The-Pocket / PocketFlow
Pocket Flow: 100-line LLM framework. Let Agents build Agents!
- agents
- flow-based-programming
- flow-engineering
- llm-agent
- llm-framework
- agentic-workflow
- +14 more
+18 stars
from 11,282 · score 2.94
33.Mftrferdinand / Zeline
Zeline — an open-source agentic AI framework developed by Zerolinear.
- ai-agent
- python
- self-hosted
- telegram-bot
- webhook
+18 stars
from 147 · score 2.94
+15 stars
from 18,301 · score 2.77
35.TransformerOptimus / SuperAGI
<⚡️> SuperAGI - A dev-first open source autonomous AI agent framework. Enabling developers to build, manage & run useful autonomous agents quickly and reliably.
- agi
- ai
- autonomous-agents
- python
- agents
- artificial-intelligence
- +9 more
+14 stars
from 17,718 · score 2.71
36.andrewyng / aisuite
Simple, unified interface to multiple Generative AI providers
+13 stars
from 16,362 · score 2.64
+13 stars
from 11,208 · score 2.64
38.tmc / langchaingo
LangChain for Go, the easiest way to write LLM-based programs in Go
+13 stars
from 9,746 · score 2.64
39.AIDotNet / pi.net
TranslatedPi.NET is a .NET 10 port of Pi. Pi is a minimal, extensible Agent harness (a TypeScript monorepo of about 171,000 lines). This project ports its core libraries one by one to net10.0, so that the .NET ecosystem can use the same set of capabilities.
- agent
- agentic-ai
- dotnet
+7 stars
from 107 · score 2.08
+6 stars
from 4,487 · score 1.95
41.paper-instruments / feather-train
Feather agent harness, training integrations, and evaluation tools for knowledge work
+2 stars
from 226 · score 1.10