Top 23 ai-agent Open-Source Projects

1. n8n

   1 454 191,300 10.0 TypeScript

   n8n is a workflow automation platform for building AI-powered workflows and agents, connecting any AI model to any business system with full control over data, security, and deployment. Build visually or in code while n8n handles infrastructure from prototype to production with fully auditable executions.

   

   Project mention: SOC-in-a-Box: One LLM, Eight Hats, A Production-Bar AI SOC on a Single GPU | dev.to | 2026-06-06

   n8n and similar visual workflow tools were on the list for one specific reason: leadership likes seeing the boxes-and-arrows. But the LLM nodes aren't first-class — you'd be wrapping every model call in HTTP, and the graph is in a database, not in code that's reviewable in a PR. Auditability and reproducibility are both worse than the LangGraph + bus path. (n8n is a great fit for non-LLM SOAR-style automations, just not for this.)

2. SaaSHub

   www.saashub.com featured

   SaaSHub - Software Alternatives and Reviews. SaaSHub helps you find the best software and product alternatives

   

3. firecrawl

   2 19 128,993 9.9 TypeScript

   The API to search, scrape, and interact with the web at scale. 🔥

   

   Project mention: I scanned Dub's codebase. It's not a link shortener. | dev.to | 2026-05-26

   generate-lander.ts — This is the interesting one. It uses Anthropic + Firecrawl to scrape a partner's website, then generates a custom landing page for their affiliate program. Automated partner onboarding.

4. browser-use

   3 58 97,236 10.0 Python

   Open-source browser automation framework for AI agents. Browser Use lets AI agents control real browser sessions to complete multi-step web workflows.

   

   Project mention: What Is browser-use? And How to Run It Through Lynkr | dev.to | 2026-06-07

   browser-use: https://github.com/browser-use/browser-use

5. Prompt-Engineering-Guide

   4 100 75,276 8.3 MDX

   🐙 Guides, papers, lessons, notebooks and resources for prompt engineering, context engineering, RAG, and AI Agents.

   

   Project mention: Your AI is not bad, your instructions are | dev.to | 2026-05-22

   Prompt Engineering Guide

6. daytona

   5 20 72,497 9.9 TypeScript

   Daytona is a Secure and Elastic Infrastructure for Running AI-Generated Code

   

   Project mention: How Daytona Works: The Complete Guide to AI-Powered Development Environments | dev.to | 2026-05-31

   GitHub: https://github.com/daytonaio/daytona

7. deer-flow

   6 15 70,440 9.9 Python

   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.

   

   Project mention: DeerFlow 2.0 – Deep Exploration and Efficient Research Flow | news.ycombinator.com | 2026-05-17

8. ai-agents-for-beginners

   7 7 66,567 9.8 Jupyter Notebook

   12 Lessons to Get Started Building AI Agents

   

   Project mention: 10 Best AI Engineering GitHub Repos to Build Real Systems | dev.to | 2026-01-07

   A free, structured 11-lesson course to start AI agents the right way. Think of it as turn-by-turn directions for agents, minus the detours and dead ends. Link: https://github.com/microsoft/ai-agents-for-beginners

9. anything-llm

   8 48 61,083 9.7 JavaScript

   Stop renting your intelligence. Own it with AnythingLLM. Everything you need for a powerful local-first agent experience

   

   Project mention: NVIDIA RTX Spark: What the Backlash Gets Wrong About AI on Your Desktop [2026] | dev.to | 2026-06-04

   The headline marketing number is "1 petaflop" of AI performance. Sounds staggering. Tim Carambat, creator of AnythingLLM and one of the most credible voices in the local AI developer community, has already questioned this figure. His point is one I've validated repeatedly in my own benchmarking: for running large language models locally, memory bandwidth is the actual bottleneck, not raw FLOPS. You can have all the tensor cores in the world, but if you can't feed them data fast enough, your Llama 3 inference is still going to crawl.

10. oh-my-openagent

    9 15 60,999 10.0 TypeScript

    omo; the one and only agent harness for complex codebases. the pickaxe for complex software engineering. For your Codex, for your OpenCode

    

    Project mention: Agent-Model Matching Guide | news.ycombinator.com | 2026-06-02

11. crewAI

    10 27 52,870 9.8 Python

    Framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks.

    

    Project mention: SOC-in-a-Box: One LLM, Eight Hats, A Production-Bar AI SOC on a Single GPU | dev.to | 2026-06-06

    CrewAI is excellent at what it's designed for: a "crew" of role-shaped agents collaborating on one task. Declarative Agent + Task + Process (sequential or hierarchical), with strong primitives for delegation between agents inside the same crew.

12. agno

    11 22 40,537 9.9 Python

    Build, run, and manage agent platforms.

    

    Project mention: AI Agents: Mastering 3 Essential Patterns (Tool Using). Part 1 of 3 | dev.to | 2026-01-03

    In this series of articles, we will explore three fundamental patterns in AI Agent development. We will use Python and the Agno framework, available on Github.

13. antigravity-awesome-skills

    12 5 39,700 9.9 Python

    Installable GitHub library of 1,500+ agentic skills for Claude Code, Cursor, Codex CLI, Gemini CLI, Antigravity, and more. Includes specialized plugins, installer CLI, bundles, workflows, and official/community skill collections.

    

    Project mention: How does an AI agent pick from 686 skills in a second? | dev.to | 2026-05-23

    Corpus. antigravity-awesome-skills, a public collection of Anthropic-format skills from the community. 4,556 SKILL.md files, deduplicated by directory. Each file has a YAML frontmatter (name, description, tags) and a markdown body.

14. agents

    13 4 36,406 9.6 Python

    Multi-harness agentic plugin marketplace for Claude Code, Codex CLI, Cursor, OpenCode, and Gemini CLI

    

    Project mention: Repository Transformation: From Chaos to Professional Prompt Engineering Toolkit | dev.to | 2026-03-25

    Prominently featured 74 professional AI agent configurations adapted from wshobson/agents:

15. oh-my-claudecode

    14 2 35,704 10.0 TypeScript

    Teams-first Multi-agent orchestration for Claude Code

    

    Project mention: Your AI agent works alone. No plan, no tests, no review. 118,000 developers found a fix. | dev.to | 2026-03-29

    oh-my-claudecode (13,996 stars) takes the team approach. Its Team mode runs a staged pipeline: team-plan, team-prd, team-exec, team-verify, team-fix. Since v4.4.0, it can run Claude, Codex, and Gemini at the same time using tmux workers. You can send code reviews to Codex, UI tasks to Gemini, and integration work to Claude in one command:

16. Vane

    15 9 35,178 9.7 TypeScript

    Vane is an AI-powered answering engine.

    

    Project mention: AI Infrastructure on Consumer Hardware | dev.to | 2025-11-21

    Perplexica - Self-hosted AI search

17. langgraph

    16 40 33,889 9.9 Python

    Build resilient agents.

    

    Project mention: Agent-Ready Engineering Infrastructure | dev.to | 2026-05-05

    LangGraph AGENTS.md

18. PageIndex

    17 18 32,583 9.3 Python

    📑 PageIndex: Document Index for Vectorless, Reasoning-based RAG

    

    Project mention: AI Builder Notes - May 2026 | dev.to | 2026-06-01

    Birdclaw is interesting because it gives agents access to a Twitter archive. [17] GBrain points at a personal recall layer around OpenClaw / Hermes-style workflows. [18] PageIndex is a useful reminder that simple retrieval, even BM25-only retrieval, still has a place. [19] The “RAG comeback in about 8 months” take lands because the archive problem is still unsolved in practice. [20]

19. 500-AI-Agents-Projects

    18 1 31,655 7.1

    The 500 AI Agents Projects is a curated collection of AI agent use cases across various industries. It showcases practical applications and provides links to open-source projects for implementation, illustrating how AI agents are transforming sectors such as healthcare, finance, education, retail, and more.

    

    Project mention: Curated list of 500 AI Agents and their use cases across industries | news.ycombinator.com | 2025-08-31

20. nanoclaw

    19 14 29,708 9.7 TypeScript

    A lightweight alternative to OpenClaw that runs in containers for security. Connects to WhatsApp, Telegram, Slack, Discord, Gmail and other messaging apps,, has memory, scheduled jobs, and runs directly on Anthropic's Agents SDK

    

    Project mention: I Use NanoClaw in Telegram All Day. I Stopped Typing to It. | dev.to | 2026-03-28

    Clone github.com/qwibitai/nanoclaw

21. composio

    20 9 28,600 10.0 TypeScript

    Composio powers 1000+ toolkits, tool search, context management, authentication, and a sandboxed workbench to help you build AI agents that turn intent into action.

    

    Project mention: pass@1 is a gamble — how ensemble coding enhances AI reliability | dev.to | 2026-04-02

    The ensemble idea is in the air. Mozilla AI's Star Chamber fans out code reviews to Claude, GPT, and Gemini in parallel, using consensus tiers and optional debate rounds where anonymized feedback circulates back to all models. Karpathy's llm-council runs a deliberation pipeline — parallel query, peer review, chairman synthesis — for general-purpose tasks. Roundtable orchestrates multiple AI CLI tools through a unified MCP interface. Composio's Agent Orchestrator manages parallel coding agents with git worktrees for task decomposition — different agents working on different sub-tasks. And Aider's Architect Mode pairs two models in complementary roles (planner + editor).

22. chroma

    21 70 28,214 9.9 Rust

    Search infrastructure for AI

    

    Project mention: The AI stack every developer will depend on in 2026 | dev.to | 2026-05-19

    LanceDB and Chroma: Lightweight local layers for fast recall and offline persistence

23. OpenViking

    22 3 25,147 9.8 Python

    OpenViking is an open-source context database designed specifically for AI Agents(such as openclaw). OpenViking unifies the management of context (memory, resources, and skills) that Agents need through a file system paradigm, enabling hierarchical context delivery and self-evolving.

    

    Project mention: ما هو أوبن فايكنج؟ شرح شامل ومبسط | dev.to | 2026-03-19

24. awesome-agent-skills

    23 6 24,333 9.4

    A curated collection of 1000+ agent skills from official dev teams and the community, compatible with Claude Code, Codex, Gemini CLI, Cursor, and more.

    

    Project mention: Are Claude skills safe in 2026? What the Snyk ToxicSkills audit actually found | dev.to | 2026-05-30

    There are free options. The alirezarezvani/claude-skills repo ships 329 skills with 5,200+ GitHub stars. The VoltAgent/awesome-agent-skills collection has 1,000+. They are good lists. They are not audited.

ai-agents related posts

• Why RAG needs context judgment, not just better retrieval

  1 project | dev.to | 7 Jun 2026

• What Is browser-use? And How to Run It Through Lynkr

  1 project | dev.to | 7 Jun 2026

• SOC-in-a-Box: One LLM, Eight Hats, A Production-Bar AI SOC on a Single GPU

  6 projects | dev.to | 6 Jun 2026

• n8n Tutorial: How to Build Your First No-Code Automation Workflow in 2026

  1 project | dev.to | 6 Jun 2026

• Hermes – Community Web UI with Agent

  1 project | news.ycombinator.com | 6 Jun 2026

• Ask HN: What is your (AI) dev tech stack / workflow? (June 2026)

  32 projects | news.ycombinator.com | 5 Jun 2026

• Three checks that separate an agent demo from a production agent

  1 project | dev.to | 6 Jun 2026
• A note from our sponsor - SaaSHub
  www.saashub.com | 7 Jun 2026

  SaaSHub helps you find the best software and product alternatives Learn more →

Index

Sponsored

SaaSHub - Software Alternatives and Reviews

SaaSHub helps you find the best software and product alternatives

www.saashub.com