#ai-coding-assistant

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.

Finish-First Autonomous Agent Loop for Claude Opus 4.7 – 2026 Edition

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.

Local web workspace for coding agents — Claude, Codex, Gemini, and more in one inspectable, LAN-ready hub.

Index, search, summarize, and approval-gate local Codex sessions through OpenClaw/MCP. Agent-first recall and dry-run orchestration for Codex-heavy work.

Not just an agent demo — a local coding-agent platform: plan mode, sub-agent teams, cron, memory, MCP. Single Go binary, DeepSeek-native, MIT.

Security-First Agentic IDE Coding Harness

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。

自己动手写 AI Agent — 从 Claude Code 开源架构到你的第一个编程助手

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.

Build Your Own AI Coding Army 2026 – Multi-Agent Dev Kit for Copilot, Cursor & Codex 🚀

Free AI coding assistant for VS Code & Cursor — Claude, GPT-4, Gemini & 300+ models. No subscription.

A practical workbench of tools + methodology for solo devs driving an AI coding agent (Claude Code, Cursor, Copilot): safety hooks, secrets crypto, invariant + test-selection tooling, leak scanner, plus skill & memory system templates.

AI skills for Claude Code, Cursor, VS Code Copilot, Cline, and more

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.

Connect whole-genome sequencing data to AI coding assistants via the Model Context Protocol (MCP). Setup guides for GeneChat-MCP, OpenCRAVAT-MCP, and Pomera across Antigravity, Codex, and Claude Code.

Terminal UI that brings the local sessions of all your AI coding agents — Claude Code, Codex, Grok, and GitHub Copilot Chat — into one searchable place to browse, search, resume, and fork.

Unofficial distribution of OpenAI Codex CLI that adds /rewind and /redo — restores your files, not just the conversation. Git-free snapshots that never touch your git state. Tracks upstream releases; installs as `codexr` alongside the official build.

One rulebook for every AI coding agent. Your rules, context and skills apply to Claude Code, Cursor and Codex alike — and a different vendor's AI checks the work before you keep it.

The terminal for running multiple AI coding agents in parallel — Claude Code, Codex, Gemini CLI, opencode. A live status sidebar shows which session is working, done, or needs you, so you never miss the agent waiting on input. macOS, built on Tabby.

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.

Autonomous Web Agent Toolkit 2026 - AI Browser Automation for Testing & Scraping

Turn ChatGPT Web into a real coding agent on your own repos - read, edit, build, test, git, PRs. MCP server with OAuth 2.1, driven by GPT-5.6 Sol on ChatGPT Plus/Pro. No OpenAI API key, no per-token API bill.

MCP server that runs CLI AI coding agents (Claude Code, Codex, opencode, Antigravity) as sub-agents from any MCP client — background sessions, terminal dashboard, structured code review

Visualig-AI: All-in-one AI platform for Image-Generation, Video-Creation, and Coding-Assistance. Build custom models via a unified AI-Controller API.

Set up macOS for AI coding agents in one command. A curated Brewfile of CLI tools for Claude Code, Codex and Cursor — each with a reason to be there.

Turn Claude Code into a phase-aware, multi-team software factory: hard-gated pipeline, Clean Architecture + Effect standards, adversarial review, token discipline.

Self-hosted server and CLI for versioning and syncing coding-agent instructions and skills.

Deterministic fact-checker for AI coding agents — verify an agent's claims about its own work against the real code, git diff & logs. Local MCP server, cited verdicts, refuses to bluff.

终端版 DeepSeek Harness：流式输出的 AI 编码助手（REPL + 实时工具调用显示）

Ship gate for AI-written code in Claude Code. Four rungs — SAFE, TRUE, OBVIOUS, ALONE — enforced on every response: security at trust boundaries, handled errors, readable code, and nothing stale left behind.

Copyable Claude Code + GitHub Copilot configuration: AGENTS.md operating manual, CLAUDE.md, copilot-instructions, rules, skills, subagents, hooks, and a gated 7-stage SDLC (spec review, self code review, PR-bot triage). Token-efficient agentic coding you vendor into your repo and adapt with /adopt.