relay
MCP Serverdbisina/relay
Relay is a vendor-neutral AI coding agent orchestrator and daemon that rotates coding tasks across multiple AI providers using signed continuation contracts.
29 5Apache-2.0Updated 2026-08-12
83
GreatOverview
Relay solves context fragmentation and usage limits by letting developers seamlessly hand off in-progress coding tasks from one AI agent, account, or provider to another without losing state. Operating as a Go daemon with a Rust desktop app and TUI, it detects running local agent sessions, captures their state into HMAC-signed continuation contracts, and provisions fresh agents to resume work effortlessly.
Capabilities
- ▸Detects running local AI coding agent processes and transcripts
- ▸Generates HMAC-signed continuation contracts carrying intent, plan, and in-flight code
- ▸Performs automatic account and provider failover based on live burn-rate tracking
- ▸Provides built-in secret redaction across all cross-boundary communications
- ▸Exposes an MCP server for integration with other MCP clients like Claude Desktop or Cursor
- ▸Maintains a knowledge and code graph with FTS5 search capabilities
Best for
Switching AI coding agents mid-task when usage quotas or rate limits are hit., Rotating between multiple subscription accounts across different providers without losing context., Orchestrating multi-agent DAG pipelines for complex software development tasks., Auditing and reviewing what each AI agent modified using time-machine git snapshots and signed contracts.
Works with
Claude CodeCodexChatGPTGemini CLICursorGitHub CopilotOpenCode
Evoa Score breakdown= Σ (score × weight)
83Task usefulness20%100 → +20.0
実タスクにどれだけ役立つか（機能の豊富さ・用途の明確さ）。 — AIによるcapabilities/use-cases解析
Code quality15%90 → +13.5
実装・指示の品質。 — AIによるSKILL.md/README解析
Maintenance15%100 → +15.0
リポジトリがどれだけ活発に保守されているか。 — GitHub 最終push日時の新しさ
Documentation12%41 → +4.9
ドキュメントの充実度・分かりやすさ。 — README/独自要約の情報量
Security15%80 → +12.0
危険・不審な挙動が無いか。 — AIによるセキュリティレビュー
Originality10%95 → +9.5
ありふれたラッパーではない独自性。 — AIによる独自性判定
Popularity8%40 → +3.2
コミュニティの採用度。 — GitHub Stars/Forks（対数スケール）
Compatibility5%100 → +5.0
対応AIエージェントの広さ。 — AIによる対応エージェント判定
Weighted total83.1 / 100
ライセンス不明/制限あり（Red）のSkillは総合スコアに0.85倍の補正を適用します。 ランキングはこのScoreのみで決まり、広告で変わりません。 算出方法の詳細 →
Security considerations
Includes an internal secret redactor that strips common API keys, tokens, and sensitive patterns before data crosses boundaries or external provider APIs.
Categories
Summary and analysis are original content generated by AI Skills Rank. The skill's source text is not reproduced here — view it on the linked repository.