🔓The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Curs…
// devtoolsaffaan-m/⟨JavaScript⟩★ 267,519◷ MIT[ claude ]
Projects tagged #llm
// llm (245)
🔓
🔓Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
// devtoolsDietrichGebert/⟨JavaScript⟩★ 148,251◷ MIT[ claude ]
🔓🌐 Make websites accessible for AI agents. Automate tasks online with ease.
// automationbrowser-use/⟨Python⟩★ 117,143◷ MIT[ claude ]
🔓TradingAgents: Multi-Agents LLM Financial Trading Framework
// financeTauricResearch/⟨Python⟩★ 108,640◷ Apache-2.0[ claude ]
🔓🪨 why use many token when few token do trick — Claude Code skill that cuts 65% of tokens by talking like caveman
// mcp-serversJuliusBrussee/⟨JavaScript⟩★ 107,719◷ MIT[ claude ]
🔓Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.
// educationmlabonne/★ 83,144◷ Apache-2.0[ claude ]
🔓Bash is all you need - A nano claude code–like 「agent harness」, built from 0 to 1
// automationshareAI-lab/⟨Python⟩★ 78,037◷ MIT[ claude ]
🔓⭐AI-driven public opinion & trend monitor with multi-platform aggregation, RSS, and smart alerts.🎯 告别信息过载，你的 AI 舆情监控助手与热点筛选工具！聚合多平台热点 + RSS 订阅，支持关键词精准筛选。AI…
// devopssansan0/⟨Python⟩★ 62,534◷ GPL-3.0[ claude ]
🔓Context7 Platform -- Up-to-date code documentation for LLMs and AI code editors
// mcp-serversupstash/⟨TypeScript⟩★ 62,452◷ MIT[ claude ]
🔓The best-benchmarked open-source AI memory system. And it's free.
// mcp-serversMemPalace/⟨Python⟩★ 59,417◷ MIT[ claude ]
🔓📑 PageIndex: Document Index for Vectorless, Reasoning-based RAG
// uncategorizedVectifyAI/⟨Python⟩★ 38,436◷ MIT[ claude ]
🔓Hundreds of models & providers. One command to find what runs on your hardware.
// skillsAlexsJones/⟨Rust⟩★ 37,632◷ MIT[ claude ]
🔓"Vibe-Trading: Your Personal Trading Agent"
// financeHKUDS/⟨Python⟩★ 34,391◷ MIT[ claude ]
🔓⌥ AI Coding agent for the terminal — hash-anchored edits, optimized tool harness, LSP, Python, browser, subagents, and more
// devtoolscan1357/⟨TypeScript⟩★ 33,492◷ MIT[ claude ]
🔓Local-first code intelligence graph for MCP and CLI. Builds a persistent map of your codebase so AI coding tools read only what matters, with benchmarked con…
// devtoolstirth8205/⟨Python⟩★ 31,794◷ MIT[ claude ]
🔓Community plugin to control Blender 3D with any LLM of your choice
// uncategorizedahujasid/⟨Python⟩★ 29,489◷ MIT[ claude ]
🔓🎨 Control Blender 3D with Claude AI — prompt-driven 3D modeling, materials & scene generation via MCP
// mcp-serversMCPBlender/⟨Python⟩★ 29,432◷ MIT[ claude ]
🔓
🔓Open-source Agent Operating System
// automationRightNow-AI/⟨Rust⟩★ 18,208◷ Apache-2.0[ claude ]
🔓A powerful AI coding agent. Built for the terminal.
// mcp-serversopencode-ai/⟨Go⟩★ 13,782◷ MIT[ claude ]
🔓A Claude skill that writes the accurate prompts for any AI tool. Zero tokens or credits wasted. Full context and memory retention
// skillsnidhinjs/★ 13,684◷ MIT[ claude ]
🔓Self-evolving memory across Agent and platform. The one portable memory layer for every agent they use - Claude Code, Codex, OpenClaw, Hermes, and more
// automationEverMind-AI/⟨Python⟩★ 13,324◷ Apache-2.0[ claude ]
🔓[MLsys2026]: RAG on Everything with LEANN. Enjoy 97% storage savings while running a fast, accurate, and 100% private RAG application on your personal device.
// mcp-serversStarTrail-org/⟨Python⟩★ 13,006◷ MIT[ claude ]
🔓Expose your FastAPI endpoints as Model Context Protocol (MCP) tools, with Auth!
// mcp-serverstadata-org/⟨Python⟩★ 12,009◷ MIT[ claude ]
🔓An Open-Source Asynchronous Coding Agent
// automationlangchain-ai/⟨Python⟩★ 10,806◷ MIT[ claude ]
🔓All-in-one LLM CLI tool featuring Shell Assistant, Chat-REPL, RAG, AI Tools & Agents, with access to OpenAI, Claude, Gemini, Ollama, Groq, and more.
// uncategorizedsigoden/⟨Rust⟩★ 10,472◷ Apache-2.0[ claude ]
🔓
🔓List of Permanent Free LLM API (API Keys)
// uncategorizedmnfst/⟨JavaScript⟩★ 9,331◷ CC0-1.0[ claude ]
🔓Put an end to code hallucinations! GitMCP is a free, open-source, remote MCP server for any GitHub project
// automationidosal/⟨TypeScript⟩★ 8,452◷ Apache-2.0[ claude ]
🔓Fastest enterprise AI gateway (50x faster than LiteLLM) with adaptive load balancer, cluster mode, guardrails, 1000+ models support & <100 µs overhead at 5k…
// datamaximhq/⟨Go⟩★ 8,364◷ Apache-2.0[ claude ]