Official Code for OpenVLHarness: Real-World Visual Agentic Tool‑Use with Multimodal Memory
- agent-harness
- agentic-ai
- ai-agents
- coding-agent
47,133 repositories indexed
601–624 of 837 · Most stars
Official Code for OpenVLHarness: Real-World Visual Agentic Tool‑Use with Multimodal Memory
TranslatedLet AI see your screen in real time: filter frames by the amount of change, stitch multiple frames into one image, and static screens cost almost no tokens
A Java library to use the OpenAI Api in the simplest possible way.
Translated🍟 Official McDonald's China MCP agent skill: orchestrates 35 atomic tools into 4 business flows — campaign push · collab watch · best-value ordering · group bill splitting. Prices are truly calculated with calculate-price, and orders must be confirmed a second time before placing. | McDonald's China MCP agent skill: campaigns, collab watch, best-value ordering, group bill splitting.
TranslatedA basic tutorial for getting started with AI Agents from zero background. It is not just a tutorial but also an Agent that can run locally: read and write files, execute commands, MCP, long-term memory, with a built-in web interface to see every step clearly. Starting from a minimal 100-line loop, each lesson adds one capability, and in the end it breaks down mainstream Agents such as Claude Code and Codex
A git hook that won't let you push code you can't explain. Quizzes you on your own diff. Works with Claude Code, Codex, Cursor.
Threat modeling for AI coding agents: point Claude Code, Codex or any agent at your repo and get an evidence-traced threat model. 36 architectures, 29 methods, MIT.
AI coding agent that makes a small model beat a frontier one
Walk through a diff the way a senior engineer reads it. A read-only TUI that turns a git change into a guided tour.
Local inference for diffusion language models (LLaDA, Dream), written in Mojo
TranslatedA Bilibili command-line tool designed for AI Agents: QR code login, watching videos, commenting, direct messages, posting updates, uploading videos, all with JSON output
FOREST is a research agent for long-horizon science, where evidence gets lost, errors compound, and goals drift. It explores ideas, reads literature, forms hypotheses, runs real experiments, analyzes results, revises paths, and builds a full paper—all in an editable graph you can inspect, branch, redirect, with claims and figures linked to evidence
TranslatedGEO Doctor: install it into your AI assistant with one sentence, find out why Doubao, DeepSeek, ChatGPT, and Claude don't recommend you, then fix your profile information, write content, and re-check. An open-source bilingual (Chinese and English) GEO (Generative Engine Optimization) skill.
An agent that compiles git maintenance chores into reusable programs, then decides whether to replay them by running checks rather than by guessing the task looks familiar
Official code for "Zero-Mem: Zero-Token Memory Operations for LLM Agents".
OPAL: a reactive optimizer. A coding agent rewrites the optimizer while your model trains.
Simplify format string exploitation.
YouTube transcript skills for Claude Code, Cursor and Codex. Agent Skills to get transcripts, search YouTube, read channels and playlists, and bulk export.
TranslatedDeploy and manage AstrBot and NapCat locally on Android phones, with a built-in PRoot Ubuntu runtime environment. Supports a native management interface, WebUI, logs, backup and restore, and independent updates, with no Root required.
Unified LLM API, structured data outputs with LLMs, and agent SDK - in PHP
Run models larger than your RAM or VRAM by streaming MoE experts from SSD. Built on llama.cpp.
Install Tiledesk on your server using Helm for Kubernetes orchestration and Docker Compose for running multi-container Docker applications. Tiledesk provides an open-source solution comparable to Voiceflow, empowering you to create sophisticated LLM-enabled chatbots that seamlessly transition interactions to human agents when needed.
Respounder detects presence of responder in the network.
Run Claude Code natively on Android via Termux or AVF (Android Virtualization Framework) -- no desktop, no SSH, no root required.