Open-source control plane for Codex projects: Git-backed context, visible agent progress, scoped MCP access, resumable work, and safe handoffs.

Pack and restore Codex Desktop across Windows and Mac: conversations, projects, skills, plugins, and reinstall backup.

Senior Architect Agent: AI architecture skill for existing system mapping, software architecture documentation, Mermaid diagrams, and AI agent handoff.

SourceryKit — counterspell for hallucinating agents. Python SDK that breaks the illusion on every tool call, API response, and MCP handoff before bad outputs propagate.

A minimal CLI to stash, move, and reuse project context, skills, and agent rules for AI coding agents.

Local-first CLI to read, compare, and hand off sessions across Claude Code, Codex, Gemini, and Cursor agents. Checkpoints, cross-agent messaging, zero npm deps.

Not a framework. A file format for agent-to-agent handoffs — provenance, parallel safety, and human visibility by design. Model-agnostic. Framework-agnostic. Open spec, MPL-2.0.

Your Claude Code & Cowork conversations are sitting on Anthropic's mercy — until they're not. claude-backup exports everything to local Markdown, and rescue bundles it for handoff to ChatGPT, Cursor, or any AI agent when you need a Plan B. Lazy install: paste PROMPT.md into any AI

Cross-tool memory for AI agents. Stitch context across Cursor, Claude Code, Codex, Gemini CLI, Windsurf, Copilot, and 9+ AI tools. Preserves decisions, failed experiments & warnings across sessions. Zero dependencies, MCP + instruction files, BM25 relevance search. Never re-explain your work.

Local-first context bridge and CC Switch installable MCP handoff integration for coding agents.

Repo-local project memory and handoff layer for direct AI coding agents, with validation evidence and sandbox-tolerant Autorunne state write-backs.

AI architecture proposal skill for turning raw ideas into reviewable architecture maps, assumptions, risks, and handoff notes.

Local-first multi-agent orchestration: run tasks across CLI agents and API models, pass work between agents when one dies. Sessions, workflows, human-in-the-loop.

Enable AI agents to share memory across tools and avoid repeating work when switching between tasks or platforms.

A cross-tool handoff skill for Claude Code and Codex CLI: generates context handoff docs, updates STATUS.md, snapshots commits, and prints next-session prompts.

Git + Markdown handoff protocol for Claude Code, Codex, Cursor, Aider, and other coding agents.

AHA (Aligned Human-AI): /aha is a single-door alignment kit with memory, typed questions, premortem critique, eval rubric, handoff contract, return-packet debrief, and standalone quick checks. For Cursor and Claude Code.

AI documentation architecture skill for clear, non-duplicated, source-of-truth driven, token-efficient project documentation.

Codex and Claude Code skills for evidence-backed conversation transfer, AI agent checkpoints, and local project Bridge Packets.

Enforced agent-to-agent handoff protocol. Zero-dependency POSIX shell. Drop cairn/ into any repo.