LazyMind
中文 | English
LazyMind: Keep AI-Agent under your control.
LazyMind is an AI Skill Runtime for knowledge-intensive work: an environment that turns knowledge, expert practice, and tools into executable, recoverable tasks. It connects reusable knowledge, executable Skills, observable workflows, editable artifacts, and evaluation-driven improvement in one workspace.
Instead of repeatedly uploading context, tuning prompts, and supervising every agent step, you choose the knowledge and workflow once. LazyMind then plans, executes, exposes intermediate results, and carries accepted feedback into the next run. Use it locally in Desktop Mode, deploy it as a shared enterprise service, or provide knowledge, Skills, and Workflows to external agents such as Codex, Cursor, and WorkBuddy.
- Desktop Mode is designed for technically capable professionals whose primary job is not programming, including solution architects, product managers, operators, testers, and content creators.
- Team and enterprise deployments serve secondary development, project delivery, proposals, FDE work, and organization-wide knowledge collaboration with shared permissions, deployment, and evaluation capabilities.
Quick start · Product architecture · Build a workflow · Desktop mode
What can you ship with it?
| Scenario | LazyMind runs | You receive |
|---|---|---|
| Research and review | Search sources → retrieve evidence → compare → synthesize → review | A traceable report grounded in your documents and external sources |
| AI Writer | Organize sources → outline → draft sections → revise → final review | An editable, versioned document rather than a one-shot answer |
| Presentations | Clarify intent → gather sources → outline → create and revise slides → export | A PDF or PPTX with speaker notes and locally editable slides |
| AI Image | Interpret intent → collect references → refine prompt → generate/edit | Images and animated stickers with the process retained |
| Knowledge assistant | Connect sources → parse/OCR → hybrid retrieve → rerank → answer | Answers linked back to reusable organizational knowledge |
| External agent augmentation | Connect projects and sessions → call knowledge, Skills, or Workflows → track execution | LazyMind capabilities and artifacts inside the agent you already use |
| Quality improvement | Capture a bad case → evaluate → diagnose → A/B test → deploy | A verified strategy improvement, not an unchecked prompt change |
For an end-to-end product video, see the Chinese README.
How LazyMind works
flowchart LR
K["Knowledge<br/>local files · cloud docs · object storage"] --> R["Retrieve & reason<br/>parse · OCR · hybrid search · rerank"]
S["Skills & workflows<br/>instructions · tools · state machines"] --> X["Observable execution<br/>steps · approvals · retry · rewind"]
R --> X
X --> A["Editable artifacts<br/>citations · revisions · delivery"]
A --> F["Feedback & evaluation<br/>preferences · bad cases · A/B tests"]
F --> K
F --> S
This loop is built from three connected systems:
| System | Responsibility | Product behavior |
|---|---|---|
| Knowledge Foundation | Give AI the right context | Multi-source ingestion, OCR, hybrid retrieval, reranking, and source traceability |
| State Brain | Keep long tasks on course | Visible steps, approvals, editable artifacts, retries, rewinds, and version history |
| AI Growth Engine | Improve future runs safely | Reviewable preferences and terminology plus evaluation, diagnosis, A/B tests, and rollback |
Core highlights
1. Deliver outcomes, not chat messages
Choose knowledge and a Skill; LazyMind continues from source organization through planning, generation, review, and delivery. Workflows define steps, tools, inputs, outputs, and transitions as state machines, while artifacts preserve editable results and revision history.
For long-running work, each step remains visible. Users can approve checkpoints, edit an artifact, or rerun from the failed step instead of restarting the whole task.
2. Ground every run in reusable knowledge
Local directories, object storage, Feishu, Notion, and other sources feed a unified knowledge base. PDFReader, MinerU, or PaddleOCR-VL parses documents; multi-embedding retrieval, hybrid search, and reranking keep results grounded in relevant evidence.
3. Package expert practice into reusable workflows
Research methods, writing processes, and domain standards can be managed as Skills and converted into executable Workflows. Teams can diagnose, repair, publish, version, and roll them back instead of rebuilding the same setup from prompts and scripts. See the Workflow format specification.
4. From an idea to an editable presentation
The PPT Workflow carries a presentation request through research, outline approval, slide generation, review, and export. It can use the user's prompt, uploaded files, LazyMind knowledge bases, web search results, and AI-generated images as source material, and it produces speaker notes for each slide.
Intermediate results, including collected materials and the outline, remain visible and editable throughout generation. After generation, users can drag the left thumbnails to reorder slides, remove slides and select text or elements for natural-language content and style changes. Results can be exported as PDF, image-based PPTX, or editable PPTX containing text, shapes, images, and charts.