cross-model

Own your AI memory — import ChatGPT, Claude and Gemini exports, see what each AI knows about you. Checkpoint/restore and cross-model continuity for agents.

交接 Skill（Jiaojie）：跨窗口、跨模型、跨设备、跨语言的 AI 上下文交接工具。换窗口，不失忆；换模型，不重来。Open-source AI context handoff.

Building your AI organization: shared records and handoffs, plus a merge gate for AI-written code with signed, replayable attestation. Works with Claude Code, Codex, Cursor, and Gemini CLI.

Cross-model shared memory for AI agents. One canon every model reads. Free OSS via pipx install memee. memee.eu hosts the Team edition with shared scope, SSO, audit log.

CROCODIL: Cross-Model Code Editing with LLMs

A local harness for agent teams on Claude Code and Codex CLI: only what they prove counts as done. Waves and lanes split the work, reviewers from another model family judge it, councils keep the dissent that lost, typed decisions with Jev are measured before they are trusted, and approvals are bound to the bytes they approved. No model calls.

Multi-perspective code review council for Claude Code. 3 advisors by default, 10 agents in deep mode (Opus + Codex). Evidence chains, adversarial self-test, dual-path verdict. Based on Karpathy's LLM Council.

Cross-model delegation and adversarial review for CLI coding agents: one lead, six runtime adapters, and no change merges reviewed only by its own model family.

CSP-1: Portable Conversational Identity — A User-Owned Protocol for Preserving AI Relational Style Across Models

An independent second model reviews the diff your AI agent wrote and blocks turn completion until issues are addressed. Local, cross-model, zero-config.

Run your own agent on other AI model CLIs (grok/codex/claude) as independent second opinions — a Claude Code plugin: deterministic multi-model adversarial arena + live steerable review. No API.

Decompose a corpus of existing projects into reusable 3-axis parts (their genome), then recombine/mutate/transplant them into auditable new-project seeds. Runtime-neutral meta-methodology + recreate skill; registry-based rerun avoidance, conditional cross-model integration, stdlib-only.

Pi + rdog cross-model Calculator GUI eval runner: 3 frozen cases, 7 model configs, strict timeline matching (16/18 strict baseline)

Claude Code and Codex skill for blind, independent review by a second model, with a citation of what it was not shown. Four patterns - red team, second opinion, verify and panel - on Codex or opencode, and a record of what each run was told and what it was not. A free tool by DBHQ.

AgentReview sends changes to an independent reviewer

Brainstorm product ideas and have a different model grade them. Whoever proposed an idea never decides whether it survives.

Model-neutral persistent memory and optional encrypted agent messaging. Native Python/TypeScript endpoints, existing MCP memory tools, signed delivery and recovery. Apache-2.0; alpha.

Independent interpretability research (DRAFT — not yet run): is an inferred character trait stored, or reconstructed from the scene on demand? Across model scale + a scene-masked direction probe

The settlement layer of the AI economy — universal wallet, FLX currency, cross-model payments