Production-grade vibe coding framework with specs, architecture, AI agents, testing, security, code review, CI/CD, and battle-tested workflows — from idea to production.
-
Updated
Oct 6, 2026 - JavaScript
Production-grade vibe coding framework with specs, architecture, AI agents, testing, security, code review, CI/CD, and battle-tested workflows — from idea to production.
Veyra — Engineering Intelligence for Coding Agents. Persistent engineering memory + optional AST code intelligence (Dual-Brain) for DeepSeek Harness. Zero runtime npm dependencies.
Local-first control room for teams of Claude Code agents: multi-agent orchestration with memory, write zones, permission modes, per-turn git commits and an Electron strategy-map UI.
Your agent writes the code. hyperfocus makes sure you still understand it: a quiz about your coding agent's live changes, in the terminal or VS Code, while it works.
Local-first browser cockpit for AI coding agents (Claude Code, Codex, Gemini) and shells: floating PTY windows, git worktree per agent, approval alerts, sessions that survive restarts.
Journal runs your AI coding agents side by side and gives each new session the project knowledge you've reviewed, so agents stop rediscovering the same context.
Keeps AI coding agents inside your project's rules: lanes, layer rules, protected paths and proof before finish, enforced by Claude Code hooks and in CI
Close the loop from intent to delivery. Planning, design, review, diagram, and delivery skills for Claude Code, Codex, and Cursor, plus the deterministic planr CLI. Specs, stories, and tasks live in your repository under .planr/.
Working rules and skills for AI coding agents, layered as base, modifiers, person and project
DeepSeek Harness (DSH) 插件精选目录 — 14 类 280+ 个社区插件,覆盖 MCP / Skill / TUI / 多 Agent / 上下文记忆 / UI 皮肤,点链接直达仓库。Curated directory of dsh plugins for DeepSeek Harness.
MCP server that dispatches and supervises parallel Codex CLI workers, one isolated Git worktree each, with a persisted work state machine.
On-device guardrails for AI coding agents. Hooks check prompts, file reads, shell commands, writes, web fetches and MCP calls before they run and scan tool output after. Validated end to end on Claude Code; Codex CLI, Copilot CLI, Cursor and Gemini CLI adapters tested on fixtures. Stdio MCP proxy for hosts without hooks. MIT.
Failure intelligence and shared debugging memory for AI coding agents
AgentDeck: one local GUI to configure every AI coding agent. Tune behavior, permissions, token usage and cost, skills, subagents, MCP servers and hooks for Claude Code, Codex CLI, Gemini CLI, Cursor, OpenCode and 16 more. Zero dependencies.
Local mail between coding-agent sessions on one machine: an MCP server and CLI on Bun and SQLite.
The most comprehensive AI-curated list of DeepSeek Harness (DSH) plugins - 190+ plugins, 12 categories, updated hourly by AI.
Composable agent skills for Matt Pocock workflows: thin PM coordination, focused engineering checks, and evidence-based delivery.
Self-hosted AI agent gateway for Slack, with Microsoft Teams and Google Chat in Beta. Run Claude Code or OpenAI Codex in a container per conversation, with MCP integrations, persistent memory, skills and scheduled automation. Source-available fair-code.
Build standalone Claude Code skills that solve real problems with simple, drop-in folders for any codebase, any OS
From web terminals for your coding agents to a self-running agent company: Claude Code and Codex in parallel git worktrees, a job board they pick work from, and one agent that runs the board from a goal.
To associate your repository with the coding-agents topic, visit your repo's landing page and select "manage topics."