心迹专属 AI 伴写伙伴 AI WRITING COMPANION

翻阅旧日片羽,聊聊当下所想。

住在摘录本里的灵感伴侣。它懂你的文风与习惯,为你打捞旧日笔记、提炼长文总结、推敲润色字句,也随时带来今日思考与灵感解答。 An AI companion living inside your notebook. It understands your voice, retrieves forgotten thoughts, refines your writing, and brings daily clarity to your thinking.

本地优先 · 数据在手 Local-First · Full Ownership
建议卡片 · 自由采纳 Proposal Cards · You Decide
专属记忆 · 懂你偏好 Personal Memory · Learns Your Voice
开放兼容 · 支持本地模型 Open API · Offline Model Support
DAILY COMPANIONSHIP

贴合日常记录的伴写场景 Everyday Companion Scenarios

不是漂浮在空中的通用聊天,而是扎根在你个人笔记土壤中的思考延伸。 Not detached generic chat, but a natural extension rooted in your personal notebook.

场景一 · 灵感打捞 Scenario 1 · Note Retrieval

打捞旧札记 · 与过去的思考重逢 Retrieve Past Notes · Reconnect with Ideas

当你写下一段随笔时,Thoughter 会在本地笔记库中翻阅相关旧记录,将数月前的名言摘录或晨间随笔呈现在你面前,帮你发现思想的脉络。 When you write a note, Thoughter browses your notebook to surface related thoughts from months ago, helping you trace patterns across time.

探讨:“时间与遗忘” Topic: "Time & Memory"

“为你打捞到你在 3 月和 5 月留下的两处闪念:” "Surfaced two notes from March and May:"

03-12 · 卡尔维诺《隐形的城市》 03-12 · Italo Calvino, Invisible Cities

“记忆中的形象一旦被词语固定住,就给抹掉了。” "Images of memory, once fixed in words, are erased."

05-18 · 晨间随笔 05-18 · Morning Journal

“遗忘不是消失,而是我们暂时失去了找寻钥匙的耐心。” "Forgetting isn't disappearing; we merely lost patience to find the key."

场景二 · 建议卡片 Scenario 2 · Proposal Cards

建议卡片 · 自由采纳与细修 Proposal Cards · Review & Refine

无论是润色语句还是重构段落,Thoughter 都会生成一张清晰完整的建议卡片。你可以一键采纳保存,也能随时进入编辑器二次细修,绝不后台直接覆盖原笔记。 Whether polishing sentences or restructuring ideas, suggestions arrive as structured cards. Accept with one click or open in the editor to fine-tune — your notes are never overwritten.

修改建议提案 Edit Proposal 待确认 Pending
《关于深度阅读的片羽思考》 "Reflections on Deep Reading"

“正如水流穿过竹筛,虽然水带不走,但竹筛已被涤荡得格外洁净……” "Like water through a bamboo sieve: water passes through, yet the sieve is left pristine..."

#深度阅读 #DeepReading #阅读感悟 #Reflections
场景三 · 灵感沉淀 Scenario 3 · Capturing Insights

灵感沉淀 · 零碎感悟一键归库 Capture Insights · Save with One Tap

在与 Thoughter 探讨中产生的思想火花,可以一键整理为包含标题、正文与推荐标签的新笔记卡片,轻松归入你的本地主笔记库。 Sparks from conversations can be captured into structured note proposals complete with titles and tags, saved seamlessly to your notebook.

新建笔记提案 New Note Proposal 草稿就绪 Draft Ready
《在时间的间隙中打捞灵感》 "Gathering Sparks in Quiet Moments"

“我们在白昼的缝隙中打捞偶得的闪念,让散落的文字沉淀为清醒的回响。” "We gather fleeting thoughts from everyday margins, letting scattered words settle into quiet resonance."

#思考与沉淀 #Reflection #灵感微光 #Inspiration
CORE DESIGN PHILOSOPHY

为什么 Thoughter 与众不同? Why Thoughter Stands Apart

专注个人思考沉淀,坚守创作主权与数据掌控。 Dedicated to personal reflection, creative sovereignty, and data ownership.

重逢 · RETRIEVE RETRIEVE

打捞旧札记,串联新想法 Retrieve Past Notes, Connect New Ideas

Thoughter 会在你的本地笔记库中翻找相关的旧日札记,将过去的思考与当下的灵感串联起来,唤醒曾经写下的文字。 Thoughter searches your notebook to connect past entries with current thoughts, bringing previous reflections back to life.

本地笔记智能探索 Smart Note Exploration
主权 · SOVEREIGNTY SOVEREIGNTY

提案卡片制,笔握在自己手里 Proposal Cards, You Hold the Pen

Thoughter 将每一次润色与灵感整理都沉淀为独立的建议卡片,你可以直接保存,也能随时进入编辑器细修。 Every revision and drafted thought is presented as an independent proposal card. You can accept it directly or edit it further in the editor.

建议卡片确认机制 Proposal & Review System
默契 · RAPPORT RAPPORT

专属记忆,懂你文风偏好 Personal Memory, Learns Your Voice

Thoughter 拥有专属的偏好记忆,记录你的文风习惯与沟通偏好。它在日常伴写中不断熟悉你的表达风格,越用越有默契;偏好随时可在设置中一键清空重置。 Thoughter remembers your phrasing preferences and habits across chats. Over time it adapts to your voice, and you can review or clear memories in Settings at any time.

专属偏好记忆 Personalized Preferences
自由 · FREEDOM FREEDOM

开放兼容,支持本地模型 Open & Compatible, Runs Local Models

支持标准 OpenAI 兼容接口,可灵活接入 DeepSeek、OpenAI、通义千问等主流云端服务;亦支持连接 Ollama、LM Studio 等本地运行的离线模型,自带 Key 或本地部署皆可使用。 Supports standard OpenAI-compatible endpoints including DeepSeek, OpenAI, and Qwen, as well as local offline models via Ollama and LM Studio. Use your own key or run locally.

标准协议 & 本地离线兼容 Standard Protocol & Offline Support
DESIGN DIFFERENCES

特性与设计差异 Key Design Differences

客观了解 Thoughter 与其他 AI 交互方式的定位差异。 An objective look at how Thoughter differs from generic chat bots and cloud notes.

对比维度 Feature / Dimension 心迹 Thoughter ThoughtEcho Thoughter 网页通用聊天 AI Generic Web AI Chat 传统云端笔记 AI Traditional Cloud Note AI
笔记库融合 Notebook Integration 深入本地笔记库探索与打捞相关札记 Deeply explores and retrieves relevant notes from your notebook 上下文割裂,需手动复制粘贴 Disconnected context; requires manual copy-pasting 依赖全库集中云端搜索 Relies on centralized cloud-side index search
建议呈现机制 Suggestion Presentation 独立建议卡片,支持直接采纳或进编辑器细修 Independent proposal cards; accept directly or fine-tune in editor 仅在对话流中输出文本 Plain text output inside the chat stream only 常见直接覆盖替换原稿 Often directly overwrites original notes
偏好记忆管理 Preference & Memory 专属偏好记录,越用越懂,支持按需重置 Learns your voice across chats; clearable and manageable anytime 对话与偏好沉淀在官方云端 Prompts and profiles stored on vendor cloud 笔记与偏好深度绑定其商业云账号 Deeply locked into proprietary cloud ecosystem
模型接入方式 Model Connectivity 支持标准 OpenAI 兼容协议 + Ollama 本地模型 Standard OpenAI protocol + local offline models via Ollama 绑定单一官方平台 Locked to a single provider 平台封闭模型,无法自由切换 Closed models with no BYOK or provider choice
MODEL COMPATIBILITY

开放兼容,连接你习惯的模型 Open & Flexible Model Support

心迹采用标准的 OpenAI 兼容协议(/chat/completions)。你可以连接任何支持该规范的云端大模型服务,也可以使用 Ollama 或 LM Studio 在本地离线运行,无需强制绑定。 ThoughtEcho uses standard OpenAI-compatible endpoints (/chat/completions). Connect to any compatible cloud provider or run fully offline using Ollama or LM Studio.

DeepSeek
OpenAI
Ollama (本地离线) Ollama (Local Offline)
LM Studio
SiliconFlow 硅基流动 SiliconFlow
通义千问 Qwen Qwen
Moonshot Kimi
自定义 OpenAI 兼容接口 Custom OpenAI Endpoint
QUESTIONS & ANSWERS

常见问题解答 Frequently Asked Questions

关于数据安全、计费方式与使用技巧的真实解答。 Clear, honest answers about privacy, billing, and offline use.

Thoughter 会把我的全部笔记上传到云端大模型吗? Does Thoughter upload all my notes to AI servers? +
不会。 你的全部笔记默认存储在本地 SQLite 数据库中。只有当你向 Thoughter 发起提问、或要求它整理某篇笔记时,心迹才会将当前必要的上下文片段发送给你配置的模型服务商。数据传输采用端到端 HTTPS 加密,心迹官方没有任何中间服务器收集你的笔记。
No. Your notes are stored locally in your SQLite database. Only when you ask Thoughter a question or request a note summary does ThoughtEcho send relevant context snippets directly to your configured provider over HTTPS. ThoughtEcho operates no intermediate server and collects no note data.
使用 Thoughter 需要付费吗? Is Thoughter free to use? +
心迹应用本身完全免费且开源,没有任何内置广告或强制内购。使用 Thoughter 需要使用你自己的 AI 服务商 API Key(如 DeepSeek 或 OpenAI),调用费用直接由服务商按实际用量结算。若使用 Ollama 或 LM Studio 本地模型,则完全无需费用。
ThoughtEcho itself is completely free and open-source with no ads or subscriptions. Using Thoughter requires your own API key (e.g. DeepSeek or OpenAI), billed directly by the provider based on token usage. Running local models via Ollama or LM Studio is entirely free.
为什么 Thoughter 提议修改笔记时不会直接覆盖? Why doesn't Thoughter overwrite notes directly? +
这是心迹的核心设计原则——“创作主权永远归属于你”。Thoughter 产生的所有修改与新建均封装为结构化的建议卡片,由你审阅、进入编辑器调整或手动确认采纳,笔记才会发生改变。
This is a core design principle: "Creative sovereignty always belongs to you." All creations and revisions arrive as structured proposal cards that require your review and confirmation before applying to your notebook.
记忆系统是如何运作的? How does the memory system work? +
Thoughter 拥有专属的偏好记忆,用于记录你的文风偏好与沟通习惯。它在日常对话中逐渐了解你该如何称呼、喜欢怎样的表达风格。如果你想清空记忆,随时可在「心迹设置 → AI 设置」中一键清空重置。
Thoughter maintains a dedicated memory profile for your writing style and phrasing preferences across chats. You can ask Thoughter to forget any detail or clear all memories anytime in Settings › AI Settings.
在没有网络的情况下可以使用 Thoughter 吗? Can I use Thoughter offline without internet? +
可以。心迹支持配置本地大模型接口(如 Ollama / LM Studio)。只要你在电脑上运行了本地模型,心迹即可在完全断网的环境下与 Thoughter 进行灵感对谈与笔记打捞。
Yes. ThoughtEcho supports local model endpoints like Ollama and LM Studio. With a local model running on your machine, you can chat with Thoughter and explore your notes completely offline.

让思考在时光中慢慢发酵 Let Thoughts Settle and Resonate

免费、开源、无广告。现在就下载心迹 ThoughtEcho,遇见住在你摘录本里的灵感伴侣。 Free, open-source, and private. Download ThoughtEcho today and meet the companion inside your notebook.