SaaSHub helps you find the best software and product alternatives Learn more →
Top 23 Python ai-agent Projects
-
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.
browser-use: https://github.com/browser-use/browser-use
-
SaaSHub
SaaSHub - Software Alternatives and Reviews. SaaSHub helps you find the best software and product alternatives
-
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.
Project mention: Vibe coding can build your pipeline. It can't explain it six months later | news.ycombinator.com | 2026-06-16hrm, there's tons of tools to do that, take https://github.com/bytedance/deer-flow
the better argument is: you pay to vibe code and you'll pay again in 6 months to vibe fix, etc.
-
crewAI
Framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks.
CrewAI: https://github.com/crewAIInc/crewAI
-
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.
-
antigravity-awesome-skills
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.
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.
-
agents
Multi-harness agentic plugin marketplace for Claude Code, Codex CLI, Cursor, OpenCode, GitHub Copilot, and Gemini CLI
Project mention: Repository Transformation: From Chaos to Professional Prompt Engineering Toolkit | dev.to | 2026-03-25Prominently featured 74 professional AI agent configurations adapted from wshobson/agents:
-
Project mention: LangGraph Fault Tolerance: Building Resilient Agents with Retries, Timeouts, and Error Handlers | dev.to | 2026-06-15
The timing matters. As organizations move from proof-of-concept agents to production deployments handling thousands of daily invocations, the economics of manual intervention become untenable. A support agent that requires human restarts 15% of the time isn't a productivity gain—it's a liability. The new @retry decorator, TimeoutPolicy class, and ErrorHandler nodes represent LangGraph's first comprehensive answer to this challenge, building on the framework's existing resilient agent architecture while addressing the operational realities of 2026's agentic workloads.
-
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]
-
500-AI-Agents-Projects
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 -
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.
-
letta
Letta is the platform for building stateful agents: AI with advanced memory that can learn and self-improve over time.
Project mention: Moltbook is the most interesting place on the internet | news.ycombinator.com | 2026-01-30> When are we going to build a safe version of this?
I built something similar to Clawdbot for my own use, but with a narrower feature set and obviously more focus on security. I'm now evaluating Letta Bot [0], a Clawdbot fork by Letta with a seemingly much saner development philosophy, and will probably migrate my own agent over. I was already using Letta's main open source offering [1] for my agent's memory, and I can already highly recommend that.
[0] https://github.com/letta-ai/lettabot
[1] https://github.com/letta-ai/letta
-
adk-python
An open-source, code-first Python toolkit for building, evaluating, and deploying sophisticated AI agents with flexibility and control.
The 497 open issues and 383 open PRs on the google/adk-python repository tell you something important: this is actively maintained, not another Google Labs experiment that'll get quietly sunset. With 3,600+ forks, people are building real things on top of it.
-
parlant
Build reliable customer-facing AI agents with Parlant: an interaction control harness optimized for controlled, consistent, and predictable LLM interactions.
-
cognee
Cognee is the open-source AI memory platform for agents. Give your AI agents persistent long-term memory across sessions with a self-hosted knowledge graph engine.
Cognee ($7.5M seed, GitHub Secure Open Source graduate, running in 70+ companies) builds a knowledge graph — not isolated facts, but a web of entities, relationships, and semantic connections.
-
Anthropic-Cybersecurity-Skills
754 structured cybersecurity skills for AI agents · Mapped to 5 frameworks: MITRE ATT&CK, NIST CSF 2.0, MITRE ATLAS, D3FEND & NIST AI RMF · agentskills.io standard · Works with Claude Code, GitHub Copilot, Codex CLI, Cursor, Gemini CLI & 20+ platforms · 26 security domains · Apache 2.0
The GitHub Trending board today corroborates this. Of the top fifteen repos, at least four are explicitly Skills-targeted: multica-ai/andrej-karpathy-skills (154K stars), affaan-m/ECC (192K stars), mukul975/Anthropic-Cybersecurity-Skills (9K), and the broader multica-ai/multica managed-agents platform.
-
-
memU
The memory harness for proactive AI agents — structured storage, intent capture, 10x token reduction.
-
Project mention: Local Inference Powers Browser Sign Language, Open-Source Agent Infra, & AI Engineering Guides | dev.to | 2026-06-15
Source: https://github.com/rohitg00/ai-engineering-from-scratch
-
-
-
-
-
claude-skills
66 Specialized Skills for Full-Stack Developers. Transform Claude Code into your expert pair programmer. (by Jeffallan)
Project mention: Show HN: Claude Skills. Try vibe engineering instead of vibe coding | news.ycombinator.com | 2026-02-0565 skills and 9 workflow commands for Claude Code. The interesting parts:
1 /common-ground: surfaces Claude's hidden assumptions about your project before you start. You confirm or reject them. "A smart thing to do." https://github.com/hesreallyhim/awesome-claude-code#latest-a....
2 Project workflows: discovery → planning → execution → retrospectives, with Jira and Confluence integration. Real tickets, real acceptance criteria, real code review.
Vibe coding is great for prototyping. Vibe engineering helps build production applications.
Repo: https://github.com/jeffallan/claude-skills
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).
Python ai-agents discussion
Python ai-agents related posts
-
DeepFork – reverse-engineer any OSS repo into a clean-room rebuild blueprint
-
Google ADK Tutorial: Build Your First AI Agent [2026]
-
LangGraph Fault Tolerance: Building Resilient Agents with Retries, Timeouts, and Error Handlers
-
GEDD – A Systematic Evidence Driven LLM as a Judge Framework
-
Three prompt injection stories from this week that your guardrail probably missed
-
Mastercard just launched Agent Pay for Machines. Here's the execution gap they didn't mention.
-
Show HN: AgentNexus – coordinate LLM agents by service boundary, not role
-
A note from our sponsor - SaaSHub
www.saashub.com | 16 Jun 2026
Index
What are some of the best open-source ai-agent projects in Python? This list will help you:
| # | Project | Stars |
|---|---|---|
| 1 | browser-use | 98,375 |
| 2 | deer-flow | 70,969 |
| 3 | crewAI | 53,305 |
| 4 | agno | 40,664 |
| 5 | antigravity-awesome-skills | 40,371 |
| 6 | agents | 36,670 |
| 7 | langgraph | 34,457 |
| 8 | PageIndex | 32,937 |
| 9 | 500-AI-Agents-Projects | 32,197 |
| 10 | OpenViking | 25,521 |
| 11 | letta | 23,244 |
| 12 | adk-python | 20,085 |
| 13 | parlant | 18,114 |
| 14 | cognee | 17,765 |
| 15 | Anthropic-Cybersecurity-Skills | 15,458 |
| 16 | DeepTutor | 14,272 |
| 17 | memU | 13,845 |
| 18 | ai-engineering-from-scratch | 13,774 |
| 19 | txtai | 12,649 |
| 20 | E2B | 12,558 |
| 21 | Agent-S | 11,831 |
| 22 | hermes-webui | 9,896 |
| 23 | claude-skills | 9,847 |
Sponsored
SaaSHub - Software Alternatives and Reviews
SaaSHub helps you find the best software and product alternatives
www.saashub.com