Mobile client for Codex and Claude — control coding agents from your phone via WebSocket bridge
- android
- bridge-server
- claude-code
- cli
105,102 visible repositories in the index
121–144 of 164 · Most stars
Mobile client for Codex and Claude — control coding agents from your phone via WebSocket bridge
Alpaca’s official MCP Server lets you trade stocks, ETFs, crypto, and options, run data analysis, and build strategies in plain English directly from your favorite LLM tools and IDEs
Run Laya, the open-source Jev-compatible System-1 decision model, from Node.js / TypeScript via ONNX Runtime
160-tool MCP server for real-time global intelligence from free public APIs: markets, liquidity, prediction markets, SEC filings, conflict, military, aircraft-cohort early warning, migration and border flows, cyber, climate, news and more. Dated observation history, 29 research prompts, cited briefs, geofences, SSE dashboard. MIT, no paid API keys.
Build AI agents from first principles using a local LLM - no frameworks, no cloud APIs, no hidden reasoning.
Local gateway for Claude Code, Codex and other AI clients on macOS, Windows and Linux: switch upstreams without touching clients, keep API keys from relays, cut off malicious tool calls, trace every request.
Clean Xcode, Docker, Homebrew, and developer caches, remove project and AI artifacts, analyze storage, and reclaim disk space from the Terminal.
Directory of 34+ free LLM & AI APIs — permanent free tiers, trial credits, and no-card options. GPT-4o, Gemini, Claude, Llama, DeepSeek, Mistral & more. Synced daily from the live directory at free-llm.com.
From-scratch PyTorch implementation of Google's TurboQuant (ICLR 2026) for LLM KV cache compression. 5x compression at 3-bit with 99.5% attention fidelity.
Verifiable program-level self-evolution for AI-for-Science agents: Skills and typed Operators grow from replay-verified executions.
from vibe coding to agentic engineering - practice makes codex perfect
Build a RAG (Retrieval Augmented Generation) pipeline from scratch and have it all run locally.
🔍 LangKit: An open-source toolkit for monitoring Large Language Models (LLMs). 📚 Extracts signals from prompts & responses, ensuring safety & security. 🛡️ Features include text quality, relevance metrics, & sentiment analysis. 📊 A comprehensive tool for LLM observability. 👀
🎬 Generate images from any camera viewpoint via 3D interactive control. Drag the camera in 3D space or use sliders to set azimuth/elevation/distance, then generate. Built with Three.js + Gradio, bilingual ZH/EN UI.
⛷️ LLaMA-MoE: Building Mixture-of-Experts from LLaMA with Continual Pre-training (EMNLP 2024)
Tensorflow + Keras + OpenAI Gym implementation of 1-step Q Learning from "Asynchronous Methods for Deep Reinforcement Learning"
Reconmap is a collaboration-first security operations platform for infosec teams and MSSPs, enabling end‑to‑end engagement management, from reconnaissance through execution and reporting. With built-in command automation, output parsing, and AI‑assisted summaries, it delivers faster, more structured, and high‑quality security assessments.
Open-source AI agent firewall for MCP security and agent egress. Scans mediated HTTP, MCP, A2A, and WebSocket traffic for exfiltration, SSRF, and prompt injection, and emits mediator-signed action receipts: verifiable audit evidence from outside the agent.
Research archive of Claude Code source and runtime artifacts reconstructed from published npm source maps.
FigmaChain is a set of Python scripts that generate HTML/CSS code based on Figma designs. Using OpenAI's GPT-3 model, FigmaChain enables developers to quickly generate HTML/CSS code from a Figma design input. It also includes a Streamlit-based chatbot interface for interactive code generation.
An open-source educational chat model from ICALK, East China Normal University. 开源中英教育对话大模型。(通用基座模型,GPU部署,数据清理) 致敬: LLaMA, MOSS, BELLE, Ziya, vLLM
The open, local take on Jev: typed decisions from an LLM, without generating a single token
Work with local and cloud LLMs from Emacs.
A structured 3-agent AI dev team — Architect, Builder, Reviewer. Built from production use. Token-optimized. Works with Claude Code, VS Code, Cursor, and any AI that supports context files.