Code agents

Simple project to connect another project work as Chatbot runtime with openAI API style, great for learning, testing, experiment, without expensive API with work all locally.

Access Twitter timelines, bookmarks, and profiles from the terminal without requiring API keys, offering a simple CLI user experience.

Own your AI from any device. Lightweight secure agent (~1100 lines Python) that smart-routes Telegram/Web Chat messages to Claude or Ollama. Docker, 6-layer security, persistent memory. One command to start.

A lightweight, framework-agnostic persistent memory graph for AI coding assistants.

Partner 🤝 Your AI Research Companion. "What have you been doing?"

Octopai - The Infinite Evolution Skill Engine for AI Agents. 🐙 Everything Can Be a Skill • Skills Evolve Through Continuous Learning • Elevating AI Agent Cognition!

A Bun + FastAPI monorepo for running a mobile-friendly AI workspace in the browser, backed by a configurable LLM gateway and repository indexing APIs.

Trust and quality infrastructure for AI agents. 225+ quality-scored capabilities, SQS scoring, EU AI Act support.

Minimal autonomous coding agent. Simple tool-use loop over LLM API — no frameworks, no magic. Bash runs in Docker sandbox. Supports Anthropic, OpenAI, and any OpenAI-compatible provider.

A Local RAG Chatbot powered by DeepSeek V3 & RapidOCR. Chat with scanned PDFs, images, and documents privately. Built with Streamlit & LangChain.

Model Context Protocol (MCP) Bootcamp offers a deep dive into MCP architecture and its role in the Agentic AI ecosystem. Learn to build real-world, production-ready AI workflows using MCP with LangChain, LangGraph, and CrewAI through fully practical, project-based implementations.

Simplify Tax is an AI-powered tax filing and optimization tool designed to assist Indian taxpayers in understanding their tax obligations, maximizing deductions, and selecting the most beneficial regime. It reads bank statements, classifies income, calculates tax liabilities, and recommends the optimal tax-saving strategy — all automatically.

🦞 Harness Engineering for OpenClaw — Turn your AI agent into a structured engineering team. Native ACP integration, Sprint contracts, multi-round review. Inspired by OpenAI, Anthropic & DeerFlow.

A deterministic development harness for Claude Code — MCP workflow engine, enforcement hooks, YAML workflows, and multi-agent consensus (Claude + Codex + Antigravity/Gemini)

Multi-agent harness for Claude Code: autonomous Planner-Generator-Evaluator sprints with parallel Agent Teams, harness-engineering framework, and 9 canonical defect diagnoses.

Build custom ACP-compatible AI agents using your existing subscriptions. No API keys. No vendor lock-in. Supports Claude, Gemini, and Codex backends.

🏛️ Manage your life with a 1,400-year-old governance framework. 15 AI agents with separation of powers — Three Departments & Six Ministries personal cabinet system. Works on Claude Code, ChatGPT, Gemini, Cursor, and 30+ platforms.

Multi-agent LangGraph assistant for Montreal urban mobility — RAG, semantic caching, and a predictive ML collision model on FastAPI.

Achieve Frontier AI performance in your CLI — fuse the local model CLIs you already run. Fan a prompt across a panel, a judge model compares the answers, a synthesizer writes one grounded reply instead of a majority vote. On a 100-task benchmark, every fusion panel beat its solo members.

Reference architecture for secure multi-agent delegation chains using Cedar-based permission attenuation on Amazon Bedrock AgentCore. Demonstrates scope narrowing, tamper-proof token chains, and audit logging across A2A agent interactions.

Multi-model AI council — spawn Claude, GPT, Gemini, and Grok as parallel coding agents to get independent opinions. CLI + pi extension.

The first open-source effort estimation tool built for AI coding agents. PERT + METR + wave planning.

⚡ Simple Agent Engine — Orchestrate AI coding agents from your terminal. No frameworks, just bash, jq, and tmux.

Open-source security-first runtime for AI agents that learn and act across sessions.

Spatial Engine AI: A DeepTech Agent that sees like a designer and calculates like a physicist. Powered by Gemini 3 Pro & Vision to optimize energy efficiency in built environments.

The system that builds itself. 500+ repos, 6000+ tests. Agent-readable onboarding from nothing to everything. Read ONBOARDING.md to wake up.

AI编码助手、Clude Code 实现 cli

A meta-mcp (mmcp) server offering a window into the exciting world of open data sources by intelligently routing model tool calls through an ever-growing index of open-data sources.

AgentNull: AI System Security Threat Catalog + Proof-of-Concepts. Collection of PoCs for using Agents, MCP, and RAG in bad ways.

GRC Mapping Analyst is a NIST IR 8477-based toolkit for AI-assisted cybersecurity crosswalks, producing deterministic set-theory mappings (equal, subset_of, superset_of, intersects_with, not_related) and 12-column STRM CSV outputs across frameworks, regulations, and control catalogs.

Enterprise and government control plane for AI agents and MCP servers: govern, secure, observe, and audit. Rust, multi-provider (incl. major Chinese models).

Fleet Pi , workspace for Pi-powered coding agents, with durable plans, memory, and repo-scoped tools

The Claude Certified Architect – Foundations certification validates that practitioners can make informed decisions about tradeoffs when implementing real-world solutions with Claude. This exam test foundational knowledge across Claude Code, the Agent SDK, APIs, and MCP — the core technologies used to build production-grade applications with Claude

Track, score, and manage your Claude Code skills across all projects with a local analytics dashboard.

Configure and use multiple AI providers (Claude CLI, Gemini, OpenCode, OpenRouter, and more) as chat Agent in IntelliJ IDEA's AI Assistant chat.

Use frontier coding agents with Zero agentic development environment

A custom reactive AI Agent framework that allows for creating flexible reactive agents to carry out tasks using MCP and Custom tools.

Agent Skill for OpenHive — shared knowledge base of AI-discovered solutions. Works with Claude Code, Cursor, VS Code, Kiro, and 35+ tools via the Agent Skills standard.

Opinionated Claude Code foundation — Explore → TDD → Audit workflow, auto-detected stack presets (nextjs, fastapi, astro, ...), curl | bash install. MIT.

A proactive AI assistant using Qwen-Agent to learn your writing style and manage Google Calendar & Gmail.

🚀 Privacy-first metasearch engine & AI infrastructure. Featuring absolute DOM proxification, zero-tracking, and structured data extraction for LLMs and AI explorers.

The trust layer for code written by agents. Two frontier models, unanimous review, SHA-pinned receipts.

An advanced, multi-backend AI Agent Chat application built with React, FastAPI, and LangChain. Features a rich toolset including web search, code execution, and long-term memory.

Local-first AI assistant for macOS — chat with your PDFs, spreadsheets, CSVs and code using a local LLM via Ollama. Model-generated Python runs in a Seatbelt sandbox with no network. No cloud, no telemetry, no API keys.

AI coding rules framework for Claude Code, Cursor & Kiro — turn tacit knowledge into enforceable guidelines

🚀 Connect Burp Suite MCP Server to multiple AI backends with practical guides and templates for safe, real traffic analysis.

Beginner-friendly All-in-One Unraid container for Khoj, a self-hosted AI second brain. Bundles the Khoj web app with an internal PostgreSQL database in a single container, while still supporting local or hosted LLMs, external search backends, reverse proxies, and advanced power-user overrides.

Find what's burning a hole in your AI coding budget. Local-first cost-control for Claude Code.

Native desktop dialogs for Claude Code — macOS and Windows. Ask, confirm, collect input where you actually work.

macOS desktop widget showing Claude Code usage as a contribution grid with real-time rate limit bars

Content creation skill for Claude Code — blogs, landing pages, email sequences, social media, video scripts, newsletters, case studies, whitepapers, content calendars, editorial briefs, platform-specific formats, repurposing workflows. By TheGEOLab.net

Systematic worldview articulation - surface beliefs, identify tensions, generate narrative outputs for personal philosophy documentation

Ghostty config plugin for Claude Code — 11 MCP tools + domain knowledge skill

Mandatory final sanity check before commits/PRs - catches security vulnerabilities, logic errors, and bugs that slip through tests

🔥 191+ battle-tested cybersecurity skills for AI coding agents | Bug Bounty • Pentesting • Red Team • AI Red Teaming | Claude Code • Cursor • Copilot compatible

Mock OpenAI and Anthropic APIs locally for fast, deterministic tests.

A complete, opinionated Claude Code configuration with global instructions, 20 slash commands, and sensible defaults.

Autonomous job search pipeline: multi-platform scraping, AI scoring, CV/cover letter generation, and Telegram delivery

Provide 19 business operation skills for AI agents following the Agent Skills standard to analyze workflows and assess ROI efficiently.

Generates Palantir Foundry ontologies from CSV files using semantic analysis (Claude API) + MCP automation

MCP server connecting Claude to Metabase for natural language data analysis, dashboard management, and SQL queries

The AI-First, Battery-Included Python API Framework. Built on FastAPI with 21 production-ready modules, Rust native engine, and real-time admin dashboard.

⛨ redactum — automated PII & secret redaction for AI, APIs, and developer tools. Protects prompts, logs, and payloads before they leave your system. Lightweight and TypeScript-first.

Visual AI canvas for building & testing Next.js UI components — supports OpenAI, Anthropic, and Google AI with node-based data pipelines.

Run Claude Code CLI with local Ollama models in an isolated Docker environment. Free, private, offline-capable AI coding assistant.

Local-first analytics for Claude Code, OpenAI Codex and OpenCode. Track tokens, costs, cache efficiency and account limits, with Discord Rich Presence. Built with Rust and Tauri.

AI-powered terminal environment for penetration testers

🧠 Build a self-hosted knowledge management system that transforms scattered information into a smart, searchable, interconnected base.

AI sales-funnel engine — Telegram, WhatsApp & web widget, RAG, visa pipeline, admin UI, Postgres (monorepo)

🤖 Build advanced AI agents with a collection of production-ready applications using modern frameworks for single and multi-agent systems.

AI-powered QA Architect agent — generates ISTQB/OWASP/IEEE/ISO-grounded Test Strategies, Risk Registers, Effort Estimates & Test Plans via RAG. Cloud-hosted (Mistral API + Pinecone).

An agentic code context engine MCP+CLI which pre-compiles an llm-described AST in the .tost format, greatly reducing context bloat and token costs for agentic coding tasks

Five Tests Standard (5TS): a vendor-neutral published standard for verifiable AI governance through proof-carrying decisions. Includes schemas, machine-checkable conformance vectors, and a reference validator.

Agentic CLI for the Scrapfly platform: scrape, extract, crawl, and drive a cloud browser over CDP. Built-in LLM agent with Anthropic, OpenAI, Gemini, and Ollama. JSON-first, pipe-friendly, one static binary.

Many Agents, one objective... yours

Industrial-grade benchmarking engine for AI agents. Define test scenarios in YAML, run high-performance parallel evaluations, and generate premium glassmorphism reports. Supports LangGraph, CrewAI, AutoGen, and custom agent stacks.

A production-grade benchmark suite using Welch's T-Tests and Cohen's D to objectively compare AI agent frameworks (LangGraph, CrewAI, AutoGen).

ramework-agnostic multi-agent orchestrator. Declaratively compose LangGraph, CrewAI, and OpenAI SDK agents in a single YAML pipeline for production-ready AI workflows.

One command to turn a fresh Ubuntu VPS into a production-ready AI coding agent environment. Installs Claude Code, Codex CLI, Gemini CLI, language runtimes, and 40+ dev tools via idempotent curl|bash installer.

An opinionated Claude operating system for PM-led engineering. Planning, enrichment, delegated execution, staged review, ship decisions, durable handoffs.

A Claude Code-powered multi-agent pipeline automating the creation of Amazon KDP coloring and activity books, from niche validation to publishing assets, for US and IT markets.

One TypeScript SDK for every local coding agent - Claude, Codex, Cursor, Copilot, Gemini, OpenCode, Droid, Pi, Cline, Kilo, Qwen, Auggie. ACP transport, Vercel AI SDK provider, cost budgets, multi-agent orchestration.

TMPA — Textual Multi-Agent Process Architecture for durable AI-agent governance, responsibility, conformance, and auditable digital work. Research, specification, and evidence.

Multi-agent AI pipeline for Swiss residential building design. Give it an address, and it fetches zoning rules, generates a 3D site model, designs an IFC building, and runs specialist agents (structural, MEP, facade, fire safety) in review loops.

Frozen public snapshot (8 May 2026) of ZenAI — the self-hosted AI OS that remembers. 60 AI tools, 12,000+ tests, 440K+ LOC, 7-layer neuroscience-inspired memory. Not the living tree; active development continues in ZenBrain.

Autonomous operations layer for Claude Code — opens small reviewable PRs for your live side project and re-orients from which ones you merge or reject. HALT file + hard cost cap; you stay in command.

Scaffold autonomous multi-agent AI workspaces in one command. 12 providers: Claude, Gemini, Codex, Qwen, Cursor, Windsurf, Copilot, Cline, Aider, Continue, Roo, Nessy. Hooks, roles, memory.

Quality engineering for agentic coding workflows — a quality team member for Claude Code that observes, analyzes, and nudges, never blocks.

Atomic Spec: AI-native agentic methodology for living requirements. DDD + TDD + Use-Case-Driven. One atom, one file, one unit of knowledge.

🧠 TermMind — Terminal-based AI mind mapping & brainstorming tool. Generate, organize & visualize ideas right from your CLI.

Personal knowledge management system powered by Claude Code. Process meetings, Slack threads, and documents into a structured, searchable memory.

emeAI is a small local AI chat app that runs inside Google Chrome. It is made for people who want a private writing, learning, coding, and document review space without setting up a cloud API.

MOVED: now the tech-to-pm plugin in github.com/mshadmanrahman/pm-pilot. Install: claude plugin install tech-to-pm@pm-pilot

MCP server enabling LLMs to interact with WhatsApp - send messages with fuzzy name matching, full-text search across conversations, manage chats and contacts, and download media

Claude Code skill that silently refines every prompt for better results (auto mode) and lets you generate optimized prompts as text with /optimize (manual mode)

Responsible use of generative AI in assisted coding

Park. Pickup. Flow. A productivity system for Claude Code + Obsidian.

Local AI assistant that lives in your MacBook's notch. Powered by Ollama — chat, vision, web search, and an autonomous file-system Agent Mode (beta), all on-device.

Fast, lightweight, cross-platform IDE built with C++17 and Qt 6. AI assistant, LSP intelligence, integrated terminal, Git — native performance, no Electron.

Transcript-first AI video editing workflow for Codex, DaVinci Resolve, FCPXML, SRT, and faster-whisper.