agent-loop

Self-evolving second brain with 35 AI skills, 10 agents, and people CRM. Closed-loop harness: a V-model verification lifecycle where the worker never grades its own homework. Plus paired anti-slop design skills for marketing and product UI. Works with Claude Code, Cursor, Kiro, Gemini CLI, Codex.

600 行 TypeScript 写成的超级迷你版 pi，让你轻松从 0 写出属于你的 pi-agent

Helixent is a small library for building ReAct-style AI agent loops based on the Bun stack.

A self-evolved, sovereign desktop AI agent built for real-world action — beyond model wrappers and coding copilots. / 真实实践中自我演化的独立桌面 AI Agent。

A Boris-style agentic orchestrator TUI that supervises headless Claude Code agents through a gated software-delivery pipeline — pointed at any repository.

Source-backed architecture notes on building an agent

学习Agent开发的笔记，尝试让Agent从可用到可靠

Learn AI Agents step by step, from scratch - from function calling to agent loops to multi-agent systems, orchestration, and evaluation.

A loop engineering framework — state a Goal; Rounds run until a skeptical, read-only Verify agent settles it.

Local-first observability your agent reads back. TMA1 records every LLM call, then routes what it sees into the agent's next turn via hooks and MCP.

Reverse-engineering Claude Code's 512K LOC TypeScript source: agent loop, tool system, permission model, Grove training pipeline, anti-distillation defense

A standalone durable graph router with explicit controls and no runtime dependencies.

Agent Harness (Loop Engineering) dev guide — complete architecture & core modules, based on production-grade agent source: Claude Code, DeepSeek Harness, OpenCode, Pi, Codex, OpenClaw & Hermes. English & 中文

Foreman 2026: AI-Agnostic Build Playbook for Shipping Real Websites Fast

Curated, verified survey of the agent harness — the layer around an LLM (loop, tools, memory, context, runtime) that turns it into an agent. 116 papers + Claude Code / Codex / Cursor / OpenHands tools + Anthropic / OpenAI / Karpathy essays. Agent = Model + Harness.

MIT-licensed, backend-agnostic AI agent orchestration loop in Python: orchestrator→worker→reviewer as a deterministic harness. Drive coding-agent backends through an MCP server + CLI.

Claude Code 源码逆向恢复项目 | Source Map 逆向 · 架构分析 · 可运行版本 | 1900+ 文件 · 51万行代码 · 12章节课程

Run DeepSeek as a real sub-agent inside Claude Code / Codex CLI — with its own 7-tool agent loop, workspace-scoped file access, and bounded Bash.

This project is for learning: it shows how an agent loop works underneath, in a way more intuitive and visual than reading about it. Behind an agent's chat box runs a loop: step after step, the model proposes an action and the harness carries it out, until it stops.

🤖 Official Interactive Tutorial for OpenHarness – Zero to Hero in 12 Chapters | Learn OpenHarness like Claude Code: Agent Loop, Tools, Memory, Multi-Agent | 面向零基础的 AI Agent 交互式教程