# 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 2026-08-10T10:42:32Z. 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 cline](https://www.theagenticleaderboard.com/agent/cline): Score 87.7, category Coding & Software Engineering, by cline, repo https://github.com/cline/cline - [#2 agentic-awesome-skills](https://www.theagenticleaderboard.com/agent/agentic-awesome-skills): Score 87.4, category Agent Framework, by sickn33, repo https://github.com/sickn33/agentic-awesome-skills - [#3 ppt-master](https://www.theagenticleaderboard.com/agent/ppt-master): Score 87.3, category Autonomous Agent, by hugohe3, repo https://github.com/hugohe3/ppt-master - [#4 ECC](https://www.theagenticleaderboard.com/agent/ecc): Score 87.0, category Agent Framework, by affaan-m, repo https://github.com/affaan-m/ECC - [#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 scientific-agent-skills](https://www.theagenticleaderboard.com/agent/scientific-agent-skills): Score 87.0, category Research & Reasoning, by K-Dense-AI, repo https://github.com/K-Dense-AI/scientific-agent-skills - [#7 openclaw](https://www.theagenticleaderboard.com/agent/openclaw): Score 86.7, category General AI Agent, by openclaw, repo https://github.com/openclaw/openclaw - [#8 n8n](https://www.theagenticleaderboard.com/agent/n8n): Score 86.6, category Workflow Orchestration, by n8n-io, repo https://github.com/n8n-io/n8n - [#9 cherry-studio](https://www.theagenticleaderboard.com/agent/cherry-studio): Score 86.6, category Chatbot & Conversational, by CherryHQ, repo https://github.com/CherryHQ/cherry-studio - [#10 dify](https://www.theagenticleaderboard.com/agent/dify): Score 86.5, category Workflow Orchestration, by langgenius, repo https://github.com/langgenius/dify ## All Top 100 Agents - [#1 cline](https://www.theagenticleaderboard.com/agent/cline): Score 87.7 - [#2 agentic-awesome-skills](https://www.theagenticleaderboard.com/agent/agentic-awesome-skills): Score 87.4 - [#3 ppt-master](https://www.theagenticleaderboard.com/agent/ppt-master): Score 87.3 - [#4 ECC](https://www.theagenticleaderboard.com/agent/ecc): Score 87.0 - [#5 AutoGPT](https://www.theagenticleaderboard.com/agent/autogpt): Score 87.0 - [#6 scientific-agent-skills](https://www.theagenticleaderboard.com/agent/scientific-agent-skills): Score 87.0 - [#7 openclaw](https://www.theagenticleaderboard.com/agent/openclaw): Score 86.7 - [#8 n8n](https://www.theagenticleaderboard.com/agent/n8n): Score 86.6 - [#9 cherry-studio](https://www.theagenticleaderboard.com/agent/cherry-studio): Score 86.6 - [#10 dify](https://www.theagenticleaderboard.com/agent/dify): Score 86.5 - [#11 page-agent](https://www.theagenticleaderboard.com/agent/page-agent): Score 86.4 - [#12 langchain](https://www.theagenticleaderboard.com/agent/langchain): Score 86.3 - [#13 ai](https://www.theagenticleaderboard.com/agent/ai): Score 86.1 - [#14 DeepSeek-Reasonix](https://www.theagenticleaderboard.com/agent/deepseek-reasonix): Score 85.9 - [#15 jan](https://www.theagenticleaderboard.com/agent/jan): Score 85.8 - [#16 Agent-Reach](https://www.theagenticleaderboard.com/agent/agent-reach): Score 85.7 - [#17 career-ops](https://www.theagenticleaderboard.com/agent/career-ops): Score 85.6 - [#18 llama_index](https://www.theagenticleaderboard.com/agent/llama-index): Score 85.5 - [#19 last30days-skill](https://www.theagenticleaderboard.com/agent/last30days-skill): Score 85.5 - [#20 smolagents](https://www.theagenticleaderboard.com/agent/smolagents): Score 85.5 - [#21 cal.diy](https://www.theagenticleaderboard.com/agent/cal-diy): Score 85.4 - [#22 WrenAI](https://www.theagenticleaderboard.com/agent/wrenai): Score 85.4 - [#23 OpenMontage](https://www.theagenticleaderboard.com/agent/openmontage): Score 85.3 - [#24 agents](https://www.theagenticleaderboard.com/agent/agents): Score 85.3 - [#25 hermes-agent](https://www.theagenticleaderboard.com/agent/hermes-agent): Score 85.2 - [#26 learn-claude-code](https://www.theagenticleaderboard.com/agent/learn-claude-code): Score 85.2 - [#27 deer-flow](https://www.theagenticleaderboard.com/agent/deer-flow): Score 85.1 - [#28 crewAI](https://www.theagenticleaderboard.com/agent/crewai): Score 85.1 - [#29 OmniRoute](https://www.theagenticleaderboard.com/agent/omniroute): Score 85.1 - [#30 lobehub](https://www.theagenticleaderboard.com/agent/lobehub): Score 85.0 - [#31 openclaude](https://www.theagenticleaderboard.com/agent/openclaude): Score 85.0 - [#32 ToolJet](https://www.theagenticleaderboard.com/agent/tooljet): Score 84.9 - [#33 semantic-kernel](https://www.theagenticleaderboard.com/agent/semantic-kernel): Score 84.9 - [#34 sim](https://www.theagenticleaderboard.com/agent/sim): Score 84.9 - [#35 crush](https://www.theagenticleaderboard.com/agent/crush): Score 84.9 - [#36 langgraph](https://www.theagenticleaderboard.com/agent/langgraph): Score 84.8 - [#37 posthog](https://www.theagenticleaderboard.com/agent/posthog): Score 84.8 - [#38 dspy](https://www.theagenticleaderboard.com/agent/dspy): Score 84.8 - [#39 OpenCLI](https://www.theagenticleaderboard.com/agent/opencli): Score 84.8 - [#40 deepagents](https://www.theagenticleaderboard.com/agent/deepagents): Score 84.7 - [#41 kestra](https://www.theagenticleaderboard.com/agent/kestra): Score 84.7 - [#42 cc-haha](https://www.theagenticleaderboard.com/agent/cc-haha): Score 84.7 - [#43 pydantic-ai](https://www.theagenticleaderboard.com/agent/pydantic-ai): Score 84.7 - [#44 cognee](https://www.theagenticleaderboard.com/agent/cognee): Score 84.6 - [#45 budibase](https://www.theagenticleaderboard.com/agent/budibase): Score 84.6 - [#46 ruflo](https://www.theagenticleaderboard.com/agent/ruflo): Score 84.5 - [#47 anything-llm](https://www.theagenticleaderboard.com/agent/anything-llm): Score 84.5 - [#48 signoz](https://www.theagenticleaderboard.com/agent/signoz): Score 84.5 - [#49 headroom](https://www.theagenticleaderboard.com/agent/headroom): Score 84.4 - [#50 ai-engineering-from-scratch](https://www.theagenticleaderboard.com/agent/ai-engineering-from-scratch): Score 84.4 - [#51 gemini-cli](https://www.theagenticleaderboard.com/agent/gemini-cli): Score 84.3 - [#52 agent-skills](https://www.theagenticleaderboard.com/agent/agent-skills): Score 84.3 - [#53 nanoclaw](https://www.theagenticleaderboard.com/agent/nanoclaw): Score 84.2 - [#54 daily_stock_analysis](https://www.theagenticleaderboard.com/agent/daily-stock-analysis): Score 84.1 - [#55 goose](https://www.theagenticleaderboard.com/agent/goose): Score 84.1 - [#56 tidb](https://www.theagenticleaderboard.com/agent/tidb): Score 84.1 - [#57 Vibe-Trading](https://www.theagenticleaderboard.com/agent/vibe-trading): Score 84.1 - [#58 gpt-researcher](https://www.theagenticleaderboard.com/agent/gpt-researcher): Score 84.1 - [#59 ollama](https://www.theagenticleaderboard.com/agent/ollama): Score 84.0 - [#60 langflow](https://www.theagenticleaderboard.com/agent/langflow): Score 84.0 - [#61 awesome-copilot](https://www.theagenticleaderboard.com/agent/awesome-copilot): Score 84.0 - [#62 hyperframes](https://www.theagenticleaderboard.com/agent/hyperframes): Score 84.0 - [#63 composio](https://www.theagenticleaderboard.com/agent/composio): Score 84.0 - [#64 edict](https://www.theagenticleaderboard.com/agent/edict): Score 84.0 - [#65 ponytail](https://www.theagenticleaderboard.com/agent/ponytail): Score 83.9 - [#66 mem0](https://www.theagenticleaderboard.com/agent/mem0): Score 83.9 - [#67 openinterpreter](https://www.theagenticleaderboard.com/agent/openinterpreter): Score 83.9 - [#68 zeroclaw](https://www.theagenticleaderboard.com/agent/zeroclaw): Score 83.9 - [#69 openhuman](https://www.theagenticleaderboard.com/agent/openhuman): Score 83.9 - [#70 planning-with-files](https://www.theagenticleaderboard.com/agent/planning-with-files): Score 83.9 - [#71 UI-TARS-desktop](https://www.theagenticleaderboard.com/agent/ui-tars-desktop): Score 83.8 - [#72 firecrawl](https://www.theagenticleaderboard.com/agent/firecrawl): Score 83.7 - [#73 claude-mem](https://www.theagenticleaderboard.com/agent/claude-mem): Score 83.7 - [#74 activepieces](https://www.theagenticleaderboard.com/agent/activepieces): Score 83.6 - [#75 kilocode](https://www.theagenticleaderboard.com/agent/kilocode): Score 83.6 - [#76 FinceptTerminal](https://www.theagenticleaderboard.com/agent/finceptterminal): Score 83.6 - [#77 CowAgent](https://www.theagenticleaderboard.com/agent/cowagent): Score 83.5 - [#78 conductor](https://www.theagenticleaderboard.com/agent/conductor): Score 83.5 - [#79 agency-agents](https://www.theagenticleaderboard.com/agent/agency-agents): Score 83.4 - [#80 pi](https://www.theagenticleaderboard.com/agent/pi): Score 83.4 - [#81 LibreChat](https://www.theagenticleaderboard.com/agent/librechat): Score 83.4 - [#82 NemoClaw](https://www.theagenticleaderboard.com/agent/nemoclaw): Score 83.4 - [#83 ragflow](https://www.theagenticleaderboard.com/agent/ragflow): Score 83.3 - [#84 open-design](https://www.theagenticleaderboard.com/agent/open-design): Score 83.3 - [#85 oh-my-openagent](https://www.theagenticleaderboard.com/agent/oh-my-openagent): Score 83.3 - [#86 qlib](https://www.theagenticleaderboard.com/agent/qlib): Score 83.3 - [#87 adk-python](https://www.theagenticleaderboard.com/agent/adk-python): Score 83.3 - [#88 agentmemory](https://www.theagenticleaderboard.com/agent/agentmemory): Score 83.3 - [#89 jcode](https://www.theagenticleaderboard.com/agent/jcode): Score 83.3 - [#90 continue](https://www.theagenticleaderboard.com/agent/continue): Score 83.2 - [#91 mlflow](https://www.theagenticleaderboard.com/agent/mlflow): Score 83.2 - [#92 openai-agents-python](https://www.theagenticleaderboard.com/agent/openai-agents-python): Score 83.2 - [#93 oh-my-pi](https://www.theagenticleaderboard.com/agent/oh-my-pi): Score 83.2 - [#94 hive](https://www.theagenticleaderboard.com/agent/hive): Score 83.2 - [#95 OpenHands](https://www.theagenticleaderboard.com/agent/openhands): Score 83.1 - [#96 agno](https://www.theagenticleaderboard.com/agent/agno): Score 83.1 - [#97 agentscope](https://www.theagenticleaderboard.com/agent/agentscope): Score 83.1 - [#98 SWE-agent](https://www.theagenticleaderboard.com/agent/swe-agent): Score 83.1 - [#99 agent-framework](https://www.theagenticleaderboard.com/agent/agent-framework): Score 83.1 - [#100 OpenViking](https://www.theagenticleaderboard.com/agent/openviking): Score 82.9 ## 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].