Code agents

让本地 AI Agent 在线管理你的远程服务器。Zero-overhead SSH multiplexing CLI for AI agents — manage remote servers like local commands.

🐦 MCP server for X/Twitter API v2 with OAuth 2.0 PKCE — 10 tools: post, search, like, retweet, timeline, profile & more. Works with Claude Desktop & Claude Code.

Real, framework-free AI support agent where SynapCores is the brain — memory, RAG, tool routing, generation in one database. Browser chat widget + live Brain debug sidebar. Fork and run in 30s.

AI-driven Android UI test automation — plain-language cases run by an agent on real devices over any network (no ADB/scripts), with visual reports & self-learning.

🧠 EdgeBrain — Lightweight edge AI inference engine. Run ML models locally with sub-100ms latency. No cloud. No API keys. Just fast, private AI.

BRA Slim — free tier of Battle Ready Armor. AI-augmented security assessment, governed end-to-end. The operator drives; an LLM agent runs recon, captures evidence, drafts findings, and writes the report — every action gated, anonymized, and recorded by a governance layer the operator owns.

模块化通用 AI Agent 平台 — 持久记忆 / 自我进化 / 多智能体协作 / 知识库 / 视频生成 / IM 网关ai-agent, multi-agent, llm, knowledge-base, video-generation, im-gateway, self-evolution, persistent-memory, typescript, nextjs, fastapi, mcp, agent-framework, open-source

Open-source autonomous AI assistant with 5-tier security, 62 tools, 14 LLM providers. Written in Rust. Single binary.

Run teams of AI agents on your machine. Claude, Codex, Gemini, Grok, Qwen — coordinating in real-time via WebSocket. 204 built-in tools. Self-hosted, open source.

Claude Code that gets sharper every session: runtime discipline and instinct memory (the 7 Laws of AI Agent Discipline)

Agent Reliability Engineering: applying SRE principles to AI agent systems. Evals, imp@k metrics, self-improvement, config versioning, transfer experiments.

Multi-agent autonomous development loop for Claude Code — 17 agents, review pipeline, context management, and parallel execution

LiAgent OS is a local-first AI agent OS for building a private personal assistant with governed autonomy across local models and hybrid cloud services. It brings conversation, tool use, multi-agent orchestration, task scheduling, heartbeat execution, human approval, and auditability into one long-lived loop.

Run a lightweight daemon that turns your Claude Code into a task scheduler and Telegram assistant without extra API keys or billing concerns.

MemOS - Universal local-first persistent memory layer for AI agents and LLMs

Architecture patterns for multi-agent systems with orchestrators, sub-agents, and tool coordination

Master workflow orchestrator with autonomous task-to-production automation, quality gates, and multi-agent review

An open-source, lean AI content generator producing SEO-optimized blog posts via multi-model orchestration. Interactive CLI tool with Rich prompts, GSC-driven SEO optimization, and direct publishing capabilities. Originally built by Flyweel We're building the layer connecting spend, revenue, and capital with agentic finance.

A code-first framework for building deterministic CLI tools that LLM agents can discover, validate, and invoke with zero guesswork. Powered by Zod schemas and structured output contracts.

A retrieval-gated skill architecture for LLM agents that scales to hundreds of tools by exposing only the top-K relevant capabilities per request.

A comprehensive guide for modernizing mainframe applications (IBM z/OS, Unisys, GCOS, ACOS) using Azure AI Foundry with GitHub and Azure DevOps, preserving existing investments while enabling modern DevOps and AI capabilities.

A .NET 8 tool that acts as a static, mission-bound agent to evaluate any OpenAPI 3 specification for governance and compliance readiness. It performs spec linting, basic security checks, rate-limit header detection, and safe endpoint sampling, then generates Markdown and JUnit reports for developers and CI/CD pipelines.

Agent skills for using OpenCage services

Comprehensive, auto-updating literature review of GenAI & LLM security research, standards, tools, and resources. 100+ curated entries with interactive webapp.

Self-hosted alternative to Claude Code Web, Codex in the Cloud, and similar managed agent environments. Spawns isolated AI coding agent workers in Docker containers, each with a live terminal, VS Code editor (browser + native tunnel), virtual desktop, TCP port + domain mapping, and GitHub integration, all managed through a web dashboard.

GASADK: Agent Development Kit for Google Apps Script. Build AI agents with Gemini API, MCP, A2A, Agent Skills, Human-in-the-Loop (HITL) suspension/resumption, token quota safeguards, and dynamic Google API MCP servers.

Agent harness for hot-reloading function evolution in Rust.

The production-ready Flutter starter built for Claude Code, Cursor, Codex, and modern AI coding agents.

An opensource agentic system infrastructure - not an OS

A Claude Code skill that generates beautiful HTML reports instead of long terminal output

Agent-ready Twenty CRM toolkit. 396 bash scripts covering every REST endpoint, CRUD, batch, filters, merges across 30+ objects. Drop-in skill for Claude Code, OpenClaw, MCP clients, or any agent/CLI with bash + curl + jq.

Twelve Claude Code skills enforcing strict code quality, security, and modern language patterns across TypeScript, Rust, Swift, Go, JavaScript, and PostgreSQL.

Your Claude Code & Cowork conversations are sitting on Anthropic's mercy — until they're not. claude-backup exports everything to local Markdown, and rescue bundles it for handoff to ChatGPT, Cursor, or any AI agent when you need a Plan B. Lazy install: paste PROMPT.md into any AI

Open-source Claude Skill + MCP integration for job search and interview prep. Live job data, role-specific interview intel, voice mock interviews on four-leaf.ai.

97 reasoning patterns from history's greatest minds — as Claude Code agents. Curie to Toulmin. Engineering to humanities. Every claim cites its source. Every commit is checked. The only agent system where "I don't know" is a feature.

Pi coding agent extension for Claude via Google Cloud Vertex AI

The first Claude Skill that reads your codebase before it writes your Privacy Policy. Multi-agent compliance workflow for vibe coders and early-stage founders - GDPR, CCPA, COPPA, Israel PPL, UK GDPR, Google OAuth, CAN-SPAM.

AI-powered adaptive learning platform. Upload PDFs to auto-generate courses with chapters, modules & assessments. Features personalized AI tutoring, spaced repetition, gamification (XP, streaks, badges), and detailed analytics. Built with Next.js 14, MongoDB, and Anthropic API.

Open source Claude Code plugin — 52 invisible engineering skills turn vibe coding into production-ready software. Auto specs, TDD, security hooks, quality gates, self-improving retrospective. 97% vs 41% on blind benchmark.

Self-healing AI agent framework for Claude Code: 13 specialized SDLC/SSDLC agents, 26 skills, 13 slash commands, 9 hooks, launchd watchdog daemon, observability dashboard. Auto-activating, drift-reconciling, snapshot-protected.

Hands-on LLM evaluation learning repo — local models via Ollama, no paid APIs, no maths. Covers deterministic eval, LLM-as-a-Judge, hallucination testing, prompt injection, RAG evaluation, and agent trajectory scoring.

the memory layer of your codebase. Knows the WHY, the WHAT, the WHERE-IT-BREAKS.

A fully functional conversational AI system for restaurant phone ordering using Twilio, Whisper, LLM, and RAG

Merlin Community Edition — free dedup engine + integrations. Saves LLM tokens. No telemetry.

FileConcat is a privacy-first tool that packs the files you pick into a single LLM-ready blob. The output is one XML or Markdown document you can paste into Claude, ChatGPT, Gemini, or any other assistant that takes long-form context.

AI-Assisted Code-to-Support-Flow Visualizer

🎓 Turn any course PDF into structured self-study notes with AI. MinerU extraction → page-by-page notes → 7-dimension AI review → Notion sync. OpenCode skill for students.

Multi-Agent OS for LLM-powered NPCs — AI characters live, wander, and talk autonomously in a pixel-art 2D world. Supports MCP protocol, skill system, multi-LLM (DeepSeek/OpenAI/Claude), and real-time collaboration chains.

Go backend SDLC spec skill for AI coding agents

Gemma 4 + Google ADK GIS Agent for NL2Semantic2GeoSQL and controlled county-scale GWM/MPC planning with native function calling, hard-constraint validation, recovery, and verified memory.

Build Dify workflows from business requirements with design, YAML generation, review, refactor, validation, nanny-mode guidance, and URL-driven app recognition.

A Claude Code plugin that transforms Claude into a multi-agent orchestrated system with specialized agents (Riko, Senku, Loid, Lawliet, Alphonse), verification gates, and cost-aware model selection.

Agent Identity Protocol -- verifiable, delegable identity for AI agents across MCP and A2A. IETF Internet-Draft. PyPI: agent-identity-protocol

A modular LLM skill for epistemic operations and noetic analysis: a cognitive-security framework (SOC) for classifying discourse and diagnosing orientation, deformation, and concealment; routing engagements through matched case modules and tactics, techniques, and procedures (TTPs), grounded in sound reason and normative disposition.

The best blockchain harness for agentic AI - on-chain execution with runtime, skills, and component library.

Local AI (LLM) Ollama Tool and Extension. It's a hammer /approve /reject are your friends.

A lightweight AI assistant sidebar for Safari / 轻量级 Safari 侧边栏 AI 助手 （Supports OpenAI-compatible）

This repo contain the LLM models , ai api keys and ai automation works practice code , project sample code of solana hackathon

Complete guide to Claude Code as a system-wide assistant — setup, workflows, advanced patterns

Model Context Protocol (MCP) server providing AI assistants with comprehensive Terragrunt documentation, code examples, and intelligent tooling for infrastructure-as-code development

Assistente virtual inteligente para WhatsApp com IA, Celery, Docker e integração com APIs modernas. Escalável, modular e pronto para produção.

MCP wrapper for Burp Suite that builds complete, well-formed HTTP requests from structured input + ingests dedup/JS exports for token-thrifty AI-assisted pentesting. Bundles a fixed Burp extension.

AI humanizer: CLI tool and Claude Code skill for rewriting AI-generated text into natural human writing.

Manage multiple Claude CLI account profiles.

Production-ready Claude Code configuration. 12 original agents, 200+ slash-command skills, 45+ MCP servers, 14 plugins, design + 3D + WebGPU + GSAP + RAG tooling. One-command Node.js installer for premium websites, SaaS apps, AI agents. Free, MIT, stack-agnostic.

Your math is wrong. Here's exactly where and why! 🔬 AI agent that verifies every step of a student solution, pinpoints the root cause of errors with SymPy symbolic math, and generates 🎯 targeted practice. Covers 📚 8 STEM subjects. Built with LangGraph multi-strategy workflow + FastAPI web UI⚡

MemroOS / memroos: memory OS and governance layer for AI agents, agent workflows, dispatch, proof, and context continuity.

Claude Code Skill that transforms Claude into a multi-agent hedge fund analyst with 8 AI agents for comprehensive stock analysis

A lightweight, file-based A2A (Agent-to-Agent) message bus for multi-agent teams. Zero middleware dependency — CLI push, bidirectional ACK, task tracking, heartbeat monitoring, full-text search, and a standalone web dashboard. Framework-agnostic: works with Hermes, OpenClaw, Cline, OpenCode, and any CLI-capable agent.

Per-agent scoped MCP tool proxy — credential isolation, resource scoping, and audit logging for AI agent deployments

Linux-native workspace for coding agents with embedded Ghostty terminals, git worktrees, local socket automation, lifecycle hooks, and prompt-aware notifications.

Portable Desktop AI Agent. Built on LangGraph & MCP. Safe by design: human-in-the-loop for all critical actions. Self-correcting, api-key-rotation, multimodal, multi-tool coding assistant in a single .exe.

Multi-model AI deliberation system querying 12 AI consultants (Gemini, Codex, Claude, Mistral, Ollama, etc.) in parallel. Features unique personas, confidence scoring, multi-agent debate, weighted synthesis, presets, and self-exclusion. Claude Code skill compatible with agentskills.io

A Claude Skill for writing publication-ready domestic and international literature reviews — five-step pipeline, eliminates citation chains, structured gap logic.

Give your AI coding assistant full programmatic access to Google NotebookLM — with per-project notebooks, session wrap-up, and cross-platform support for Claude Code, Cursor and OpenAI Codex.

Write with AI Agents — Markdown Editor & Viewer. 100% client-side, no sign-up.

Claude Code autopilot with self-healing memory: one command → build → test → localhost. Trajectory tracking, learned routing, and stop-hook enforcement across runs.

📚 Lexicon AI — Agentic Research Workspace. Multi-agent literature intelligence powered by Next.js, FastAPI, ChromaDB, and CrewAI.

Autonomous multi-agent AI pipeline that reviews GitHub pull requests, generates fixes, runs test validation, and produces documentation.

Run the DeepSeek V4 Pro AI model on your desktop for fast coding, research, and problem solving.

🐜 Control a real Claude Code AI agent on your machine from Telegram — code, run commands, voice, files & multi-user team access. Self-hosted personal AI assistant. (Hasharot — ishlaringizni hashar qilib bitiring.)

Autonomous AI-agent workflow experiments for Xiaomi MiMo Orbit 100T Token Grant for Builders.

Memory-native coding Agent with episodic memory, and both semantic/verbatim recall. Shipped as an Opencode fork and comes with Hermes-native memory integration.

Sleek, fast, token-efficient AI coding agent. Multi-provider (Cortex, OpenAI, Anthropic, Ollama) with a polished terminal UI. Fork of vix.

Turn a natural-language spec into a coherent three-platform SaaS — Rails 8.1 API + native SwiftUI iOS + native Jetpack Compose Android. A Claude Code agent with structural, runtime, and vision-based validation.

CLI coding agent สไตล์ Claude Code — Claude API / Cloud / Ollama / llama.cpp, 42 skills, single-file

Drive LinkedIn from the CLI or any program — search, scrape profiles, check status, connect & message — via a real browser session (Playwright) + the Voyager API. JSON-first, LLM-agent friendly. No API key, no SaaS.

Universal full-stack dev Skills for Kiro IDE, based on superpowers methodology

Scribo Claude/Codex skill — generate EN 16931-compliant e-invoices (ZUGFeRD, XRechnung, US plain PDF; Factur-X, Facturae, Peppol BIS UBL coming soon) via the public Scribo HTTP API

Your agents forget every correction. otto makes them stick.

Xcoder — 超越人类与 AI 边界的 AI 编程 CLI | AI coding assistant that pushes beyond the boundary between human and AI

Open-source security firewall for MCP servers. Scan for OWASP MCP Top 10 vulnerabilities, enforce runtime policies on AI agent tool calls, and generate compliance audit logs.

Open-source, local-first AI coding agent for developers who want control. Use any model, inspect every action, review diffs, run commands safely, and keep your code under your rules.

Automated B2B company outreach via web contact forms — TypeScript port (Electron main + dashboard server)

MOVED to github.com/professorpalmer/marionette -- this repo is archived. Marionette: a desktop AI coding harness over Puppetmaster durable state.

This project is a dynamic AI chatbot that can be trained from various sources, such as PDFs, documents, websites, and YouTube videos.

Production-grade RAG system with hybrid retrieval (Qdrant + Elasticsearch + Neo4j), Corrective RAG via LangGraph, feedback-driven reward model, and RAGAS evaluation dashboard

LLM-powered Quantitative research assistant which combines financial data, quantitative models, and natural laungage generation to produce insightful market research reports. AI/ML + FinTech Engineering

Reusable AI teams for real work: generate, run, and evolve versioned multi-agent teams.

Multi-agent, evidence-weighted orchestration CLI. Vendor-neutral (Claude/Codex/Gemini/local), layered safety, chat connectors (Telegram/Slack/Notion/WhatsApp). Evidence decides — not consensus.