300,411 stars
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
ai-agentsanthropicclaudeclaude-codedeveloper-tools
Open source hub
Open-Source Agents
A hub for open-source agent frameworks, workflow builders, orchestration libraries, and repository-backed AI automation projects.
Built for: Developers, automation teams, platform engineers, technical founders
12
Ranked entries
13
Verified repos
11
Decision pages
99
Top score
1
Does the framework style match the workflow: visual automation, code-first agents, or RAG agents?
2
Are releases, issues, license, documentation, and examples healthy enough for production use?
3
Can tool permissions be sandboxed before connecting sensitive systems?
Ranking
Shortlist the leading entries.
These entries come from the current SkillRank dataset. Scores help discovery; final decisions should use your own workflow tests.
Coding
Claude Code
Anthropic
99
Score
Terminal-native coding agent that plans, edits, and runs tools in your repo.
Agentic codingRank #1Editorial profile
Coding
Cursor
Cursor
99
Score
Forked-editor experience with inline agents, rules, and multi-model support.
IDE agentRank #2Editorial profile
Coding
GitHub Copilot Chat & agent
GitHub
98
Score
Latest Copilot assistants with inline chat, agent mode, and IDE plus GitHub-native agents.
IDE assistantRank #3Editorial profile
Coding
OpenAI Codex (current)
OpenAI
98
Score
OpenAI’s shipping coding agents and completions behind ChatGPT IDE and Codex tooling.
Coding model / agentRank #4Editorial profile
Coding
Windsurf
Codeium
97
Score
Cascade-style agent IDE optimized for flow and multi-step edits.
IDE agentRank #5Editorial profile
Coding
Devin
Cognition
97
Score
Autonomous software engineer agent with dedicated cloud environment.
Software agentRank #6Editorial profile
Coding
Qwen 4 Coder
Alibaba
96
Score
Current code-specialized Qwen line for completion, agents, and on-prem deployments.
Code LLMRank #7Editorial profile
Coding
andrej-karpathy-skills
forrestchang
96
Score
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
Open source agent / repoRank #8Verified repo
Daily signals
What today's briefing says about this category.
Signals are generated from recorded snapshots and verified source metadata. They keep the hub connected to the daily crawler.
Coding
ECC
affaan-m/ECC is verified on GitHub with 236,513 stars, 35,960 forks, and last push date 2026-07-29.
Coding
superpowers
obra/superpowers is verified on GitHub with 264,292 stars, 23,595 forks, and last push date 2026-07-28.
Coding
JavaGuide
Snailclimb/JavaGuide is verified on GitHub with 157,413 stars, 46,175 forks, and last push date 2026-07-28.
Coding
awesome-llm-apps
Shubhamsaboo/awesome-llm-apps is verified on GitHub with 129,267 stars, 19,060 forks, and last push date 2026-07-31.
Coding
agency-agents
msitarzewski/agency-agents is verified on GitHub with 137,796 stars, 22,492 forks, and last push date 2026-07-30.
Coding
langchain
langchain-ai/langchain is verified on GitHub with 143,087 stars, 23,828 forks, and last push date 2026-07-31.
Verified repositories
Repository-backed projects to inspect.
GitHub metadata is useful for discovery, but production fit still depends on license, docs, security posture, and local maintainability.
155,143 stars
Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by executing routine tasks, explaining complex code, and handling git workflows - all through natural language commands.
141,012 stars
Use Garry Tan's exact Claude Code setup: 23 opinionated tools that serve as CEO, Designer, Eng Manager, Release Manager, Doc Engineer, and QA
153,218 stars
A cross-platform desktop All-in-One assistant for Claude Code, Codex, OpenCode,DeepSeek Harness and more. Only official website: ccswitch.io
ai-toolsclaude-codecodexdeepseek-harnessdesktop-app
145,244 stars
Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Cursor, Codex, and Gemini CLI: local deterministic AST parsing, every edge explained, no vector store.
ai-agentsantigravityastclaude-codecode-analysis
115,552 stars
Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More
aiai-agentsai-memoryanthropicartificial-intelligence
Guides
Read the operating playbooks.
Coding agents10 min
Coding Agent Rollout Playbook
How to introduce Claude Code, Cursor, Codex-style agents, Copilot, and open-source coding repos without weakening engineering review.
Retrieval8 min
RAG Evaluation Checklist
A grounded checklist for choosing embedding models, retrieval pipelines, rerankers, and document-agent workflows.
Media generation7 min
AI Image and Video Model Workflow
How creative teams can compare image and video generators using briefs, brand constraints, rights review, and repeatability.
Security9 min
AI Agent Security Review Checklist
A security review guide for AI agents that can read files, call tools, browse, write code, or automate workflows.
Open source9 min
Open-Source AI Agent Frameworks: Evaluation Guide
How to evaluate open-source agent frameworks, orchestration libraries, workflow builders, and repository-backed AI tools.
Multimodal8 min
Multimodal AI Evaluation Guide
How to evaluate models that combine text, images, audio, video, files, screens, and tool use in one workflow.
Compare
Turn options into a decision.
Frontier reasoningUpdated 2026-06-04
GPT-5.5 vs Claude Opus for Professional Work
A practical comparison of GPT-5.5 and Claude Opus for research, coding, long documents, agentic workflows, and enterprise evaluation.
Coding agentsUpdated 2026-06-04
Claude Code vs Cursor
Compare Claude Code and Cursor for repository work, IDE assistance, refactoring, code review, team rollout, and daily engineering workflows.
Platform choiceUpdated 2026-06-04
OpenAI vs Gemini for Product Teams
How product teams should compare OpenAI and Google Gemini for chat, multimodal apps, workflow automation, enterprise deployment, and cost control.
Video generationUpdated 2026-06-04
Sora vs Veo vs Runway for AI Video
Compare AI video generators for storyboards, social ads, cinematic clips, brand workflows, and production review.
Open source agentsUpdated 2026-06-04
Open-Source Agent Frameworks Compared
Compare n8n, AutoGen, CrewAI, Flowise, LlamaIndex, and other open-source agent frameworks by workflow fit and operational risk.
Source boundaries
Open-source watchlists use verified repository metadata when source URLs match GitHub records.
Stars are a discovery signal, not a production approval score.
Security review should map every tool, credential, file read, and write action.