# The Agentic Leaderboard

> The weekly-updated ranking of the top 100 open-source AI agents, scored on reliability, tool selection quality, autonomous iteration efficiency, and community mindshare. Last updated 2026-06-08T13:24:45Z. Total agents evaluated: 200.

## Methodology
- [Scoring formula and weights](https://www.theagenticleaderboard.com/methodology): Total = 0.35×Reliability + 0.20×Tool Selection Quality + 0.15×Autonomous Iteration + 0.10×Efficiency + 0.20×Community Mindshare
- [About + data sources](https://www.theagenticleaderboard.com/about)
- [Full leaderboard JSON](https://www.theagenticleaderboard.com/leaderboard.json)

## Top 10 Agents This Week
- [#1 ECC](https://www.theagenticleaderboard.com/agent/ecc): Score 89.2, category Agent Framework, by affaan-m, repo https://github.com/affaan-m/ECC
- [#2 career-ops](https://www.theagenticleaderboard.com/agent/career-ops): Score 87.8, category General AI Agent, by santifer, repo https://github.com/santifer/career-ops
- [#3 cline](https://www.theagenticleaderboard.com/agent/cline): Score 87.7, category Coding & Software Engineering, by cline, repo https://github.com/cline/cline
- [#4 antigravity-awesome-skills](https://www.theagenticleaderboard.com/agent/antigravity-awesome-skills): Score 87.4, category Coding & Software Engineering, by sickn33, repo https://github.com/sickn33/antigravity-awesome-skills
- [#5 AutoGPT](https://www.theagenticleaderboard.com/agent/autogpt): Score 87.0, category Autonomous Agent, by Significant-Gravitas, repo https://github.com/Significant-Gravitas/AutoGPT
- [#6 n8n](https://www.theagenticleaderboard.com/agent/n8n): Score 86.6, category Workflow Orchestration, by n8n-io, repo https://github.com/n8n-io/n8n
- [#7 cherry-studio](https://www.theagenticleaderboard.com/agent/cherry-studio): Score 86.5, category Chatbot & Conversational, by CherryHQ, repo https://github.com/CherryHQ/cherry-studio
- [#8 dify](https://www.theagenticleaderboard.com/agent/dify): Score 86.4, category Workflow Orchestration, by langgenius, repo https://github.com/langgenius/dify
- [#9 langchain](https://www.theagenticleaderboard.com/agent/langchain): Score 86.2, category Agent Framework, by langchain-ai, repo https://github.com/langchain-ai/langchain
- [#10 ai](https://www.theagenticleaderboard.com/agent/ai): Score 86.1, category Agent Framework, by vercel, repo https://github.com/vercel/ai

## All Top 100 Agents
- [#1 ECC](https://www.theagenticleaderboard.com/agent/ecc): Score 89.2
- [#2 career-ops](https://www.theagenticleaderboard.com/agent/career-ops): Score 87.8
- [#3 cline](https://www.theagenticleaderboard.com/agent/cline): Score 87.7
- [#4 antigravity-awesome-skills](https://www.theagenticleaderboard.com/agent/antigravity-awesome-skills): Score 87.4
- [#5 AutoGPT](https://www.theagenticleaderboard.com/agent/autogpt): Score 87.0
- [#6 n8n](https://www.theagenticleaderboard.com/agent/n8n): Score 86.6
- [#7 cherry-studio](https://www.theagenticleaderboard.com/agent/cherry-studio): Score 86.5
- [#8 dify](https://www.theagenticleaderboard.com/agent/dify): Score 86.4
- [#9 langchain](https://www.theagenticleaderboard.com/agent/langchain): Score 86.2
- [#10 ai](https://www.theagenticleaderboard.com/agent/ai): Score 86.1
- [#11 deepagents](https://www.theagenticleaderboard.com/agent/deepagents): Score 86.1
- [#12 page-agent](https://www.theagenticleaderboard.com/agent/page-agent): Score 85.9
- [#13 openclaw](https://www.theagenticleaderboard.com/agent/openclaw): Score 85.8
- [#14 smolagents](https://www.theagenticleaderboard.com/agent/smolagents): Score 85.8
- [#15 jan](https://www.theagenticleaderboard.com/agent/jan): Score 85.7
- [#16 ppt-master](https://www.theagenticleaderboard.com/agent/ppt-master): Score 85.7
- [#17 oh-my-openagent](https://www.theagenticleaderboard.com/agent/oh-my-openagent): Score 85.6
- [#18 cal.diy](https://www.theagenticleaderboard.com/agent/cal-diy): Score 85.4
- [#19 llama_index](https://www.theagenticleaderboard.com/agent/llama-index): Score 85.4
- [#20 agents](https://www.theagenticleaderboard.com/agent/agents): Score 85.4
- [#21 scientific-agent-skills](https://www.theagenticleaderboard.com/agent/scientific-agent-skills): Score 85.1
- [#22 hermes-agent](https://www.theagenticleaderboard.com/agent/hermes-agent): Score 85.0
- [#23 lobehub](https://www.theagenticleaderboard.com/agent/lobehub): Score 85.0
- [#24 crewAI](https://www.theagenticleaderboard.com/agent/crewai): Score 85.0
- [#25 ToolJet](https://www.theagenticleaderboard.com/agent/tooljet): Score 85.0
- [#26 1Panel](https://www.theagenticleaderboard.com/agent/1panel): Score 85.0
- [#27 deer-flow](https://www.theagenticleaderboard.com/agent/deer-flow): Score 84.9
- [#28 openclaude](https://www.theagenticleaderboard.com/agent/openclaude): Score 84.9
- [#29 semantic-kernel](https://www.theagenticleaderboard.com/agent/semantic-kernel): Score 84.9
- [#30 sim](https://www.theagenticleaderboard.com/agent/sim): Score 84.9
- [#31 dspy](https://www.theagenticleaderboard.com/agent/dspy): Score 84.8
- [#32 crush](https://www.theagenticleaderboard.com/agent/crush): Score 84.8
- [#33 langgraph](https://www.theagenticleaderboard.com/agent/langgraph): Score 84.7
- [#34 budibase](https://www.theagenticleaderboard.com/agent/budibase): Score 84.7
- [#35 OpenCLI](https://www.theagenticleaderboard.com/agent/opencli): Score 84.7
- [#36 pydantic-ai](https://www.theagenticleaderboard.com/agent/pydantic-ai): Score 84.6
- [#37 learn-claude-code](https://www.theagenticleaderboard.com/agent/learn-claude-code): Score 84.5
- [#38 anything-llm](https://www.theagenticleaderboard.com/agent/anything-llm): Score 84.5
- [#39 litellm](https://www.theagenticleaderboard.com/agent/litellm): Score 84.4
- [#40 autogen](https://www.theagenticleaderboard.com/agent/autogen): Score 84.4
- [#41 gemini-cli](https://www.theagenticleaderboard.com/agent/gemini-cli): Score 84.3
- [#42 nanoclaw](https://www.theagenticleaderboard.com/agent/nanoclaw): Score 84.2
- [#43 tidb](https://www.theagenticleaderboard.com/agent/tidb): Score 84.2
- [#44 Agent-Reach](https://www.theagenticleaderboard.com/agent/agent-reach): Score 84.2
- [#45 CopilotKit](https://www.theagenticleaderboard.com/agent/copilotkit): Score 84.1
- [#46 edict](https://www.theagenticleaderboard.com/agent/edict): Score 84.1
- [#47 ollama](https://www.theagenticleaderboard.com/agent/ollama): Score 84.0
- [#48 langflow](https://www.theagenticleaderboard.com/agent/langflow): Score 84.0
- [#49 composio](https://www.theagenticleaderboard.com/agent/composio): Score 84.0
- [#50 cognee](https://www.theagenticleaderboard.com/agent/cognee): Score 84.0
- [#51 awesome-copilot](https://www.theagenticleaderboard.com/agent/awesome-copilot): Score 83.9
- [#52 zeroclaw](https://www.theagenticleaderboard.com/agent/zeroclaw): Score 83.9
- [#53 last30days-skill](https://www.theagenticleaderboard.com/agent/last30days-skill): Score 83.9
- [#54 airbyte](https://www.theagenticleaderboard.com/agent/airbyte): Score 83.9
- [#55 open-interpreter](https://www.theagenticleaderboard.com/agent/open-interpreter): Score 83.8
- [#56 FinceptTerminal](https://www.theagenticleaderboard.com/agent/finceptterminal): Score 83.8
- [#57 promptfoo](https://www.theagenticleaderboard.com/agent/promptfoo): Score 83.8
- [#58 daily_stock_analysis](https://www.theagenticleaderboard.com/agent/daily-stock-analysis): Score 83.7
- [#59 agent-skills](https://www.theagenticleaderboard.com/agent/agent-skills): Score 83.7
- [#60 claude-mem](https://www.theagenticleaderboard.com/agent/claude-mem): Score 83.6
- [#61 activepieces](https://www.theagenticleaderboard.com/agent/activepieces): Score 83.6
- [#62 opencode](https://www.theagenticleaderboard.com/agent/opencode): Score 83.5
- [#63 firecrawl](https://www.theagenticleaderboard.com/agent/firecrawl): Score 83.5
- [#64 hyperframes](https://www.theagenticleaderboard.com/agent/hyperframes): Score 83.5
- [#65 conductor](https://www.theagenticleaderboard.com/agent/conductor): Score 83.5
- [#66 InsForge](https://www.theagenticleaderboard.com/agent/insforge): Score 83.5
- [#67 UI-TARS-desktop](https://www.theagenticleaderboard.com/agent/ui-tars-desktop): Score 83.4
- [#68 NemoClaw](https://www.theagenticleaderboard.com/agent/nemoclaw): Score 83.4
- [#69 ragflow](https://www.theagenticleaderboard.com/agent/ragflow): Score 83.3
- [#70 ruflo](https://www.theagenticleaderboard.com/agent/ruflo): Score 83.3
- [#71 LibreChat](https://www.theagenticleaderboard.com/agent/librechat): Score 83.3
- [#72 gpt-researcher](https://www.theagenticleaderboard.com/agent/gpt-researcher): Score 83.3
- [#73 adk-python](https://www.theagenticleaderboard.com/agent/adk-python): Score 83.3
- [#74 DeepSeek-Reasonix](https://www.theagenticleaderboard.com/agent/deepseek-reasonix): Score 83.3
- [#75 agency-agents](https://www.theagenticleaderboard.com/agent/agency-agents): Score 83.2
- [#76 mlflow](https://www.theagenticleaderboard.com/agent/mlflow): Score 83.2
- [#77 SWE-agent](https://www.theagenticleaderboard.com/agent/swe-agent): Score 83.2
- [#78 goose](https://www.theagenticleaderboard.com/agent/goose): Score 83.1
- [#79 agno](https://www.theagenticleaderboard.com/agent/agno): Score 83.1
- [#80 continue](https://www.theagenticleaderboard.com/agent/continue): Score 83.1
- [#81 agentmemory](https://www.theagenticleaderboard.com/agent/agentmemory): Score 83.1
- [#82 Vibe-Trading](https://www.theagenticleaderboard.com/agent/vibe-trading): Score 83.1
- [#83 OpenHands](https://www.theagenticleaderboard.com/agent/openhands): Score 83.0
- [#84 open-design](https://www.theagenticleaderboard.com/agent/open-design): Score 83.0
- [#85 agentscope](https://www.theagenticleaderboard.com/agent/agentscope): Score 83.0
- [#86 pr-agent](https://www.theagenticleaderboard.com/agent/pr-agent): Score 83.0
- [#87 mem0](https://www.theagenticleaderboard.com/agent/mem0): Score 82.9
- [#88 hive](https://www.theagenticleaderboard.com/agent/hive): Score 82.9
- [#89 agent-framework](https://www.theagenticleaderboard.com/agent/agent-framework): Score 82.9
- [#90 spring-ai-alibaba](https://www.theagenticleaderboard.com/agent/spring-ai-alibaba): Score 82.9
- [#91 daytona](https://www.theagenticleaderboard.com/agent/daytona): Score 82.8
- [#92 nanobot](https://www.theagenticleaderboard.com/agent/nanobot): Score 82.8
- [#93 nx](https://www.theagenticleaderboard.com/agent/nx): Score 82.8
- [#94 OpenViking](https://www.theagenticleaderboard.com/agent/openviking): Score 82.8
- [#95 Auto-claude-code-research-in-sleep](https://www.theagenticleaderboard.com/agent/auto-claude-code-research-in-sleep): Score 82.8
- [#96 pi](https://www.theagenticleaderboard.com/agent/pi): Score 82.7
- [#97 oh-my-claudecode](https://www.theagenticleaderboard.com/agent/oh-my-claudecode): Score 82.7
- [#98 openai-agents-python](https://www.theagenticleaderboard.com/agent/openai-agents-python): Score 82.7
- [#99 eliza](https://www.theagenticleaderboard.com/agent/eliza): Score 82.7
- [#100 DB-GPT](https://www.theagenticleaderboard.com/agent/db-gpt): Score 82.7

## Categories
- [Coding & Software Engineering](https://www.theagenticleaderboard.com/category/coding-software-engineering)
- [Agent Framework](https://www.theagenticleaderboard.com/category/agent-framework)
- [Autonomous Agent](https://www.theagenticleaderboard.com/category/autonomous-agent)
- [Browser & Computer Use](https://www.theagenticleaderboard.com/category/browser-computer-use)
- [Research & Reasoning](https://www.theagenticleaderboard.com/category/research-reasoning)
- [Workflow Orchestration](https://www.theagenticleaderboard.com/category/workflow-orchestration)
- [Multi-Modal Agent](https://www.theagenticleaderboard.com/category/multi-modal-agent)

## Weekly Archive
- [Weekly digests](https://www.theagenticleaderboard.com/weekly)

## How to cite
The Agentic Leaderboard, weekly snapshot. theagenticleaderboard.com. Accessed [date].