Skip to content

Latest commit

 

History

3 Commits

Folders and files

NameName
Last commit message
Last commit date
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Still 🧪

Knowledge Distillation Protocol for AI Agents

Still is a structured knowledge distillation framework designed for AI agents, built on the Cangjie (仓颉) deep distillation methodology. It transforms raw information — videos, articles, conversations, concepts — into structured knowledge units that agents can reason about directly.

Cangjie invented Chinese writing; Still distills knowledge.


Why Still?

Traditional Notes Still
Written for humans, grows stale and ignored Written for AI agents, lightweight and queryable
Flat tag-based organization Bidirectional knowledge graph
Pure summarization, depth depends on the writer Structured validation, framework-driven depth
No boundary conditions Explicit applicability matrix
Isolated notes Auto-linked across entries

Core insight: In the age of information overload, the bottleneck isn't acquisition — it's distillation. AI agents don't need more data; they need purer knowledge.


The Still Schema

Every distilled entry has 8 structured modules + 1 optional, with typed relationships between entries:

 0. 📡 Lifecycle          → V1 (raw) → V2 (verified) → V3 (synthesized)
 1. ⚡ One-Liner         → 3-second relevance check
 2. 🏗️ Core Framework    → The skeleton
 3. 📚 Theory Backing    → Why it holds
 4. ⚙️ Method E/B        → Execution steps + Boundaries
 5. 🤖 What AI Can't Do  → Human-AI division
 6. 🧭 Judgment Path     → Novice → Expert roadmap
 7. ✅ Triple Validation → Cross-domain / Predictive / Distinctive
 8. 🔗 Linked Concepts   → Typed relationship graph (8 relation types)
[9]. 🧩 Cross-Domain Grid → Mental model lattice (optional)

Full specification: SCHEMA.md (Chinese)


Repository Structure

still/
├── README.md              # This file
├── SCHEMA.md              # Distillation protocol specification (Chinese)
├── AGENTS.md              # Agent usage guide (Chinese)
├── templates/             # Distillation templates
│   ├── video.md           # Video content
│   └── concept.md         # Concepts & methodology
├── examples/              # Real-world distillation examples
│   └── ai-imagination-bottleneck.md
├── scripts/               # CLI tools
│   ├── distill.py         # Distiller
│   ├── validate.py        # Validator
│   └── link.py            # Linker
└── workflows/             # Automation pipeline
    └── distill.sh         # One-shot distillation pipeline

Quick Start

1. Manual Distillation

Pick a template from templates/, follow the schema, fill in the 8 modules.

2. Using the CLI

# Distill a raw article
python3 scripts/distill.py --input article.md --output distilled.md

# Validate a distilled entry
python3 scripts/validate.py examples/*.md

# Find orphan entries (no cross-links)
python3 scripts/link.py --target examples/my-distill.md --wiki ../wiki/

3. Pipeline Automation

# Batch process all raw files
bash workflows/distill.sh ./raw/ ./wiki/

Usage with AI Agents

Place distilled .md files into your agent's knowledge base. Agents can:

  1. 3-second relevance check — read the "One-Liner"
  2. Cross-domain reasoning — traverse "Linked Concepts" for analogies
  3. Boundary awareness — check the "Boundary" matrix for applicability
  4. Output validation — use "Triple Validation" as a cross-check
  5. Progressive learning — follow the "Judgment Path" from novice to expert

See AGENTS.md (Chinese) for detailed agent workflow instructions.


Design Philosophy

Principle Meaning
Essence Every entry retains only its irreducible core
Verifiable Every claim has a validation anchor
Approachable 3 seconds to decide relevance

Related Projects

This framework pairs well with:

  • Obsidian / any wiki — as the storage backend for distilled entries
  • codebase-memory-mcp — for code knowledge graphs
  • Graphify — for project-level relationship mapping

License

MIT

About

Still — 知识蒸馏协议 | Knowledge Distillation Protocol for AI Agents (基于仓颉方法论)

Resources

Stars

0 stars

Watchers

0 watching

Forks

Releases

Packages

Contributors

Languages