#agentic-ai

A trilingual (繁中 / English / 简中) learning roadmap for agentic AI: from LLM basics to multi-agent systems, with 240+ curated resources and hands-on examples. 中文 AI agent 學習地圖。

The living ecosystem where AI agents complete tasks through workflow loops, improve through iterative execution, are evaluated by mentor agents or humans in the loop, and turn completed work into reusable work experience and data to improve future agents.

Local-first, zero-trust agentic IDE for verifiable autonomous software development.

AI Agent Toolkit 2026: Smart Device Control for iOS & Android

Turn feature requests into review-ready pull requests: issue, implementation, tests, a review-and-fix loop, and docs. Runs locally or on GitHub Actions, and is built for complex brownfield repos. Each week its retrospective reads what you actually merged and proposes improvements to your skill extensions.

Copilot-style AI coding agent for VS Code, powered by DeepSeek V4.

The AI-native JupyterLab — open-source Cursor for notebooks. Cmd+K inline edit, multi-step agent with cell-level tools (read/edit/run), chat with @cell/@file context, ghost-text completion, one-click traceback fix. BYO model: Anthropic, OpenAI, Gemini, Ollama, vLLM. Local-first, privacy-first, fully open source.

🔁 Build reliable recurring AI-agent systems: 968 resources, 22 operational patterns, 22 loop contracts, 8 runtime starters, an interactive atlas, and a structured dataset.

Ultra-lightweight native AI agent framework written entirely in Object Pascal for Delphi and Free Pascal, designed for performance, portability, and extensibility.

CubePi — An async-first Python agent kernel inspired by Pi, built for coding agents, tools, and continuous sessions.

fak — the Fused Agent Kernel: one Go binary that turns a tool-using agent (Claude Code, Codex, Cursor, any OpenAI/Anthropic/MCP client) into a managed agent: cache-stable model traffic, context compaction + crash resume, nanosecond tool-call policy, local GGUF serving with SSD expert offload.

A simple studio to use agent

Self-hosted agentic OS — connects Claude Code, Codex or Hermes Agent to Discord, Telegram, WhatsApp, Slack & Email. EU AI Act 2026 & GDPR compliance by architecture.

Agentic research control plane: queue state, worker preflight, wake-gated execution, evidence sync, dashboard, alerts, and AI-generated paper packaging.

Experimental Chrome side-panel browser agent with LangGraph.js, MCP/WebMCP, local models, and semantic browser automation.

MCP server for the Ejentum API. 8 cognitive operations across 4 harnesses (reasoning, code, anti-deception, memory) in dynamic and adaptive modes.

The runtime substrate for agentic systems — one Go binary, six LLM providers, MCP-native, configurable as a managed sandbox or full agentic dev environment. Where agents live, talk, and learn.

Universal multi-agent infrastructure for AI coding assistants. 26 specialist agents, 19 enforced workflow skills, and a lead orchestrator — for Claude Code, Codex CLI, Cursor, and OpenCode.

基于 DeepSeek 大语言模型的 AI 编程助手 Agent —— 自然语言驱动的终端编码助手。支持自动读写文件、代码搜索、命令执行、Git 管理，复杂任务智能拆解与多 Agent 并行执行。

Agent SkillOS — the wealth-accumulation layer for self-improving AI agents.

Keyless heuristic self-inspection tool: an agent describes a thought or task and always gets back one metathought. Deterministic routing over an open CSV (no LLM). REST + MCP.

An autonomous AI chatbot built for WhatsApp using Node.js, Baileys, and the Vercel AI SDK powered by OpenAI. Designed to act like an active, context-aware participant in group chats and direct messages, Quart goes far beyond traditional command-and-response bots by actively listening and engaging in human conversations.

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

Plumbline — a self-learning, customer-value-governed agile AI agent team for Claude Code. 87 subagents + skills, TDD defense-in-depth gates, Kaizen retros, a four-body adversarial council, and an empirically benchmarked QA harness. Does it hang true?

Skills from pubXers. Straight from our .claude directories. Live long and prompt!

Docs site of OpenAgent: https://github.com/the-open-agent/openagent

Your own self-hosted AI agent OS

Local-first autonomous agent: Hermes speed plus Rust determinism, gated actions, checkpoints, evidence receipts, MCP, skills, and multi-model freedom.

Proof Gradient is the agent evolution protocol where every run leaves proof, every proof selects intelligence, and every selected artifact evolves the network.

Cross-agent prompt pocket: remember your most-used prompts and pick one to run. Works on Claude Code, Codex, OpenCode, Cursor, Copilot & Gemini; auto-scans Claude/Codex/OpenCode sessions for prompts you repeat 7+ times. Forged by agent-plugin-kit.

Desktop AI chat app unifying local Ollama models with OpenAI and Claude — includes an agentic mode where the model can read/write files and run shell commands, with every action requiring your approval.

Agentic AI system that ingests PSX market data and financial news, resolves conflicting signals, and constructs a justified investment portfolio with simulated execution.

Skainet Bridge — local automation bridge for AI agents: one process, one port. MCP server + client, REST, browser extension, sandboxed exec. Independent project, unaffiliated.

Live index of the newest agent frameworks shipping on GitHub, sorted by recency not stars

Ten composable AI skills covering the full arc from idea to launch. Discovery hub for prd-ready, architecture-ready, roadmap-ready, stack-ready, repo-ready, production-ready, deploy-ready, observe-ready, launch-ready, harden-ready. Plug into Claude Code, Codex, Cursor, Windsurf.

🏭 Coding agent CLI engineered to make any LLM — local or cloud, frontier or 7B — actually useful. 16 providers, multi-tab sessions, automatic key+model failover, plan-mode review, MCP, and recovery loops for models that misbehave.

ClaudeRoam — Your Claude Code config, anywhere. Across Macs. Across accounts. Without the copy-paste.

A curated, credited library of loops — repeatable AI-agent workflows for Claude Code, Cursor & Codex. Refactor until clean, test until 100%, hunt bugs until none remain.

Proxilion is the security layer for the agentic workforce. It turns managed AI agents into governed users by enforcing strict cryptographic boundaries on every API call to SaaS like Google Workspace, Salesforce, or Atlassian.

Enterprise-grade multi-agent AI orchestration platform using LangGraph, LangChain, CrewAI, Gemini, and ChromaDB.