Bring Your AI

No-secret smoke payloads for agent buyers and directory reviewers:

- examples/agent-discovery/directory-review-proof.json- single machine-readable proof bundle for directory reviewers and agent buyers.
- examples/agent-discovery/mcp-tools-call.json- JSON-RPC tools/list payload for the no-data remote MCP endpoint.
- examples/agent-discovery/quote-request.json- quote request shape for the local CLI lifetime license.
- examples/agent-discovery/checkout-request.json- checkout handoff request shape with placeholder return URLs.

bringyour sync export --root ~/.codex --out ./bya-codex-sync bringyour sync plan --in ./bya-codex-sync --root ~/.codex bringyour sync apply --in ./bya-codex-sync --root ~/.codex

The remote MCP server must not receive private harness data. Actual migration and sync work happens through the local CLI or local MCP server. The hosted endpoint exists for discovery, preview, and install handoff.

This repo also carries installable, no-secret public artifacts for auditing migrated Codex setups:

- .codex-plugin/plugin.json- Codex plugin manifest that exposes the migration-auditor skill as an installable plugin.
- skills/bringyour-migration-auditor/SKILL.md- Codex skill for checking AGENTS.md/CLAUDE.md scope, hooks, MCP config, skills, secrets, and validation notes after a migration.
- agents/harness-migration-auditor.toml- Codex subagent config for the same read-only audit path.
- .github/workflows/agent-surface-proof.yml- public CI proof that the hosted discovery, commerce, and MCP handoff surfaces stay callable without secrets.
- examples/github-actions/bringyour-agent-surface-check.yml- reusable workflow sample for teams that want a scheduled discovery, MCP, quote, and checkout handoff check before relying on Bring Your AI during a Claude Code to Codex move.
- examples/github-actions/codex-import-audit.yml- reusable workflow sample for teams that want a Codex import audit record before allowing Codex to edit source after a Claude Code migration.
- examples/github-actions/claude-codex-continuity-check.yml- pull-request workflow sample that inventories AGENTS.md, CLAUDE.md, .claude, .codex, and MCP config changes, then writes Codex validation notes before source edits.
- examples/github-actions/mcp-config-migration-check.yml- pull-request workflow sample that inventories MCP config surfaces, verifies the public no-data checklist, and writes target-side MCP validation notes.
- examples/agent-discovery/*.json- no-secret proof and payload examples for directory review, MCP tools/list, quote, and checkout smoke checks.
- examples/codex-import-audit/sample-report.json- machine-readable example audit report for Claude Code to Codex import review.
- examples/mcp-config-migration/checklist.json- agent-readable MCP config migration checklist that preserves the no-data remote boundary.

Directory reviewers can use the latestagent-surface-proofworkflow run as public evidence that the MCP endpoint, agent manifests, commerce surfaces, quote endpoint, and checkout handoff are live without receiving private harness data.

This is a web browser that enables your coding agent, such as Claude Code, to visit websites on your behalf and assist you in identifying bugs or creating UI test cases.

Execute any LLM-generated code in the YepCode secure and scalable sandbox environment and create your own MCP tools using JavaScript or Python, with full support for NPM and PyPI packages

Agent-native developer Q&A API with MCP + A2A endpoints for citations, job pickup, and answer submission.

MCP bridge that lets Claude Code delegate heavy tasks to the Antigravity CLI (agy) — purpose-built tools, model routing with fallback, session continuity, and output truncation to save Claude's context and tokens.

Structured .aide spec files that give AI agents progressive disclosure into your codebase architecture. 6 MCP tools, 8 slash commands, TUI wizard, multi-IDE support.

An MCP server for real-time user intervention in AI-assisted development workflows.

Embeds intelligent guidance into AI workflows to organize development and ensure quality.

Hosted MCP server and coordination layer for AI coding agents — live API contracts, database schema, frontend/backend mismatch detection, and shared handoff tickets for Claude Code, Cursor, Codex, and Lovable.

Open-source AI coding stack — bundled MCP servers, agent runtime, and developer tooling for shipping AI-native dev tools.

Local agent workbench bundling OpenHands, Goose, Aider, and ashlrcode against one local LLM, with ashlr-plugin MCP servers pre-wired.

Async Parallel Antigravity for Codex & Claude Code