#code-generation

Open, MIT context format for AI coding agents: centralized .aigx/ rules + a per-file boundary index that targets the right rules, forbidden imports, and gotchas to each file. The only context format validated in a controlled benchmark. Tool-agnostic; nothing injected into your source.

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。

Route implementation to OpenCode, Antigravity, Cursor, Codex CLI or Claude Code CLI, with Claude Code or Codex as architect and judge. Committed acceptance tests and verified integration gate delivery.

Fable 5 workflow Loop; A Claude Code skill: autonomous build / audit / verify loop that runs until a machine-checkable contract passes, with ▎ deterministic anti-spin stop conditions (no-progress, retry, oscillation, budget) and on-disk human escalation.

你的全能 AI 员工——短剧、写代码、做硬件，一句话搞定

Two Claude Code skills that run a coding task through a multi-agent harness — plan → N parallel implementations → adversarial verification → judge. pantheon (Claude-only), pantheon-x (GPT-5.5 cross-model verify). MIT.

A Claude Code plugin for Java & Spring Boot backend engineers that turns one task into a gate-enforced 7-phase agentic workflow — Discover → Brainstorm → Spec → Plan → Implement → Review → Learn. Native hooks, 11 subagents, path-scoped rules, project memory & strict test-first TDD.

Autonomous software factory: give it a plan, get a verified, merged codebase. Pull-based agents (Claude Code, OpenCode, Codex) in a sandboxed rig, with a Beads ledger, typed railway-oriented Rust, and done-means-verified.

REST API wrapper for Claude Code CLI — execute code, manage files, and run commands remotely. Built on claude-agent-sdk with FastAPI.

AISEF — AI Software Engineering Framework: one requirements file in, a gated and evidence-backed application out. Agents do the judgement; code enforces the guarantees.

The open standard for AI-ready software specifications

TypeScript coding-agent runtime with explicit planning, isolated PIV execution, multi-agent coordination and terminal/editor clients.

Your tasks with 99% accuracy using any LLM (Claude, DeepSeek, Codex, Gemini, Hermes, OpenClaw, Cursor).

Guardrails for AI coding agents. EADOS generates a governed repo - agent contract, ADRs, CI gates, SemVer - for any of 19 languages, then enforces the rules with lint. Works with Claude Code, Codex, and Gemini.

Cross-agent frontend design skill for Claude Code and Codex CLI: seeded aesthetic variance, evidence-derived anti-slop rules, and a measured QA gate with bounded self-correction.

an ai model built from scratch that is 1.11 Billion Parameters [ yeah i know its an tiny model but this was only made by me

Compile S-expression specs into Go scaffolding via lowering passes and tree tiling, leaving typed holes for an LLM.

AI-powered full-stack tool that converts Figma designs into React + Tailwind code with a FastAPI backend, Ollama LLM integration, and a React/Vite frontend.

Autonomous SWE-Agent powered by Xiaomi MiMo — reads GitHub issues, writes code, runs tests, creates PRs

Autonomous AI Cloud Agent 2026: Auto-Fix Code & PRs with Multi-LLM Sandbox

⚡ RustyClaw 2026 — AI CLI for RAG Agents, Voice Cloning & Browser Automation

Enclave Local is a fully offline, air-gapped AI synthesis platform for generating production-ready codebases and native PowerPoint presentations without cloud API connections.

Context-efficient AI agents for software engineering. Turns tasks into investigated, implemented, validated and independently reviewed changes.

MCP server that saves Claude Code tokens by delegating bounded tasks to local or cloud LLMs. Works with LM Studio, Ollama, vLLM, DeepSeek, Groq, Cerebras.

Evaluator-grounded autonomous prompt evolution. Genetic algorithms + runtime validation + meta-evolution to evolve prompts that generate better AI agent code. 150 generations, 862/1000 best score.