怀疑，直到剩下的确定。

🔭 兄弟项目：Asker — 今天的AI回答，这个人问。

提问者学会提出*最尖锐的问题以理解主题; 笛卡尔学会了怀疑**，直到剩下的事变得确定。一体的两半 观点：正确的问题胜过自信的答案。 → https://github.com/pranjalbhatia710/the-asker

🪶 登陆页→  ·  descartes --epigraph，这是他本人的一个随口想法。

一个MCP服务器在提示时，怀疑计划中的每一个决定，也怀疑自己的决定 怀疑并回答它们——每个答案都基于真实证据——不断反复 直到计划停止产生新的负重疑虑。然后它会交还给 精炼的计划加上只有你能做的少数决定。

重点是：没有未经审视的假设能影响作品，所以幻觉也没有 藏身的空间。

---

循环

在一个提示中，笛卡尔运行递归笛卡尔怀疑：

1. 起草计划/决策。
2. 怀疑每一个承重决策（每个疑点中有11个怀疑操作员）。
3. 怀疑怀疑——修剪那些琐碎和人为制造的疑虑。

Descartes

doubt, until what remains is certain.

🔭 Sibling project: The Asker — today’s AI answers, this one asks.

The Asker learns to ask the sharpest questions to understand a subject; Descartes learns to doubt until what remains is certain. Two halves of one idea: the right question beats the confident answer. → https://github.com/pranjalbhatia710/the-asker

🪶 Landing page →  ·  descartes --epigraph for a passing thought from the man himself.

An MCP server that, on a prompt, doubts every decision in a plan, doubts its own doubts, and answers them — grounding every answer in real evidence — iterating until the plan stops producing new load-bearing doubts. Then it hands back a refined plan plus the few decisions only you can make.

The point: no unexamined assumption reaches the work, so hallucination has no room to hide.

---

The loop

On a prompt, Descartes runs recursive Cartesian doubt:

1. Draft the plan / decisions.
2. Doubt every load-bearing decision (one of 11 doubt operators per doubt).
3. Doubt the doubts — prune the trivial and manufactured ones.
4. Answer each surviving doubt only from real evidence:
   • code doubts → resolved from the context you pass in,
   • world doubts → resolved via Exa (cited, confidence-scored),
   • ungroundable → marked NEEDS_HUMAN.
5. Doubt the answer — recurse: each settled answer is itself doubted (the question behind the question), spawning the next layer of doubts, bounded by depth and a global doubt budget.
6. Bank it — every grounded finding accumulates into a knowledge base that feeds the next round of doubting and the final plan.
7. Revise the plan with what survived, and repeat from step 2.

The output is therefore a doubt tree (each entry carries depth + parent), not a flat list, plus a knowledge_base of accumulated facts.

Stopping rule: the loop stops the moment a full pass produces no new load-bearing doubt — that is convergence. It might be pass 3 or pass 9. 20 is a hard ceiling, never a target, and recursion is bounded by DESCARTES_MAX_DEPTH (default 3) and DESCARTES_DOUBT_BUDGET (default 64). It never manufactures doubt to keep going.

Grounding rule: every answer resolves against real evidence or becomes a question for you. Low-confidence Exa is never asserted. 20 rounds of self-answered, ungrounded doubt would be 20 rounds of confident hallucination — so that is forbidden by construction.

---

Two engines (auto-selected)

| If you set… | Descartes runs… |