★ 410 Veldra — talk an agent into existence, then watch it grow. A self-hostable, local-first agent platform: describe what you need in plain language and it compiles a working agent tools, MCP, RAG, teams. The more you use it, the better it gets agents learn from your feedback and reshape as you talk.
Python90 forks7 min read
★ 410AI red-team platform. Autonomous LLM agents run a penetration test end to end inside a Kali container and write the report. LangGraph plan/act engine, provider-agnostic models via LiteLLM, PDF/JSON/SARIF output. FastAPI + React.
Python83 forks8 min read
★ 410My AI Stand. Realtime by day, rewriting itself by night. Summon my AI superpower.
Python99 forks8 min read
★ 410Execution-Layer Security (ELS) for AI agents — policy-enforced shell with audit.
Go19 forks7 min read
★ 409🦜🔗 LangChain interfaces to Google's suite of AI products (e.g. Gemini & Vertex AI)
Python502 forks4 min read
★ 409A Fork of Rikkahub with an overhauled UI and feature additions
Kotlin59 forks9 min read
★ 408React components for visualizing traces from AI agents
TypeScript25 forks5 min read
★ 408tmux plugin that runs Claude Code sessions in popups per project directory, with an fzf picker showing each session's status and a bell that highlights the window that needs you.
Shell59 forks6 min read
★ 408Claude skill: refactor code to reduce cyclomatic complexity
Unknown9 forks5 min read
★ 407Query robotics, drone, and IoT data in plain English through an MCP server, with an intelligent edge data reduction pipeline that keeps only the data that matters.
Python31 forks6 min read
★ 407AI-powered E2E testing for 10 platforms. 253 MCP tools. Zero config. Works with Claude, Cursor, Windsurf, Copilot. Test Flutter, React Native, iOS, Android, Web, Electron, Tauri, KMP, .NET MAUI — all from natural language.
Dart61 forks6 min read
★ 407clawdcursor compiles whatever's on screen into one UI map — accessibility tree and OCR fused into stable, addressable elements, with a screenshot only when needed — then drives apps through reusable scripts, verifying every action and routing it through a single safety gate.
TypeScript59 forks7 min read
★ 406ATLAS: a senior-engineer layer for Claude Code. Explore with wireframes & prototypes, clarify the essentials, capture it in HTML spec doc then let Claude Code's native plan/goal/workflow loop build. Fewer tokens, less ceremony, faster to what people pictured. KISS/YAGNI/DRY, context decides. No overengineering. Clean architecture that works.
Python60 forks6 min read
★ 406J-space / Jacobian-lens visualizer for Qwen3.6-27B (4-bit) on Apple Silicon, ported to Apple MLX
Python30 forks9 min read
★ 406"Immortal Path" AI-driven immersive cultivation text adventure game, based on Vue 3 + TypeScript + Fastapi, supports multiple AI models such as Gemini/Claude/OpenAI
Vue80 forks9 min read

Shelpuk-AI-Technology-Consulting ★ 405Kindly Web Search MCP Server: Web search + robust content retrieval for AI coding tools (Claude Code, Codex, Cursor, GitHub Copilot, Gemini, etc.) and AI agents (Claude Desktop, OpenClaw, Hermes, etc.). Supports Serper, Tavily, and SearXNG.
Python37 forks6 min read
★ 405Open-source local AI workspace — advancing on-device inference.
TypeScript13 forks5 min read
★ 405Swytchcode demo projects with different agents
TypeScript4 forks5 min read
★ 404Adaptive Chunking: automatically select the best chunking method per document for RAG. Accepted at LREC 2026.
Python45 forks5 min read
★ 404An AI agent for hardware PCB design: it automatically confirms requirements, analyzes chip technical solutions from vendors worldwide in real time, selects components, downloads datasheets, outputs a BOM, calculates pricing, generates module schematics, and integrates everything into a deployable technical solution.
Python56 forks6 min read