codex — independent software & tools
-
@axiomatic-labs/claudeflow
Claudeflow — AI-powered development toolkit for Claude Code and Codex. Skills, agents, hooks, and quality gates that ship production apps.
-
codeadd
CLI for Code Addiction framework - AI-powered development workflows
-
codeburn
See where your AI spend goes - by task, tool, model, and project
-
codelens-ai
Correlate AI coding agent token usage with git output to measure ROI
-
@fatihkan/badi
Workflow management CLI for Claude Code, Cursor, and Gemini CLI — 30 AI agents (incl. a virtual eng team, ads strategist, market/SEO/data analysts), 86 commands, OWASP security scans. Built for Anthropic Claude Opus and Sonnet.
-
gitnexus
Graph-powered code intelligence for AI agents. Index any codebase, query via MCP or CLI.
-
@hayasaka7/haya-pet
Generic AI CLI pet runtime foundation.
-
@hypabolic/hypa
Local context runtime for coding agents: compress shell output, query code, and proxy MCP tools
-
@intellectronica/ruler
Ruler — apply the same rules to all coding agents
-
@itradingai/aiwiki
Local Markdown knowledge base for AI assistants. Save what your AI reads, ask it later, and keep everything local.
-
kodelyth-ecc
Production-grade AI coding toolkit — 70 agents (incl. devil-mode adversarial crew), 194 skills, 97 commands, parallel multi-agent commands, semantic intent routing, self-learning memory, and a built-in MCP server (16 tools / 6 prompts / 377 resources) tha
-
llm-wiki-skills
Local-first CLI for installing host-specific LLM wiki skills.
-
loomlog
Local, cross-agent dev journal for Claude Code, Codex & Gemini CLI — passively weaves your AI coding sessions into an Obsidian-compatible vault.
-
@n24q02m/better-notion-mcp
Better MCP server for Notion API with composite tools optimized for AI agents
-
@openai/codex-sdk
TypeScript SDK for Codex APIs.
-
outlier-audit
AI coding audit, token tracker, and deskilling detector. Local-first CLI that measures AI authorship, carbon footprint, agent blast radius, and context waste — with warnings, not surveillance.
-
paqad-ai
Spec-driven development framework — AI agents that think before they type
-
@raishin/vanguard-frontier-agentic
Cloud and zero-trust agentic workflow marketplace for skills, agents, rules, MCP references, and compliance-aware architecture.
-
@sentropic/graphify
AI coding assistant skill (Claude Code, Codex, Gemini CLI, Kimi Code, GitHub Copilot CLI, Aider, OpenCode, OpenClaw) - turn any folder of code, docs, papers, images, or audio/video transcripts into a queryable knowledge graph
-
sneakoscope
Sneakoscope Codex: fast proof-first Codex trust layer with image-based Voxel TriWiki.
-
@surething/cockpit
The open-source Claude Code GUI — an IDE-like workbench for parallel AI coding. Drive Claude (default), Codex, DeepSeek, Kimi, or local Ollama in tabs. Terminal, browser & DB bubbles, code review. Self-host on a shared dev box — a seat for every teammate.
-
takt
Workflow control for AI coding agents
-
wendkeep
Automatically capture AI coding agent sessions (Claude Code, Codex) as local Markdown in your Obsidian vault — turn-by-turn history, cost/token tracking, auto-extracted decisions/bugs/learnings, rendered in the graph. Local-first.
-
agent-browser-workspace
Automate local Chrome browsing with isolated profiles, extract content, save pages to Markdown, and run searches using CLI tools and Node.js APIs.
-
oh-no-my-claudecode
Memory-grounded autonomous coding loops for Claude Code and Codex, with verifier gates, replay, evals, and tamper-evident receipts.
-
agentty
Agentic Development Environment (ADE) in your terminal
-
botference
One room, three minds: a multi-LLM planning council for your terminal — you, Claude Code, and Codex debate and ship an implementation plan.
-
paneflow
Local-first Rust/GPUI workspace for running coding agents side by side: real terminal panes, live status, worktree review, read-only MCP, and local orchestration.
-
nano-banana-2-ai
Deliver high-speed 4K text-to-image generation with 5-character consistency using the open-source Gemini 3.1 Flash Image model.
-
voriya-skills
Convert website capabilities into reusable, API-first AI skills with automated authentication and seamless integration for workflow automation.
-
story-skills
📚 Streamline story writing using markdown and AI agents to manage characters, plots, and chapters with structured YAML files.
-
NyxID
Connect AI agents to any API, anywhere. Securely. Open-source gateway that proxies requests, injects credentials automatically, punches through NAT to reach localhost services, and wraps REST APIs as MCP tools. Per-agent isolation. Never expose a raw key.
-
longhouse
Self-hosted mission control for CLI coding agents — one searchable timeline for Claude Code, Codex & more, across your machines, with live remote control.
-
ae
ae — agentic engineering: run multiple AI coding agents side-by-side in tmux focus on simplicity
-
AIDOCS
AIDOCS — AI Doctrine Orchestrator, Control & Security.
-
claude-compaction-viewer
View and analyze Claude Code conversation history and compaction events with a TUI and CLI tool for clear session insights.
-
vibe-coding
Capture AI-driven coding workflows by describing needs in natural language and iterating to generate and refine code automatically.
-
claude-terminal
Manage multiple Claude Code sessions in a single terminal with tabs, session persistence, multi-project workspaces, and git worktree support.
-
google-ads-mcp
Manage Google Ads accounts via MCP. Execute GAQL reads and secure two-phase mutations with full v24 API coverage for reliable ad campaign control.
-
Secure-Agent-Launcher
Block AI agent access to sensitive macOS paths and log all actions to protect private data during command execution.
-
Claude-Code-Agent-Monitor
Monitor and visualize Claude Code agent sessions, tool use, and orchestration in real-time with a Node.js and React dashboard integrated via native hooks.
-
ClaudeUsageBar
📊 Track your Claude.ai usage seamlessly with this lightweight macOS menu bar app, providing real-time updates and notifications.
-
claude-tts
Convert Claude Code responses to speech using various TTS providers with local fallback for seamless audio output across platforms.
-
obsidian-headless
Sync Obsidian vaults from the command line using a headless client, enabling automated and continuous sync without the desktop app.
-
axon
Self-hosted web crawling and RAG pipeline with MCP tooling for scrape, crawl, ingest, embed, query, and ask workflows.
-
Agent-Skills
Governed skill foundry and Skills SDK for Codex/AI coding agents: author, validate, evaluate, and sync runtime projections through ask.
-
mfa-servicenow-mcp
A lean, developer-focused MCP for ServiceNow — explore flows, portals, and tables from your LLM.
-
gemini_cli_skill
🚀 Enhance Claude Code with Gemini CLI for better code generation, reviews, testing, documentation, and architecture analysis.
-
hive
A terminal TUI for managing multiple AI coding agent sessions across projects — Claude, Codex, Gemini, GitHub Copilot, Aider, OpenCode, and more.
-
tokentop
Terminal dashboard for monitoring OpenRouter and Codex API usage in real time
-
claude-skills
Provide and maintain a community-driven collection of standardized Agent Skills for Claude AI using the SKILL.md format
-
agent-skills
Provide structured markdown guides to teach AI assistants how to complete complex React Native engineering tasks efficiently.
-
agent-commands
🚀 Automate project handoffs and resumption with these command files and skills, enhancing workflow continuity across your development tasks.
-
BorisChernyClaudeMarkdown
Provide a Claude-inspired Markdown template adapted from research to streamline note-taking and idea organization.
-
AgentsCommander
Run multiple CLI coding agents (Claude Code, Codex, Gemini, OpenCode) as a coordinated team, on a Loop. Local-first, file-based coordination, full PTY, no telemetry.
-
agentchattr
Facilitate real-time chat and task coordination between AI coding agents and humans using a local server with multi-agent support.
-
vibe-engineering
Deliver and enforce engineering discipline with 38 proven skills and a CLI designed for real-world multi-agent CI/CD workflows.
-
sixtyfour-skill
Enable AI agents to access live web data for in-depth people and company research, lead enrichment, contact discovery, and automated workflows.
-
claude-code-openai-wrapper
🚀 Use the Claude Code OpenAI wrapper to seamlessly integrate Claude Code with any OpenAI client library for enhanced performance and features.
-
codeflare
The enterprise agentic engine. Governed engineering agents that build, test, review, and operate inside your own estate. Spec-driven, attributed, and encrypted.