0xwilliamortiz
Featured
openclaude-improved
OpenClaude is an open-source CLI coding agent that runs on any platform and supports a wide range of LLM providers, offering the same tools and workflows as Claude Code.
AI repository intelligence
FR-AI / ANALYSISWhy it is worth attention
It abstracts the backend away so one portable agent script runs on Codex, Claude, or OpenCode, and adds production-grade features (verification loops, cron scheduling, org memory) that Claude Code alone lacks.
Who it is for
- Developers using Claude Code who want to offload heavy workloads to a Codex subscription
- Teams building multi-step agent workflows that need verification and iteration
- Engineers automating recurring tasks (e.g., nightly builds, monitoring) with agent fleets
- Researchers experimenting with multi-agent systems and structured agent memory
Use cases
- Automated code review with adversarial critique loops until all criteria pass
- Scheduled data ingestion and processing tasks (e.g., digest every 30 minutes)
- Building a persistent research desk of agents that remember and summarize findings
- Running the same build script across different backends to compare cost and performance
Strengths
- Runs unmodified Claude Code workflows on Codex subscription, saving Claude quota
- Supports multiple backends (Codex, Claude, OpenCode) with simple routing configuration
- Includes a built-in loop mechanism with separate verifier agents for quality control
- Provides OS-level sandboxing on Codex (macOS Seatbelt) for safe untrusted content
Considerations
- Orgs are experimental and require supervision; not yet stable for unattended production use
- OpenCode has no OS sandbox and may collide under heavy concurrency
- OS sandbox validated only on macOS; pre-1.0 release pinned to specific backend versions
README quick start
Workflow 🌟 Loop 🌟 Scheduler 🌟 Org (experimental)
ultracodex
Run Claude Code workflow scripts, unmodified, on your Codex subscription — and on OpenCode. Then go further than running them: loop them until a skeptical verifier approves, schedule them with cron doing the waking, or stand up a permanent organization of agents that remembers. Your Claude session writes the script and reads the verified result; the heavy lifting lands on the subscription you aren't rationing.
The idea underneath: the agent is a unit of programming. You write ordinary JavaScript and call an agent like a function — await agent(prompt, { schema }) hands back a structured result. ultracodex abstracts the backend away, so one script runs on any of the three it supports: Codex, Claude, or OpenCode. Workflows, loops, schedules, and orgs are what you build once the agent is something you can program with.
Getting started is quick because your agent does the learning: a bundled skill teaches your coding agent how to drive ultracodex, so you describe the task and your agent writes and runs the workflow. One command installs it for Claude Code (ultracodex sync-skills); docs/skills.md covers codex, opencode, and any other agent. Given only that skill, a fresh agent ran all four pillars across Codex, Claude, and OpenCode (the numbers).
Quickstart
Prerequisites: Node ≥ 20, the Codex CLI installed and authenticated (codex login; tested against codex-cli 0.144.0), and — for the prompt-driven flow below — a driving agent, typically Claude Code. No driving agent handy? Skip to driving from the CLI. OpenCode is optional (tested against 1.17.18) — one [route] line turns it on.
npm install -g ultracodex # or: pnpm add -g ultracodex
ultracodex doctor # checks node, codex, auth, config — with actionable next steps
ultracodex sync-skills # teaches Claude Code (and opencode) the whole contract
Then, in Claude Code, the prompt is just the task:
Write a haiku that survives three rounds of adversarial critique. Run it with ultracodex.
Claude auth
Description
Run Claude Code workflow scripts, unmodified, on the OpenAI Codex CLI — fable plans, codex executes, fable verifies. Parallel agent fleets, builder–verifier loops, token budgets, full-screen TUI.
Related repositories
Similar projects matched by category, topics, and programming language.
S40911120
Featured
recensa
Recensa is a self-hosted web viewer that indexes Claude Code session transcripts into a local SQLite database, enabling full-text search, replay, and audit of all past agent conversations without uploading data anywhere.
7-e1even
Featured
learn-agent
A collection of notes on building coding agents, derived from the production development of the desktop agent Reina, with each mechanism simplified into a zero-dependency, single-file Node.js demo.