Code agents

Rust-native AI inference & training engine. Block AttnRes linear-time transformer with profile-driven GPU dispatch, TurboQuant, GGUF/SafeTensors, LoRA, multimodal (vision/audio/video), FerrisRes Armor security. 39K LOC, 951 tests. Adapts to any GPU via wgpu — Intel iGPU to H100. No Python.

Alternative to OpenClaw for macOS & iOS Swift builds; Openclaw vocal assistant with full machine access. 讓你的蘋果設備更加智能，以及個性化本地部署。

A smart CLI tool powered by OpenAI to assist with terminal commands, answer questions, and provide context-aware help. Automatically detects your working directory and supports piped input. Streamline your workflow with AI! 🚀✨

Self-hosted personal AI assistant on Telegram. Powered by OpenCode + Claude Sonnet (free big-pickle). OpenClaw skills compatible. SQLite + MCP live memory with optional Ollama vector search.

Automated PR reviews powered by AI. Plug into any GitHub repo in minutes. Supports Groq, Gemini, Anthropic, and OpenAI with multi-provider fallback and key rotation. Get actionable, context-aware code feedback on every pull request without slowing down your team. Zero dependencies beyond requests.

Code analysis CLI - code review, bugs, security, docs, refactoring. Multi-provider LLM, SARIF output, CI-ready.

Assistant IA souverain multiplateforme intégrant Albert, les API compatibles OpenAI, le RAG avec Qdrant et les serveurs MCP.

AI-assisted context management and prompt compression toolkit for developer productivity, ADR workflows, and LLM token optimization.

Open-source, security-first AI agent that runs 100% locally. Provider-agnostic CLI + dashboard for agentic workflows, encrypted secrets, deterministic execution traces, and multi-step automation.

Find your forgotten side projects and figure out what to ship next. Scans local + GitHub, diagnoses health with Claude, suggests next steps.

Python agent harness — 5 LLM providers, 7 real tools, sub-agent spawning, hooks, skills"

Observable AI agent runtime with built-in execution tracing. Inspect, replay, diff, and debug agent behavior step by step. Model-agnostic (Claude, Ollama, OpenAI, Gemini). Built on Strands Agents SDK.

Claude Code plugin for React/Next.js — multi-agent orchestration, Figma-to-code, TDD, Harness Engineering, RTK, Obsidian

VectorSEO is a local AI SEO analysis tool with web scraping, AI based seo report generation, fine tuned AI Prompts for chats and seo optimizations.

🦑 Hire a PM. Get a company. — Open-source AI PM for solopreneurs: dev team, marketing team, creator team, all from Telegram

Claude Code skill: decide when to render output as HTML over Markdown — based on Thariq Shihipar's html-effectiveness examples. Bilingual (zh-CN / en).

Neuroplex is a cutting-edge AI Agent platform that combines FastAPI, Vue.js, an AI Engine, Neo4j, and Milvus to enable smart knowledge management and intelligent Q&A.

Single-binary web scraper for AI agents. Headless Chrome + Readability → clean Markdown. Up to 99% token savings. Zero dependencies. Built-in MCP server.

AI-powered lakehouse platform for IT job market analytics

Local-first AI dashboard for med students. Lives on your Mac, drives your apps, knows your week. Real Anki / Outlook / iMessage / UWorld / Spotify integrations + a Claude agent with tool access.

Autonomous Claude Code agent — 14 specialized agents, 10-parallel execution, project-specific skill learning, mechanical checkpointing, wave-based planning with acceptance gates, caveman ultra (~75% token savings). One prompt → finished project.

🚀 Enhance Claude Code with Gemini CLI for better code generation, reviews, testing, documentation, and architecture analysis.

AI agent skills for onboarding merchants to UCP (Universal Commerce Protocol). Audit → Profile → Catalog → Checkout → Validate.

An issue-driven AI coding agent for reliable GitHub execution with plan-first orchestration and validator-gated completion.

Agent Knowledge Cycle (AKC) — a knowledge cycle for AI agents: agent behavior compounds, human judgment sharpens. Six phases keep behavior aligned with operator intent as human attention becomes the scarce resource. ADRs, JSON schemas, dependency-free Python reference.

Deterministic Go code editing for LLM agents. AST-based CLI and MCP server that replaces Edit, Read, and Grep on .go files for Claude Code, Cursor, and any agent.

An example of Amazon Bedrock Agent integration with external APIs via Lambda.

A ultra-lightweight AI agent that communicates with the OpenRouter API and executes shell commands.

The user sees text that doesn't exist = Chrome's font settings + a malicious OpenType font + an AI agent's legitimate permissions. Here's the full chain and why it's hard to operationalize.

A Model Context Protocol (MCP) server that exposes Kali Linux penetration testing tools as structured, callable tools for large language models. Designed for integration with VS Code GitHub Copilot and any MCP-compatible LLM client.

Secondary LANE | Windows version. Turn ChatGPT into a real coding agent on your machine.

A mobile-first VC brief agent that turns YouTube and RSS signals into explainable Feishu daily briefings.

A standalone desktop workspace for Ask, Plan, and Agent workflows, built on GitHub Models and the Copilot SDK.

A no-fluff system prompt for Codex and coding agents.

An AI-powered blockchain agent that can interact with the Abstract Testnet blockchain. Built with OpenAI's Assistant API and viem.

AI-native browser automation for OpenClaw, LangChain, and AI agents. Automate job applications, price monitoring, trading bots, web scraping. Puppeteer/Selenium alternative with 40+ capabilities.

Y2K Labs — Agent skills for the entire software development lifecycle. Azure DevOps, backlog automation, sprint planning, and more. Works with Claude Code, Cursor, Copilot & 40+ AI agents.

O IDE onde a IA programa por ti. Chat-first, diffs ao vivo, pré-visualização em tempo real.

MentorCatto is an AI-powered learning platform designed to help students master Data Structures and Algorithms (DSA). With an interactive AI mentor, structured courses, real-time coding practice [Coming soon], and gamified achievements, MentorCatto makes DSA learning efficient and fun!

Governed coding agent infrastructure for real repositories with approvals, rollback, live validation, and local CLI/API/IDE workflows.

Production-ready AI Code Review Agent built with Google Cloud Agent Development Kit (ADK). Reviews pull requests via GitHub webhooks and posts structured feedback as PR comments.

Standard operating procedures for Claude Code sessions. Defined file set, slash commands for session start/end, Backlog with status tags and P-numbers, six non-negotiable rules, compliance checker, reference agents. Supports 3-5 parallel Claude Code instances on separate git worktrees — tracking-file conflicts prevented structurally.

AI agent that watches GitHub PRs for changes that silently contradict documented architectural decisions (ADRs) — and alerts the responsible engineer via Telegram before the code merges. Two-stage RAG pipeline with section-level ADR chunking, rejected-alternative detection, and corpus gap signals for self-healing knowledge bases.

Manage Notion from the terminal — faster than MCP. 19 commands, C++23, pre-built binaries.

🤖 Unit Test Agent 4J (uta): A production-ready, AI-powered CLI agent designed to automate JUnit 5 test generation. Built with Java 21 & LangChain4j. Features context-aware analysis, configurable LLM backends (OpenAI/DeepSeek), and a "write-once, run-anywhere" cross-platform architecture.

Idea-to-production AI blueprint generator for PRDs, system design, GTM plans, estimates, and coding-agent prompts.

One-command setup to turn a Raspberry Pi into a 24/7 AI agent with browser control, chat integrations, and local LLMs. Powered by OpenClaw.

Claude Code plugin: Control WhatsApp from Claude — read chats, send messages, search, auto-reply, export conversations, monitor in real-time. macOS only.

OpenCxMS Memory System - Persistent memory for AI coding assistants through structured documentation

Autonomous multi-agent IDE built on Cloud.ru Evolution that generates, executes, debugs, and self-maintains automated tests.

Privacy shield for AI Agents: Automatically mask PII and credentials before sending to LLM APIs. Supports tool calls & streaming.AI Agent 隐私防护盾：在调用 LLM API 前自动遮罩个人身份信息和凭据。支持工具调用与流式响应。

Migrated the brilliant everything-claude-code repo to an equivalent for Opencode. As I use several different programming languages, I'll progressively add support for all of them

Input product name, get enterprise-grade competitive analysis report in 10m. Powered by 5-Agent LangGraph DAG (Planner→Research→Analysis→Writer→Reviewer), Tavily search, SWOT output, citation traceability, SSE live replay & observability. FastAPI+Next.js+PostgreSQL / 输入产品名，5个Agent协同10分钟自动生成企业级竞品分析报告，支持全链路溯源与SSE可视化。

AI-powered agent that translates natural language into validated, benchmarked AVX2 intrinsics. Compiles and stress-tests generated C++ against a scalar reference, with an agentic retry loop on compiler errors and semantic mismatches. Built with Gemini, FastAPI, and deployed on Google Cloud Run.

Proactive screen awareness + Claude Vision assistance

A clean one-page calculator app built with Codexirra, using a React, Vite, TypeScript frontend and a FastAPI backend.

An open, non-commercial, schema-driven review platform built for AI Agents and humans. | 开放、非商业化、结构化驱动的评价平台。

Security scanner for AI agents, MCP servers, and agent skills

Autonomous AI agent framework for Python using OpenAI & LangChain — generates app descriptions, architecture outlines, UX flows & code from natural language objectives. Published on PyPI.

A speech-to-text chat agent with multiple tools. Utilizes Gemini, OpenAI, Wolfram|Alpha, openweathermap, and a few other APIs. Can manipulate files and web browsers. Currently working on implementing long-term memory via a neo4j graph database and allowing the user to feed additional data (knowledge) to that db via an obsidian knowledge graph.

🚀 Production-ready WebAssembly plugin examples for the Noorle platform - showcasing HTTP APIs, WASI 2.0, and the Component Model across Rust, Go, Python, JavaScript, and TypeScript

🤖 An AI-powered DevOps agent implementing ReAct architecture to automate mobile release pipelines (Crash Check -> Perf -> Build -> Audit). Built with LangGraph & Ollama.

Make AI work reproducible, debuggable, and contestable — like real software.

A full-stack multimodal meeting intelligence system with layered RAG, long-term memory, and skill-based generation.

Skills that help AI agents build better AI agents — prompt engineering, architecture, evaluation, and more.

🪞 Systematic self-reflection for AI agents. GENERATE → CRITIQUE → REFINE → CHECK. Based on peer-reviewed research. Zero API cost. Works with Claude Code, Cursor, Copilot, Codex CLI, and 10+ more platforms.

🎭 hark / ahoy / fr no cap / mans still — Claude Code plugin that makes thy AI agent speak like Shakespeare, a pirate, Gen-Alpha, or a Toronto mans. Code stays verbatim. For fun, not for token savings.

LLM-driven browser automation with wallet extension testing. Accessibility tree + optional vision.

Automate any website with natural language — AI browser automation CLI & API

Production-quality performance validation and regression testing for LLM inference systems

Advertising skills for AI agents. Covers strategy, campaign structure, audience targeting, creative best practices, and budget management.

Issue/PR-driven autonomous development system for GitHub, built with FastAPI, agent workers, and local/runtime automation.

Surgical integration tool - extract features from agent plugins without bloat

Ultra-minimal opencode agent runner for Cloudflare. Run AI agents indefinitely on your repos. Deploy in 5 minutes. ~/month. 300 lines of code.

A Claude Code plugin that helps you turn ideas into reality. It silently records the full AI session lifecycle, automatically fetches proven solutions from the community for reuse, and compiles structured reports back — so every collaboration stands on the shoulders of those before it.

Autonomous AI agent that reviews GitHub PRs for bugs, security vulnerabilities & code quality issues — powered by LangGraph, Llama 3.3 70B, and Langfuse observability. Includes evaluation benchmarks with honest metrics.

RAG-powered PDF QA system with self-reflection and multiple retrieval strategies (Stuff/Map Reduce/Refine). Includes monitoring via Langfuse & LangSmith and containerization with Docker

Autonomous memory and learning system for AI coding agents. LLM-powered knowledge extraction, triple fusion retrieval (FTS5 + TF-IDF + entity graph), quality-gated storage, and self-curating consolidation. Your agent never makes the same mistake twice.

logpeek — Peek into mobile device logs from AI coding agents. Give your agent eyes into Android & iOS logs.

OpenClaw plugin for dynamic capability discovery and tool calling via the QVeris API

Automate git workflows with AI-powered hooks that review code, generate and validate commit messages, and scan for bugs and security issues.

Cross-tool memory for AI agents. Stitch context across Cursor, Claude Code, Codex, Gemini CLI, Windsurf, Copilot, and 9+ AI tools. Preserves decisions, failed experiments & warnings across sessions. Zero dependencies, MCP + instruction files, BM25 relevance search. Never re-explain your work.

AI agent skill: Headless browser automation using Podman + Playwright for scraping JavaScript-rendered pages

AI-powered job search pipeline for cloud, cybersecurity, and tech roles. 15 modes, cover letter generation, cert gap analysis, follow-up scheduler. Built with Claude Code.

AI-powered engineering workflows — Learn from any source, Act through any tool, Report through any channel

Autonomous A-share quantitative trading strategy optimization powered by AI agents

Self-learning agent system for Claude Code. Humans steer at every layer. The agent learns at every layer.

A terminal-based AI agent for API developers.

A complete sales deal tracking web application built with Codexirra, using a React, Vite, TypeScript frontend, a FastAPI backend, and Postgres-ready persistence.

A hackable, local agent harness in pure Python. Claude Code–style tools, MCP, skills, subagents. Works with OpenAI, DeepSeek, Qwen, Ollama.

An AI-powered interview practice agent that simulates real interviews, asks contextual follow-up questions, adapts to user behavior, and provides detailed feedback using Groq Llama 3.1. Built with FastAPI and JavaScript.

BuddyQ is a fully local AI voice assistant for Windows that runs on your own hardware. It uses faster‑whisper, Piper TTS, and an OpenAI‑compatible local LLM (LM Studio or llama.cpp) to provide private, always‑on voice control with web search, timers, notes, weather, and screen/vision tools. No cloud, no API keys, no subscriptions!

Claude Code skill that enforces task scope boundaries during agent execution, preventing drift beyond the approved plan.

Everything you need to make an AI autonomous. One file. Production-tested.

Interactive AI development loop with mode selection — choose your pipeline before you start

Self-growing tag-dictionary RAG for any device. Zero dependencies, no GPU, no vector DB. pip install sandclaw-memory

🔧 AI Coding Agent Token Optimizer | Skills for Claude Code, Cursor, Windsurf, Codex | Save 40-80% tokens & costs | 省Token神器