SaaSHub helps you find the best software and product alternatives Learn more →
Top 23 Python Agent Projects
-
ragflow
RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to create a superior context layer for LLMs
Project mention: I Scanned 5 Popular Open-Source AI Projects for EU AI Act Compliance. Here's What I Found. | dev.to | 2026-03-31I ran AIR Blackbox (the scanner itself), Browser Use (79K+ stars), RAGFlow (76K+ stars), LiteLLM (23K+ stars), and Superlinked (15K+ stars) through the same compliance checks.
-
SaaSHub
SaaSHub - Software Alternatives and Reviews. SaaSHub helps you find the best software and product alternatives
-
OpenHands AGENTS.md
-
Project mention: Llama-Factory: Unified, Efficient Fine-Tuning for 100 Open LLMs | news.ycombinator.com | 2025-09-18
-
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.
Tools have been trending in this direction for the last 3-6 months with features like "Assign to Copilot" in GitHub.com, and the Linear's work tracking system where its unique sales pitch is "write tickets for agents to work on here". The final form of this kind of solution is currently a vague, but there are several projects already pitching to own this space such as Open AI's Symphony project (https://openai.com/index/open-source-codex-orchestration-symphony/), ByteDance's DeerFlow (https://github.com/bytedance/deer-flow) which pitches itself as "an open-source super-agent harness", and other similar projects.
-
MetaGPT
🌟 The Multi-Agent Framework: First AI Software Company, Towards Natural Language Programming
Project mention: Backlog.md – CLI that auto-generates task files (took my Claude success to 95 %) | news.ycombinator.com | 2025-07-06 -
unsloth
Unsloth Studio is a web UI for training and running open models like Gemma 4, Qwen3.6, DeepSeek, gpt-oss locally.
Project mention: I Trained an LLM on 75K of My Own Messages So It Would Stop Writing Like a Chatbot | dev.to | 2026-05-08Training: unsloth + trl (SFTTrainer). Unsloth handles the 4-bit quantization and gradient checkpointing; trl handles the training loop.
-
Note: This is a fork of shareAI-lab/learn-claude-code with all agents migrated from the Anthropic SDK to the OpenAI SDK (openai Python package). All agents work with any OpenAI-compatible endpoint — cloud APIs (OpenAI, GitHub Models, Azure OpenAI) or local servers (LM Studio, Ollama, GPT4All).
-
Agents need to compress work into state. [10] Mem0 positions memory inside the harness alongside tools and coordination. [11] [17]
-
-
khoj
Your AI second brain. Self-hostable. Get answers from the web or your docs. Build custom agents, schedule automations, do deep research. Turn any online or local LLM into your personal, autonomous AI (gpt, claude, gemini, llama, qwen, mistral). Get started - free.
-
AstrBot
AI Agent Assistant & development framework that integrates lots of IM platforms, LLMs, plugins and AI feature, and can be your openclaw alternative. ✨
-
I spent a weekend studying GPT-Researcher, an open-source project with 24,000+ GitHub stars. It builds an autonomous research agent that generates comprehensive reports with citations. The architecture is elegant: multiple specialized agents coordinate through LangGraph, parallel execution speeds up research, and quality gates ensure reliable output.
-
GitHub Link: https://github.com/agentscope-ai/agentscope Summary: Agentscope is an agent-oriented programming library that makes it easier to build LLM applications. It's designed to be "developer-centric" with features like asynchronous execution, parallel tool calls, and real-time steering. It offers a transparent approach where prompt engineering and API invocation are fully visible and controllable. Why it's important: Agentscope, along with its related libraries like agentscope-runtime and agentscope-studio, provides a comprehensive toolkit for not only developing but also deploying and visualizing agent-based applications.
-
OpenViking
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.
-
serena
A powerful MCP toolkit for coding, providing semantic retrieval and editing capabilities - the IDE for your agent
You should add Serena https://github.com/oraios/serena to your list.
Serena gives you symbol-level navigation, reading, and editing via tree-sitter. So you're already getting much of what CoderLM offers — plus Serena has editing capabilities(replace symbol body, insert before/after symbol, rename). GitNexus goes further with the graph/impact analysis layer on top.
I personally use Serena and GitNexus.
The case for using both
- GitNexus tells you what to change (impact analysis, dependency maps, blast radius) -
adk-python
An open-source, code-first Python toolkit for building, evaluating, and deploying sophisticated AI agents with flexibility and control.
Project mention: Google ADK CLI: The Fastest Way to Build and Ship AI Agents in 2026 [Guide] | dev.to | 2026-06-11First, ADK is genuinely multi-model. It supports Gemini, Gemma, Claude (via Vertex), Ollama, vLLM, LiteLLM, and LiteRT-LM. You're not locked into Gemini. You can route different agent tasks to different models based on cost, latency, or capability. This matters in production, where your summarization agent absolutely doesn't need the same model as your code generation agent.
-
owl
🦉 OWL: Optimized Workforce Learning for General Multi-Agent Assistance in Real-World Task Automation
Project mention: Launch: Eigent – Open-Source Local-First Multi-Agent Workforce Built on Camel-AI | news.ycombinator.com | 2025-07-30We built on top of our previous project OWL which ranked top 1 on GAIA: https://github.com/camel-ai/owl in March. For the Eigent update, we haven't got to benchmark it on GAIA yet. Will do it soon in the up coming weeks. Sorry for the confusion.
-
SWE-agent
SWE-agent takes a GitHub issue and tries to automatically fix it, using your LM of choice. It can also be employed for offensive cybersecurity or competitive coding challenges. [NeurIPS 2024]
Project mention: Boost Your Coding Agent and Understand Its Reasoning with 3 Simple Prompts | dev.to | 2025-06-20SWE-Agent
-
Project mention: Tongyi DeepResearch – open-source 30B MoE Model that rivals OpenAI DeepResearch | news.ycombinator.com | 2025-11-02
-
Project mention: OSS Alternative to Open WebUI – ChatGPT-Like UI, API and CLI | news.ycombinator.com | 2025-11-03
-
Microsoft's agent-lightning project offers a comprehensive toolkit aimed at accelerating the process of building, testing, and deploying AI Agents. This open-source initiative highlights the industry's commitment to enabling faster development and implementation of advanced AI capabilities, providing developers with robust resources to streamline AI agent creation.
-
camel
🐫 CAMEL: The first and the best multi-agent framework. Finding the Scaling Law of Agents. https://www.camel-ai.org
Project mention: Eigent: An open source Claude cowork alternative | news.ycombinator.com | 2026-01-14You can have a try; almost all sota models are supported all powered thanks to https://github.com/camel-ai/camel
-
Project mention: Preview your coding agents' work without painful CIs or servers; just paste a prompt | dev.to | 2026-05-05
Trying to preview a WIP branch of LangBot :
Python Agent discussion
Python Agent related posts
-
Google ADK CLI: The Fastest Way to Build and Ship AI Agents in 2026 [Guide]
-
From MiMo Code to MiMo SoloEngine: Xiaomi's Dual-Agent Strategy
-
MiMo Code Goes Open Source, but Xiaomi's Real Ambition Is MiMo SoloEngine
-
MiMo Code Frees Developers from Long-Running Tasks — MiMo SoloEngine Brings Claude Code to Every Industry
-
Lawyers, Marketers, Product Managers—Xiaomi's Breakthrough Agent Product SoloEngine: Everyone Is a Creator
-
The AI Engineering Baseline
-
SoloEngine: How to Let AI Run Every Industry
-
A note from our sponsor - SaaSHub
www.saashub.com | 13 Jun 2026
Index
What are some of the best open-source Agent projects in Python? This list will help you:
| # | Project | Stars |
|---|---|---|
| 1 | ragflow | 82,474 |
| 2 | OpenHands | 76,575 |
| 3 | LlamaFactory | 72,081 |
| 4 | deer-flow | 70,969 |
| 5 | MetaGPT | 68,683 |
| 6 | unsloth | 66,397 |
| 7 | learn-claude-code | 66,285 |
| 8 | mem0 | 58,292 |
| 9 | ChatTTS | 39,435 |
| 10 | khoj | 35,097 |
| 11 | AstrBot | 34,454 |
| 12 | gpt-researcher | 27,645 |
| 13 | agentscope | 26,737 |
| 14 | OpenViking | 25,521 |
| 15 | serena | 25,296 |
| 16 | adk-python | 20,085 |
| 17 | owl | 19,842 |
| 18 | SWE-agent | 19,487 |
| 19 | DeepResearch | 19,369 |
| 20 | agent-zero | 18,033 |
| 21 | agent-lightning | 17,301 |
| 22 | camel | 17,169 |
| 23 | LangBot | 16,282 |