1.AhmadHassan-BTed / AutoSwarm-Shadow-Adapter
Zero-modification Human-in-the-Loop adapter for OpenOPC's agentic DAG runtime.
+1,569 stars
from 3,470 · score 7.36
Trending repositories
Ranked by Attention Score: stars gained over the last 7 complete days
21 repositories by Attention Score · Oct 27, 2026 – Nov 2, 2026 (UTC)
2.ruvnet / ruflo
🌊 The original agent harness. Deploy intelligent multi-player swarms, coordinate autonomous workflows, and build conversational AI systems. Features adaptive memory, self-learning intelligence, federation, vector RAG integration, and native Claude Code / Codex / Hermes and many more Integrated
+1,262 stars
from 79,279 · score 7.14
3.langgenius / dify
Build Agentic workflows, RAG pipelines, with rich AI model and tool support on one collaborative workspace. Deploy on cloud, VPC, or self-hosted, so teams move from prototype to production without rebuilding the stack.
+647 stars
from 159,524 · score 6.47
4.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.
+423 stars
from 84,416 · score 6.05
5.shanraisshan / claude-code-best-practice
from vibe coding to agentic engineering - practice makes claude perfect
+360 stars
from 68,068 · score 5.89
6.Mintplex-Labs / anything-llm
Stop renting your intelligence. Own it with AnythingLLM. Everything you need for a powerful local-first agent experience
+278 stars
from 67,552 · score 5.63
7.ag-ui-protocol / ag-ui
AG-UI: the Agent-User Interaction Protocol. Bring Agents into Frontend Applications.
+149 stars
from 16,813 · score 5.01
8.Sidiora-Labs / hyperfide
The ai agent workflow tool that scales from small, simple projects to large, complex codebases.
+119 stars
from 520 · score 4.79
9.LodyAI / Lody
Share coding agents with your team on phone and desktop
+78 stars
from 1,562 · score 4.37
10.eigent-ai / eigent
Eigent: The Open Source Cowork Desktop - Local and Free Alternative to Claude Cowork and Codex
+53 stars
from 15,659 · score 3.99
11.simstudioai / sim
Sim is the collaborative workspace to build, deploy, and monitor AI agents and workflows. Used by 100,000+ builders.
+44 stars
from 29,917 · score 3.81
12.thomasunise / argus
Open-source agentic security operations platform:
+22 stars
from 96 · score 3.14
13.The-Pocket / PocketFlow
Pocket Flow: 100-line LLM framework. Let Agents build Agents!
+16 stars
from 11,279 · score 2.83
14.jazzyalex / agent-sessions
Local-first macOS app to browse, search, analyze, and resume supported AI coding-agent session history across Codex, Claude Code, OpenCode, Cursor Agent, Antigravity, Hermes, OpenClaw, Copilot CLI, and more.
+15 stars
from 916 · score 2.77
15.FlowiseAI / FlowiseArchived
Build AI Agents, Visually
+14 stars
from 55,528 · score 2.71
16.kedro-org / kedro
Kedro is a toolbox for production-ready data science. It uses software engineering best practices to help you create data engineering and data science pipelines that are reproducible, maintainable, and modular.
+6 stars
from 11,034 · score 1.95
17.Gen-Verse / DiscoveryRSI
DiscoveryRSI: Recursively Learning to Discover Valuable Hypotheses
+6 stars
from 136 · score 1.95
18.RichardKnop / minisql
Embedded single file SQL database written in Golang
+2 stars
from 52 · score 1.10
19.lofcz / LLMTornado
The .NET library to build AI agents with 30+ built-in connectors.
+1 stars
from 649 · score 0.69
20.Ivy-Interactive / Ivy-Tendril
AI agents can now write 99% of the code. This changes what it means to be a developer. Our role shifts to knowing "what good looks like". To do that, we need completely new developer tools. Tendril is what replaces your IDE in an agentic era.
+1 stars
from 203 · score 0.69
21.metavert-io / lightcms
Self-hosted CMS that works human or headless: full admin UI plus REST and MCP APIs, built-in semantic search and site chat, and content forking, versioning, diff/merge review, templates, approvals, and static page generation.
+1 stars
from 32 · score 0.69