LLM Explorer: AI Agent and Open-Source Language Model Directory
Browse 165 AI agents and 53999 open-source language models. Compare features, benchmarks, explore capabilities, and find the right tool for your project.
What open-source LLMs or SLMs are you in search of? 53999 in total.
Subscribe to LLM updates
AI Agent Directory
Most Popular AI Agents
| Agent | Type | Stars | Forks | License |
|---|---|---|---|---|
| OpenClaw OpenClaw Community | Ready-to-Use | 334,201 | 65,178 | MIT |
| AutoGPT Significant Gravitas | Ready-to-Use | 173,000 | 45,000 | Other |
| Flowise Flowise (acquired by Workday Aug 2025) | Platform | 51,044 | 23,976 | Apache-2.0 |
| LangChain LangChain Inc | Framework | 130,900 | 21,555 | MIT |
| Dify LangGenius | Platform | 134,280 | 20,917 | Apache-2.0 |
| Bolt.new StackBlitz | Ready-to-Use | 16,300 | 14,600 | MIT |
| browser-use browser-use | Framework | 84,000 | 9,700 | MIT |
| OpenManus FoundationAgents | Ready-to-Use | 55,000 | 9,600 | MIT |
| OpenAI Codex CLI OpenAI | Ready-to-Use | 67,340 | 9,013 | Apache-2.0 |
| OpenHands OpenHands | Ready-to-Use | 69,680 | 8,729 | MIT |
Recently Updated AI Agents
| Agent | Type | Stars | Forks | License |
|---|---|---|---|---|
| Conductor Conductor OSS | AI Harness | 31,581 | 840 | Apache-2.0 |
| Composio Agent Orchestrator Composio | AI Harness | 5,519 | 725 | MIT |
| Mission Control Builderz Labs | AI Harness | 3,477 | 594 | MIT |
| Memoh Memoh AI | AI Harness | 1,136 | 113 | AGPL-3.0 |
| Pinchy Pinchy | AI Harness | 136 | 15 | AGPL-3.0 |
| AgentPool phil65 | AI Harness | 120 | 19 | MIT |
| Tinyflow Java Tinyflow AI | AI Harness | 78 | 18 | LGPL-3.0 |
| HUF Tridz Dev | AI Harness | 66 | 25 | AGPL-3.0 |
| AI Maestro 23blocks OS | AI Harness | 566 | 78 | MIT |
| Maestro RunMaestro | AI Harness | 2,588 | 259 | AGPL-3.0 |
Open-Source Language Model Lists by Categories
All Large Language Models LMSYS ChatBot Arena ELO Original & Foundation LLMs OpenCompass LeaderBoard Recently Added Models Code Generating Models Instruction-Based LLMs Uncensored LLMs LLMs Fit in 4GB RAM LLMs Fit in 8GB RAM LLMs Fit in 12GB RAM LLMs Fit in 24GB RAM LLMs Fit in 32GB RAM GGUF Quantized Models GPTQ Quantized Models EXL2 Quantized Models Fine-Tuned Models LLMs for Commercial Use TheBloke's Models Context Size >16K Tokens Mixture-Of-Experts Models Apple's MLX LLMs Small Language ModelsRecent LLM List
| Model | Downloads | Likes | VRAM |
|---|---|---|---|
| HRM Text 1B sapientinc | 23532 | 169 | 2 |
| Qwen3.6 27B OBLITERATED OBLITERATUS | 7701 | 96 | 53 |
| Equinox 31B LatitudeGames | 506 | 44 | 62 |
| Carbon 8B HuggingFaceBio | 1566 | 33 | 16 |
| Supra 50M Instruct SupraLabs | 822 | 12 | 0 |
| DeepSeek V4 Flash JANG CRACK dealignai | 684 | 4 | 46 |
| Nandi Mini 150M GuardRails FrontiersMind | 136 | 16 | 0 |
| Gemma 4 A4B 98e V5 Coder It ManniX-ITA | 2842 | 1 | 41 |
| Vlite4 Nano YUKI 80M aixk | 95 | 2 | 0 |
| BusyBeaver 50M GestaltLabs | 168 | 10 | 0 |
TOP 7b Param LLMs
| Model | Downloads | Likes | VRAM |
|---|---|---|---|
| Mistral 7B Instruct V0.2 mistralai | 3156227 | 3149 | 14 |
| Hunyuan MT 7B tencent | 12785 | 730 | 16 |
| Qwen2.5 7B Instruct Qwen | 12602900 | 1195 | 15 |
| Qwen2 7B Qwen | 63057 | 171 | 15 |
| Qwen2.5 7B Preview marcuscedricridia | 10 | 0 | 15 |
| Llama 2 7B Chat Hf meta-llama | 386169 | 4754 | 13 |
| Zephyr 7B Beta HuggingFaceH4 | 179060 | 1843 | 14 |
| Mistral 7B Instruct V0.1 mistralai | 302458 | 1833 | 14 |
| Mistral 7B Instruct V0.3 mistralai | 4474686 | 2578 | 14 |
| Gemma 7B It google | 29207 | 1246 | 17 |
TOP 34b Param LLMs
| Model | Downloads | Likes | VRAM |
|---|---|---|---|
| Yi 1.5 34B Chat 01-ai | 16195 | 278 | 69 |
| Yi 34B Chat 01-ai | 64324 | 356 | 69 |
| Dolphin 2.9.1 Yi 1.5 34B cognitivecomputations | 4811054 | 37 | 69 |
| CodeLlama 34B Instruct Hf codellama | 57493 | 304 | 67 |
| YiSM Blossom5.1 34B SLERP CombinHorizon | 8279 | 0 | 69 |
| YiSM 34B 0rn altomek | 16276 | 2 | 67 |
| Yi 1.5 34B 32K 01-ai | 9464 | 37 | 69 |
| Yi 1.5 34B Chat 16K 01-ai | 9673 | 27 | 69 |
| Blossom V5.1 34B Azure99 | 8142 | 5 | 68 |
| Yi 34B 01-ai | 10364 | 1302 | 68 |
LLMs Fit 16GB VRAM
| Model | Downloads | Likes | VRAM |
|---|---|---|---|
| MiMo V2.5 Pro XiaomiMiMo | 72633 | 540 | 2 |
| MiMo V2.5 XiaomiMiMo | 194805 | 255 | 1 |
| Step 3.5 Flash stepfun-ai | 304890 | 814 | 8 |
| Gemma 4 26B A4b It 4bit mlx-community | 89270 | 47 | 15 |
| HRM Text 1B sapientinc | 23532 | 169 | 2 |
| Gemma 4 E4B It OBLITERATED OBLITERATUS | 345902 | 665 | 15 |
| Gemma 4 E2B It google | 3222438 | 654 | 10 |
| GPT Oss 20B openai | 8082595 | 4637 | 13 |
| LongCat Flash Chat meituan-longcat | 84875 | 533 | 0 |
| Gemma 4 31B It Assistant google | 208710 | 261 | 0 |
TOP Code Generating LLMs
| Model | Downloads | Likes | VRAM |
|---|---|---|---|
| Qwen2.5 Coder 32B Instruct Qwen | 1305611 | 2014 | 65 |
| Qwen3 Coder Next Qwen | 1108788 | 1384 | 159 |
| Qwen3 Coder 30B A3B Instruct Qwen | 2006711 | 1064 | 61 |
| List 3.0 Ultra Coder Brain List-cloud | 280075 | 10 | 77 |
| Qwen3 Coder Next FP8 Qwen | 606934 | 148 | 80 |
| Qwen2.5 Coder 14B Instruct Qwen | 1496835 | 156 | 29 |
| Zeta 2 zed-industries | 3956 | 178 | 16 |
| Qwen2.5 Coder 7B Instruct Qwen | 2110918 | 684 | 15 |
| ...est Coder V1 40B Loop Instruct IQuestLab | 32024 | 329 | 80 |
| DeepSeek Coder V2 Instruct deepseek-ai | 88248 | 685 | 387 |
Open-Source Language Model Lists by Benchmarks
LMSys ELOLMSys Chatbot Arena ELO RatingARC
Common Sense Reasoning, AccuracyHellaSwag
Sentence Completion, AccuracyMMLU
Multi-task Language Understanding, AverageGSM8K
Arithmetic Reasoning, AccuracyHumanEval AVG
HumanEval for Multiple Languages, Pass@1Python Eval
HumanEval for Python, Pass@1Java Eval
HumanEval for Java, Pass@1Javascript Eval
HumanEval for Javascript, Pass@1CPP Eval
HumanEval for CPP, Pass@1PHP Eval
HumanEval for PHP, Pass@1Julia Eval
HumanEval for Julia, Pass@1D Eval
HumanEval for D, Pass@1Lua Eval
HumanEval for Lua, Pass@1R Eval
HumanEval for R, Pass@1Racket Eval
HumanEval for Racket, Pass@1Rust Eval
HumanEval for Rust, Pass@1Swift Eval
HumanEval for Swift, Pass@1OpenCompass Avg
OpenCompass Average ScoreExam
OpenCompass Examination ScoreLanguage
OpenCompass Language CapabilitiesKnowledge
OpenCompass Knowledge CapabilitiesUnderstanding
OpenCompass Understanding CapabilitiesReasoning
OpenCompass Reasoning CapabilitiesMTBench
Machine Translation, BLEULLME Score
LLM Explorer Score
About LLM Explorer
LLM Explorer: A platform connecting over 30,000 AI and ML professionals every month with the most recent AI agents and Large Language Models. Browse 165 AI agents (frameworks, SDKs, platforms, and ready-to-use tools) and 53999 open-source LLMs. Offering an extensive collection of agentic AI tools and language models, it's the go-to resource for the latest in AI advancements. With intuitive categorization, powerful analytics, and up-to-date benchmarks, it simplifies the search for the perfect AI agent or language model for any business application. Whether you're an AI enthusiast, researcher, or industry professional, LLM Explorer is your essential guide to the dynamic landscape of AI agents and language models.
Summary Statistics
| AI Agents | 165 |
| Total LLMs | 53999 |
| Quantized LLMs | 12636 |
| Merged LLMs | 9041 |
| Finetuned LLMs | 996 |
| Instruction-Based LLMs | 11572 |
| Codegen LLMs | 1618 |
| DB Last Update | 2026-05-26 |
Original data from HuggingFace, OpenCompass and various public git repos.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a