開源 · MIT 授權 · 使用您自己的 API 金鑰運行

別再把呼叫哪個模型寫死在程式碼裡。

兩個核心概念：策略決定每次呼叫由哪個模型處理；工作流程將這些決策串聯成完整的處理管線。開源、MIT 授權，使用您自己的供應商 API 金鑰運行，無需信任任何中間層。

策略 · 基本單元

選擇模型的是策略，不是您。

把 model="gpt-5.5" 寫死在程式碼裡，它很快就會過時。新模型每週發布，價格持續變動，部分請求需要工具呼叫能力、圖像理解，或只是需要成本更低的選項。策略宣告資格條件與排名方式，針對每次請求選出合適的模型，並在失敗時執行備援。您傳入的是規則，而非一個名稱。

每次決策都會留下可重放的追蹤紀錄：相同的策略、輸入與模型目錄，可在主機或您自己的機器上精確還原決策過程。沒有任何路由發生在暗處。

組合路由呼叫

工作流程對整個任務進行路由。

真實的功能不是單次呼叫。一個客服回覆包含分類 → 起草 → 審核：每個步驟需要不同的模型，審核環節可以在內容送出前拒絕它，各步驟可以並行展開再匯合。一條策略路由一次呼叫；工作流程路由整個處理管線，並產生一份完整的統一追蹤紀錄。

低成本分類，達到品質基線後起草，再經強力 no-log 審核——可在送出前拒絕內容。

查看 flow_ir

flow.support-ticket.json

["flow", {
  "u": {"kind": "input"},
  "t": {"kind": "llm", "system": "Classify the ticket and extract the account id as JSON.",
    "policy": ["policy", ["and", ["meets_req"], ["not", ["is", "disabled"]], ["has_cap", "supports_json_mode"]],
      ["neg", ["normalize", ["field", "price_out"]]], ["argmax"], ["id"], ["always", {"action": "next_candidate"}]],
    "inputs": ["u"]},
  "d": {"kind": "llm", "system": "Write a reply using the ticket and the triage.",
    "policy": ["policy", ["and", ["meets_req"], ["not", ["is", "disabled"]], ["cmp", "bench_intelligence", "ge", 0.55]],
      ["neg", ["normalize", ["field", "price_out"]]], ["argmax"], ["id"], ["always", {"action": "next_candidate"}]],
    "inputs": ["u", "t"], "template": "Ticket:\n$1\n\nTriage:\n$2"},
  "g": {"kind": "llm", "system": "Check brand voice, PII, refund limits. Refuse if any fail.",
    "policy": ["policy", ["and", ["meets_req"], ["not", ["is", "disabled"]], ["is", "no_log"]],
      ["field", "bench_intelligence"], ["argmax"], ["id"], ["always", {"action": "next_candidate"}]],
    "inputs": ["d"]},
  "out": {"kind": "output", "inputs": ["g"]}
}]

低成本起草，強力批評，再改寫。在預算內實現品質躍升。

查看 flow_ir

flow.draft-critique-revise.json

["flow", {
  "u": {"kind": "input"},
  "d": {"kind": "llm", "system": "Draft an answer.",
    "policy": ["policy", ["and", ["meets_req"], ["not", ["is", "disabled"]]],
      ["neg", ["normalize", ["field", "price_out"]]], ["argmax"], ["id"], ["always", {"action": "next_candidate"}]],
    "inputs": ["u"]},
  "c": {"kind": "llm", "system": "Critique the draft: list concrete flaws and gaps.",
    "policy": ["policy", ["and", ["meets_req"], ["not", ["is", "disabled"]]],
      ["field", "bench_intelligence"], ["argmax"], ["id"], ["always", {"action": "next_candidate"}]],
    "inputs": ["d"]},
  "r": {"kind": "llm", "system": "Rewrite the answer, fixing every point in the critique.",
    "policy": ["policy", ["and", ["meets_req"], ["not", ["is", "disabled"]]],
      ["field", "bench_intelligence"], ["argmax"], ["id"], ["always", {"action": "next_candidate"}]],
    "inputs": ["u", "d", "c"], "template": "Question:\n$1\n\nDraft:\n$2\n\nCritique:\n$3"},
  "out": {"kind": "output", "inputs": ["r"]}
}]

從同一強力策略中進行 N 次隨機抽樣（sample 將它們分散至排名靠前的候選模型），再由裁判擇優選出結果。

查看 flow_ir

flow.best-of-n.json

["flow", {
  "u": {"kind": "input"},
  "n1": {"kind": "llm", "system": "Answer the question.",
    "policy": ["policy", ["and", ["meets_req"], ["not", ["is", "disabled"]]],
      ["field", "bench_intelligence"], ["sample", 0.5], ["id"], ["always", {"action": "next_candidate"}]],
    "inputs": ["u"]},
  "n2": {"kind": "llm", "system": "Answer the question.",
    "policy": ["policy", ["and", ["meets_req"], ["not", ["is", "disabled"]]],
      ["field", "bench_intelligence"], ["sample", 0.5], ["id"], ["always", {"action": "next_candidate"}]],
    "inputs": ["u"]},
  "n3": {"kind": "llm", "system": "Answer the question.",
    "policy": ["policy", ["and", ["meets_req"], ["not", ["is", "disabled"]]],
      ["field", "bench_intelligence"], ["sample", 0.5], ["id"], ["always", {"action": "next_candidate"}]],
    "inputs": ["u"]},
  "j": {"kind": "llm", "system": "Pick the single best candidate; return it verbatim.",
    "policy": ["policy", ["and", ["meets_req"], ["not", ["is", "disabled"]]],
      ["field", "bench_intelligence"], ["argmax"], ["id"], ["always", {"action": "next_candidate"}]],
    "inputs": ["n1", "n2", "n3"], "template": "A:\n$1\n\nB:\n$2\n\nC:\n$3"},
  "out": {"kind": "output", "inputs": ["j"]}
}]

三個依族系固定的模型並行起草，第四個模型綜合出更優的單一答案。

查看 flow_ir

flow.panel.json

["flow", {
  "u": {"kind": "input"},
  "a": {"kind": "llm", "system": "Draft an answer.",
    "policy": ["policy", ["and", ["meets_req"], ["not", ["is", "disabled"]], ["family_eq", "gemini-3.1-pro-preview"]],
      ["zero"], ["argmax"], ["id"], ["always", {"action": "next_candidate"}]], "inputs": ["u"]},
  "b": {"kind": "llm", "system": "Draft an answer.",
    "policy": ["policy", ["and", ["meets_req"], ["not", ["is", "disabled"]], ["family_eq", "claude-opus-4-8"]],
      ["zero"], ["argmax"], ["id"], ["always", {"action": "next_candidate"}]], "inputs": ["u"]},
  "c": {"kind": "llm", "system": "Draft an answer.",
    "policy": ["policy", ["and", ["meets_req"], ["not", ["is", "disabled"]], ["family_eq", "deepseek-v4-flash"]],
      ["zero"], ["argmax"], ["id"], ["always", {"action": "next_candidate"}]], "inputs": ["u"]},
  "f": {"kind": "llm", "system": "Synthesize the single best answer from the drafts.",
    "policy": ["policy", ["and", ["meets_req"], ["not", ["is", "disabled"]]],
      ["add", ["scale", 0.7, ["normalize", ["field", "bench_intelligence"]]],
             ["scale", 0.3, ["neg", ["normalize", ["field", "price_in"]]]]],
      ["argmax"], ["id"], ["always", {"action": "next_candidate"}]],
    "inputs": ["a", "b", "c"]},
  "out": {"kind": "output", "inputs": ["f"]}
}]

推理模型與程式碼模型在不同篩選條件下並行運行，再經合併步驟融合輸出，適用於推理與程式碼混合的任務。

查看 flow_ir

flow.specialist-split.json

["flow", {
  "u": {"kind": "input"},
  "rz": {"kind": "llm", "system": "Reason through the problem step by step.",
    "policy": ["policy", ["and", ["meets_req"], ["not", ["is", "disabled"]], ["is", "cap_reasoning"]],
      ["field", "bench_intelligence"], ["argmax"], ["id"], ["always", {"action": "next_candidate"}]], "inputs": ["u"]},
  "cd": {"kind": "llm", "system": "Produce any code the problem needs.",
    "policy": ["policy", ["and", ["meets_req"], ["not", ["is", "disabled"]], ["cmp", "bench_coding_rank", "le", 5]],
      ["add", ["scale", 0.7, ["normalize", ["field", "bench_coding"]]],
             ["scale", 0.3, ["neg", ["normalize", ["field", "price_out"]]]]],
      ["argmax"], ["id"], ["always", {"action": "next_candidate"}]], "inputs": ["u"]},
  "m": {"kind": "llm", "system": "Merge the reasoning and the code into one answer.",
    "policy": ["policy", ["and", ["meets_req"], ["not", ["is", "disabled"]]],
      ["add", ["scale", 0.6, ["normalize", ["field", "bench_intelligence"]]],
             ["scale", 0.4, ["neg", ["normalize", ["field", "price_out"]]]]],
      ["argmax"], ["id"], ["always", {"action": "next_candidate"}]],
    "inputs": ["rz", "cd"], "template": "Reasoning:\n$1\n\nCode:\n$2"},
  "out": {"kind": "output", "inputs": ["m"]}
}]

橫向滑動查看圖示 →

在文件中查看所有工作流程模式 →

開始使用

兩個儲存庫，MIT 授權，現在即可使用。

複製 Host 與 Engine 儲存庫，設定您的供應商帳戶，今天就能以自己的 API 金鑰開始路由。無加價，無隱藏路由邏輯。

unhardcoded

參考主機實作：接收策略並產生指紋，使用您的供應商 API 金鑰路由呼叫，並寫入追蹤紀錄。

查看儲存庫 →快速開始 →

unhardcoded-engine

policy_ir 與 flow_ir 規格、參考直譯器，以及其他實作用於自我驗證的一致性向量。

查看儲存庫 →policy_ir →

MIT 授權供應商中立可攜式 IR 可自行託管

不想自己運行主機？託管版本（含託管目錄、追蹤紀錄儲存與團隊管控功能）即將上線。

或寄送電子郵件至 hello@unhardcoded.com 加入。

不發垃圾郵件。託管版就緒時僅發一封通知郵件。