SaaSHub helps you find the best software and product alternatives Learn more →
Top 23 ai-agent Open-Source Projects
-
n8n
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.
Source: the n8n advisory GHSA-89gh-3pgc-v5h2.
-
AppSignal
AppSignal knows why the f*#k it crashed. Stop vibe-debugging. Every exception, every backtrace, grouped so you see patterns, not noise.
-
firecrawl
Supercharge your AI agents with data from the web and beyond. Building the library for superintelligence. 🔥
Project mention: A 200 OK is not an article: the bug that made me write my own web layer in Rust | dev.to | 2026-09-22I'm not going to pretend the field is empty. Firecrawl is the hosted API you can call from a lambda. If you live in Python, Crawl4AI is mature and ships a Docker server. Scrapling does adaptive parsing with session and proxy control. For plain browser automation over MCP the reference answer is still Playwright MCP. All four are in the repo's comparison table, and if you want a URL you can hit from a serverless function, use a hosted service.
-
ponytail
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
Project mention: Claude Code Skills Worth Trying: From Vague Idea to Finished Feature | dev.to | 2026-09-14Ponytail for keeping implementations simple.
-
Project mention: Why does my vector DB retrieval keep returning duplicate noise for my chat agent, and how to fix it? | dev.to | 2026-10-07
In langchain-qdrant, LangChain's lambda_mult reaches Qdrant as its diversity, so the direction flips, as an open LangChain bug report records. At 0.5 the two readings coincide; the trap opens when you move it.
-
browser-use
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: Browser Use vs Skyvern Self-Hosted: Setup, Trade-offs, and Completion Verification | dev.to | 2026-10-03We also separated the product shapes. Browser Use is primarily an embeddable MIT-licensed agent library. Skyvern is a larger AGPL-licensed workflow platform with an API server, web interface, database, browser runtime, workflow state, and operational views.
-
Project mention: Google Quietly Dropped 12 Free AI Tools. Developers Should Probably Care. | dev.to | 2026-08-07
-
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.
DeerFlow is developed by ByteDance and the DeerFlow community. Its name originally stood for Deep Exploration and Efficient Research Flow, but an important distinction now exists between the original 1.x Deep Research framework and DeerFlow 2.0.
-
SaaSHub
SaaSHub - Software Alternatives and Reviews. SaaSHub helps you find the best software and product alternatives
-
Prompt-Engineering-Guide
🐙 Guides, papers, lessons, notebooks and resources for prompt engineering, context engineering, RAG, and AI Agents.
Project mention: Text-to-Image APIs Explained: Node.js Backend Trade-offs for Property Marketing | dev.to | 2026-09-30Prompt Engineering Guide: https://www.promptingguide.ai
-
The patterns are the other half. DeepLearning.AI's course organises them into four: reflection, tool use, planning, and multi-agent workflows (DeepLearning.AI); those four names recur across almost every serious syllabus. Microsoft's free AI Agents for Beginners repository covers the same ground plus RAG, memory, agent security and the MCP and A2A protocols across 15 lessons, and has passed 68,000 stars (GitHub).
-
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
Ruflo repository -- the multi-agent orchestration platform
-
Project mention: Choosing the Best Cloud Infrastructure for AI Agents: A Comprehensive 2026 Guide | dev.to | 2026-10-05
Daytona offers a versatile ecosystem that defaults to containers but allows for VM and GPU upgrades. It is particularly strong for enterprise use cases requiring SSH access and robust SDK support across multiple languages.
-
oh-my-openagent
OmO: Just type "mass ulw" keyword with your prompt. Now you are the master of graph engineering.
-
mem0
The Memory Layer for AI Agents - Drop-in memory infrastructure for AI agents and apps. Context that persists. Built for production.
Project mention: 07 - From Knowledge Base to Long-Term Memory: How I Understand an Agent Memory System | dev.to | 2026-10-07The official example shows a straightforward path: first search related memories by the current question and user scope, add the results to the model input, complete the conversation, then hand new content to the memory layer for processing. It provides an SDK and service interfaces, and distinguishes between the open-source library, self-hosted deployment, and managed service. Mem0 project
-
anything-llm
Stop renting your intelligence. Own it with AnythingLLM. Everything you need for a powerful local-first agent experience
AnythingLLM lets you create your own AI assistant that can work with your documents.
-
crewAI
Framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks.
Primary sources: CVE-2026-37008 on NVD · MITRE CNA record · GHSA-2q68-3cp7-72v9 · Fix commit fb2323b · CERT/CC VU#221883
-
agentic-awesome-skills
AAS Core is the local, agent-first control plane for complete catalog discovery, agent-owned selection, stack validation, and planning, backed by 2,400+ agentic skills. Includes CLI, local MCP, catalog, plugins, and Workbench.
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.
-
herdr is the terminal multiplexer on my laptops. Unlike tmux, it knows which pane is an agent and whether that agent is working, blocked, done or idle:
-
Project mention: Spending Limits for LangGraph Agents That a Prompt Injection Can't Talk Past | dev.to | 2026-10-04
This isn't hypothetical. langchain-ai/langgraph#9120 documents it directly against LangGraph's own customer-support tutorial: the agent's refund cap and access restrictions live in natural-language prompt instructions, and adversarial testing showed the agent could be talked past them, for example approving a refund over its stated limit when the input described an urgent, litigation-flavored scenario. The issue reports 100% of adversarial tests breaking the limit when the only guard was the prompt, dropping to 0% once the fix moved to runtime validation at the tool boundary: decorators that enforce numeric caps and restrict admin actions before the underlying call fires, independent of what the prompt says.
-
The same ask keeps resurfacing across frameworks (smolagents #901, Agno #2500, Letta #957), and the honest summary is: memory grows unbounded unless something prunes it, and real consolidation is hard. It's worth finding out what in your store ever takes a record back out of the retrievable set - an expiry, a state you can set, a pass that runs on its own - and whether that is the store doing it or you remembering to. I won't claim Engrava has solved forgetting - it hasn't.
-
agents
Multi-harness agentic plugin marketplace for Claude Code, Codex, Cursor, OpenCode, GitHub Copilot, Google Antigravity, and Pi
Project mention: Skills Sprawl: When Too Much of a Good Thing Confuses Your AI Agent | dev.to | 2026-08-17Specialised & Community Skills: Niche skills sourced from specific community repositories, including wshobson/agents (documentation-and-adrs, interview-me), coreyhaines31/marketingskills (seo-audit), remotion-dev/skills (remotion-best-practices), and vercel-labs/skills (find-skills).
-
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:
-
OpenViking
Self-evolving Context Database for AI Agents. Unify Agent Memory, Knowledge RAG and Skills.
Project mention: OpenViking’s Filesystem View of Agent Context Is a Welcome Escape from RAG Glue Code | dev.to | 2026-09-05git clone https://github.com/volcengine/OpenViking.git cd OpenViking pip install -e . python -m openviking.server --config config.yaml
-
-
SaaSHub
SaaSHub - Software Alternatives and Reviews. SaaSHub helps you find the best software and product alternatives
NOTE:
The open source projects on this list are ordered by number of github stars.
The number of mentions indicates repo mentiontions in the last 12 Months or
since we started tracking (Dec 2020).
ai-agents discussion
ai-agents related posts
-
"Just use RBAC" is half right. Here's the other half for AI agents.
-
My embedding model couldn't find "order 48207". Here's the one-line fix and what LongMemEval said next.
-
Reverse Engineer Anything
-
I Gave My AI Agents an Org Chart
-
Screening the payee of an x402 payment with Privy: OFAC, UN, EU and UK in one signed call
-
I connected Contentful to Cognee. Importing content was the easy part.
-
A failed SQLite integrity check on Windows that reported itself as a POSIX lock conflict
-
A note from our sponsor - SaaSHub
www.saashub.com | 8 Oct 2026
Index
What are some of the best open-source ai-agent projects? This list will help you:
| # | Project | Stars |
|---|---|---|
| 1 | n8n | 206,604 |
| 2 | firecrawl | 188,065 |
| 3 | ponytail | 155,167 |
| 4 | langchain | 147,425 |
| 5 | browser-use | 117,003 |
| 6 | gemini-cli | 107,220 |
| 7 | deer-flow | 83,528 |
| 8 | Prompt-Engineering-Guide | 78,900 |
| 9 | ai-agents-for-beginners | 76,410 |
| 10 | ruflo | 73,732 |
| 11 | daytona | 71,674 |
| 12 | oh-my-openagent | 69,901 |
| 13 | mem0 | 66,809 |
| 14 | anything-llm | 66,670 |
| 15 | crewAI | 59,291 |
| 16 | agentic-awesome-skills | 47,168 |
| 17 | herdr | 42,938 |
| 18 | langgraph | 42,600 |
| 19 | agno | 42,542 |
| 20 | agents | 40,180 |
| 21 | oh-my-claudecode | 39,659 |
| 22 | OpenViking | 39,122 |
| 23 | PageIndex | 38,512 |
Sponsored
AppSignal knows why the f*#k it crashed.
Stop vibe-debugging. Every exception, every backtrace, grouped so you see patterns, not noise.
www.appsignal.com