ishenwei/llm-wiki-agent
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Make Claude Code the primary interface — no API key needed

Browse Source 
Add .claude/commands/ slash commands (/wiki-ingest, /wiki-query,
/wiki-lint, /wiki-graph) so the wiki works directly inside Claude Code
without any Python or API key. CLAUDE.md updated to lead with Claude
Code usage. Python tools remain as optional standalone scripts.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
Anil Matcha
2026-04-07 07:07:23 +05:30
parent d12089aaaf
commit 116ccc4d3c
6 changed files with 182 additions and 72 deletions
Download Patch File Download Diff File Expand all files Collapse all files

18
.claude/commands/wiki-graph.md Normal file
View File

@@ -0,0 +1,18 @@
Build the LLM Wiki knowledge graph.
Usage: /wiki-graph
First try running: python tools/build_graph.py --open
If that fails (missing dependencies), build the graph manually:
1. Use Grep to find all [[wikilinks]] across every file in wiki/
2. Build a nodes list: one node per wiki page, with id=relative-path, label=title, type from frontmatter
3. Build an edges list: one edge per [[wikilink]], tagged EXTRACTED
4. Infer additional implicit relationships between pages not captured by wikilinks — tag these INFERRED with a confidence score (0.0–1.0); tag low-confidence ones AMBIGUOUS
5. Write graph/graph.json with {nodes, edges, built: today}
6. Write graph/graph.html as a self-contained vis.js page (nodes colored by type, edges colored by type, interactive, searchable)
After building, summarize: node count, edge count, breakdown by type, and the most connected nodes (hubs).
Append to wiki/log.md: ## [today's date] graph | Knowledge graph rebuilt

18
.claude/commands/wiki-ingest.md Normal file
View File

@@ -0,0 +1,18 @@
Ingest a source document into the LLM Wiki.
Usage: /wiki-ingest $ARGUMENTS
$ARGUMENTS should be the path to a file in raw/, e.g. `raw/articles/my-article.md`
Follow the Ingest Workflow defined in CLAUDE.md exactly:
1. Read the source file at the given path
2. Read wiki/index.md and wiki/overview.md for current context
3. Write wiki/sources/<slug>.md (source page format per CLAUDE.md)
4. Update wiki/index.md — add the new entry under Sources
5. Update wiki/overview.md — revise synthesis if warranted
6. Create/update entity pages (wiki/entities/) for key people, companies, projects
7. Create/update concept pages (wiki/concepts/) for key ideas and frameworks
8. Flag any contradictions with existing wiki content
9. Append to wiki/log.md: ## [today's date] ingest | <Title>
After completing all writes, summarize: what was added, which pages were created or updated, and any contradictions found.

19
.claude/commands/wiki-lint.md Normal file
View File

@@ -0,0 +1,19 @@
Health-check the LLM Wiki for issues.
Usage: /wiki-lint
Follow the Lint Workflow defined in CLAUDE.md:
Structural checks (use Grep and Glob tools):
1. Orphan pages — wiki pages with no inbound [[wikilinks]] from other pages
2. Broken links — [[WikiLinks]] pointing to pages that don't exist
3. Missing entity pages — names referenced in 3+ pages but lacking their own page
Semantic checks (read and reason over page content):
4. Contradictions — claims that conflict between pages
5. Stale summaries — pages not updated after newer sources changed the picture
6. Data gaps — important questions the wiki can't answer; suggest specific sources to find
Output a structured markdown lint report. At the end, ask if the user wants it saved to wiki/lint-report.md.
Append to wiki/log.md: ## [today's date] lint | Wiki health check

14
.claude/commands/wiki-query.md Normal file
View File

@@ -0,0 +1,14 @@
Query the LLM Wiki and synthesize an answer.
Usage: /wiki-query $ARGUMENTS
$ARGUMENTS is the question to answer, e.g. `What are the main themes across all sources?`
Follow the Query Workflow defined in CLAUDE.md:
1. Read wiki/index.md to identify the most relevant pages
2. Read those pages (up to ~10 most relevant)
3. Synthesize a thorough markdown answer with [[PageName]] wikilink citations
4. Include a ## Sources section at the end listing pages you drew from
5. Ask the user if they want the answer saved as wiki/syntheses/<slug>.md
If the wiki is empty, say so and suggest running /wiki-ingest first.

94
CLAUDE.md
View File

@@ -1,6 +1,25 @@
# LLM Wiki Agent — Schema & Workflow Instructions # LLM Wiki Agent — Schema & Workflow Instructions
This document defines how Claude maintains this wiki. Follow these conventions exactly in every session. This wiki is maintained entirely by Claude Code. No API key or Python scripts needed — just open this repo in Claude Code and talk to it.
## Slash Commands (Claude Code)
| Command | What to say |
|---|---|
| `/wiki-ingest` | `ingest raw/my-article.md` |
| `/wiki-query` | `query: what are the main themes?` |
| `/wiki-lint` | `lint the wiki` |
| `/wiki-graph` | `build the knowledge graph` |
Or just describe what you want in plain English:
- *"Ingest this file: raw/papers/attention-is-all-you-need.md"*
- *"What does the wiki say about transformer models?"*
- *"Check the wiki for orphan pages and contradictions"*
- *"Build the graph and show me what's connected to RAG"*
Claude Code reads this file automatically and follows the workflows below.
---
## Directory Layout ## Directory Layout
@@ -13,10 +32,13 @@ wiki/ # Claude owns this layer entirely
sources/ # One summary page per source document sources/ # One summary page per source document
entities/ # People, companies, projects, products entities/ # People, companies, projects, products
concepts/ # Ideas, frameworks, methods, theories concepts/ # Ideas, frameworks, methods, theories
graph/ # Auto-generated graph data — regenerate with build_graph.py syntheses/ # Saved query answers
tools/ # CLI scripts graph/ # Auto-generated graph data
tools/ # Optional standalone Python scripts (require ANTHROPIC_API_KEY)
``` ```
---
## Page Format ## Page Format
Every wiki page uses this frontmatter: Every wiki page uses this frontmatter:
@@ -31,23 +53,24 @@ last_updated: YYYY-MM-DD
--- ---
``` ```
Use `[[PageName]]` wikilinks to link to other wiki pages. These are parsed by build_graph.py. Use `[[PageName]]` wikilinks to link to other wiki pages.
--- ---
## Ingest Workflow ## Ingest Workflow
Triggered when user runs: `python tools/ingest.py <source-path>` Triggered by: *"ingest <file>"* or `/wiki-ingest`
Steps (in order): Steps (in order):
1. Read the source document fully 1. Read the source document fully using the Read tool
2. Write `wiki/sources/<slug>.md` — title, date, key claims, key quotes, tags, links to entity/concept pages 2. Read `wiki/index.md` and `wiki/overview.md` for current wiki context
3. Update `wiki/index.md` — add entry under the correct section 3. Write `wiki/sources/<slug>.md` — use the source page format below
4. Update `wiki/overview.md` — revise synthesis if the source adds new perspectives, themes, or contradicts prior conclusions 4. Update `wiki/index.md` — add entry under Sources section
5. Update existing entity pages that this source mentions; create new entity pages if needed 5. Update `wiki/overview.md` — revise synthesis if warranted
6. Update existing concept pages that this source discusses; create new concept pages if needed 6. Update/create entity pages for key people, companies, projects mentioned
7. Flag any contradictions with existing wiki content in the log entry 7. Update/create concept pages for key ideas and frameworks discussed
8. Append to `wiki/log.md` with this prefix format: `## [YYYY-MM-DD] ingest | <Title>` 8. Flag any contradictions with existing wiki content
9. Append to `wiki/log.md`: `## [YYYY-MM-DD] ingest | <Title>`
### Source Page Format ### Source Page Format
@@ -82,48 +105,53 @@ source_file: raw/...
## Query Workflow ## Query Workflow
Triggered when user runs: `python tools/query.py "<question>"` Triggered by: *"query: <question>"* or `/wiki-query`
Steps: Steps:
1. Read `wiki/index.md` to identify relevant pages 1. Read `wiki/index.md` to identify relevant pages
2. Read the relevant pages 2. Read those pages with the Read tool
3. Synthesize an answer with inline citations as wikilinks: `[[PageName]]` 3. Synthesize an answer with inline citations as `[[PageName]]` wikilinks
4. Ask the user if they want the answer filed as a new synthesis page in `wiki/` 4. Ask the user if they want the answer filed as `wiki/syntheses/<slug>.md`
--- ---
## Lint Workflow ## Lint Workflow
Triggered when user runs: `python tools/lint.py` Triggered by: *"lint the wiki"* or `/wiki-lint`
Check for: Use Grep and Read tools to check for:
- **Orphan pages** — wiki pages with no inbound `[[links]]` from other pages - **Orphan pages** — wiki pages with no inbound `[[links]]` from other pages
- **Contradictions** — claims that conflict across pages
- **Stale summaries** — pages not updated after newer sources changed the picture
- **Missing entity pages** — entities mentioned in 3+ pages but lacking their own page
- **Broken links** — `[[WikiLinks]]` pointing to pages that don't exist - **Broken links** — `[[WikiLinks]]` pointing to pages that don't exist
- **Data gaps** — important questions the wiki cannot answer — suggest new sources to find - **Contradictions** — claims that conflict across pages
- **Stale summaries** — pages not updated after newer sources
- **Missing entity pages** — entities mentioned in 3+ pages but lacking their own page
- **Data gaps** — questions the wiki can't answer; suggest new sources
Output a lint report as markdown. Output a lint report and ask if the user wants it saved to `wiki/lint-report.md`.
--- ---
## Graph Workflow ## Graph Workflow
Triggered when user runs: `python tools/build_graph.py` Triggered by: *"build the knowledge graph"* or `/wiki-graph`
- Pass 1: Parse all `[[wikilinks]]` in wiki pages → deterministic edges tagged `EXTRACTED` When the user asks to build the graph, run `tools/build_graph.py` which:
- Pass 2: Call Claude API to infer implicit relationships not captured by wikilinks → edges tagged `INFERRED` with confidence score - Pass 1: Parses all `[[wikilinks]]` → deterministic `EXTRACTED` edges
- Tag ambiguous relationships as `AMBIGUOUS` - Pass 2: Infers implicit relationships → `INFERRED` edges with confidence scores
- Use Louvain community detection to cluster nodes - Runs Louvain community detection
- Output `graph/graph.json` and `graph/graph.html` - Outputs `graph/graph.json` + `graph/graph.html`
- Cache by SHA256 of page content — only reprocess changed pages
If the user doesn't have Python/dependencies set up, instead generate the graph data manually:
1. Use Grep to find all `[[wikilinks]]` across wiki pages
2. Build a node/edge list
3. Write `graph/graph.json` directly
4. Write `graph/graph.html` using the vis.js template
--- ---
## Naming Conventions ## Naming Conventions
- Source slugs: `kebab-case` matching the source filename - Source slugs: `kebab-case` matching source filename
- Entity pages: `TitleCase.md` (e.g. `OpenAI.md`, `SamAltman.md`) - Entity pages: `TitleCase.md` (e.g. `OpenAI.md`, `SamAltman.md`)
- Concept pages: `TitleCase.md` (e.g. `ReinforcementLearning.md`, `RAG.md`) - Concept pages: `TitleCase.md` (e.g. `ReinforcementLearning.md`, `RAG.md`)
- Source pages: `kebab-case.md` - Source pages: `kebab-case.md`
@@ -151,7 +179,7 @@ Triggered when user runs: `python tools/build_graph.py`
## Log Format ## Log Format
Each entry starts with `## [YYYY-MM-DD] <operation> | <title>` so it's parseable: Each entry starts with `## [YYYY-MM-DD] <operation> | <title>` so it's grep-parseable:
``` ```
grep "^## \[" wiki/log.md | tail -10 grep "^## \[" wiki/log.md | tail -10

91
README.md
View File

@@ -2,60 +2,60 @@
[![License](https://img.shields.io/badge/license-MIT-blue.svg)](LICENSE) [![License](https://img.shields.io/badge/license-MIT-blue.svg)](LICENSE)
**A personal knowledge base that builds and maintains itself.** Drop in source documents — articles, papers, notes — and the LLM reads them, extracts the knowledge, and integrates everything into a persistent, interlinked wiki. You never write the wiki. The LLM does. **A personal knowledge base that builds and maintains itself.** Drop in source documents — articles, papers, notes — and the LLM reads them, extracts the knowledge, and integrates everything into a persistent, interlinked wiki. You never write the wiki. Claude does.
Unlike RAG systems that re-derive knowledge from scratch on every query, LLM Wiki Agent compiles knowledge once and keeps it current. Cross-references are pre-built. Contradictions are flagged at ingest time. Every new source makes the wiki richer. Unlike RAG systems that re-derive knowledge from scratch on every query, LLM Wiki Agent compiles knowledge once and keeps it current. Cross-references are pre-built. Contradictions are flagged at ingest time. Every new source makes the wiki richer.
## How It Works ## How It Works
``` ```
You drop a source → LLM reads it → wiki pages are created/updated → graph is rebuilt You drop a source → Claude reads it → wiki pages are created/updated → graph is rebuilt
You ask a question → LLM reads relevant wiki pages → synthesizes answer with citations You ask a question → Claude reads relevant wiki pages → synthesizes answer with citations
``` ```
Three layers: Three layers:
- **`raw/`** — your source documents (immutable, you own this) - **`raw/`** — your source documents (immutable, you own this)
- **`wiki/`** — LLM-maintained markdown pages (Claude writes, you read) - **`wiki/`** — Claude-maintained markdown pages (Claude writes, you read)
- **`graph/`** — auto-generated knowledge graph visualization - **`graph/`** — auto-generated knowledge graph visualization
## Quick Start ## Quick Start — Claude Code (no API key needed)
Open this repo in [Claude Code](https://claude.ai/code):
```bash ```bash
git clone https://github.com/SamurAIGPT/GPT-Agent.git git clone https://github.com/SamurAIGPT/GPT-Agent.git
cd GPT-Agent cd GPT-Agent
claude # opens Claude Code in this repo
```
Claude Code reads `CLAUDE.md` automatically. Then just talk to it:
```
# Drop a source into raw/ first, then:
/wiki-ingest raw/articles/my-article.md
/wiki-query what are the main themes across all sources?
/wiki-lint
/wiki-graph
```
Or in plain English: *"Ingest this paper"*, *"What does the wiki say about X?"*, *"Check for contradictions"*
## Quick Start — Standalone Python (requires API key)
```bash
pip install -r requirements.txt pip install -r requirements.txt
export ANTHROPIC_API_KEY=your_key_here export ANTHROPIC_API_KEY=your_key_here
```
Add your first source:
```bash
# Drop a source document into raw/
cp my-article.md raw/articles/my-article.md
# Ingest it — LLM reads, extracts, and files knowledge into the wiki
python tools/ingest.py raw/articles/my-article.md python tools/ingest.py raw/articles/my-article.md
``` python tools/query.py "What are the main themes?"
python tools/query.py "How does X relate to Y?" --save
Query the wiki: python tools/build_graph.py --open
python tools/lint.py --save
```bash
python tools/query.py "What are the main themes across all sources?"
python tools/query.py "How does X relate to Y?" --save # save answer back to wiki
```
Build the knowledge graph:
```bash
python tools/build_graph.py --open # opens graph.html in browser
```
Health-check the wiki:
```bash
python tools/lint.py --save # checks for orphans, contradictions, gaps
``` ```
## Architecture ## Architecture
@@ -81,16 +81,29 @@ tools/
CLAUDE.md ← schema and workflow instructions for the LLM CLAUDE.md ← schema and workflow instructions for the LLM
``` ```
## Tools ## Commands
### Claude Code (primary — no API key)
| Slash command | What it does |
|---|---|
| `/wiki-ingest <file>` | Read a source, update wiki pages, append to log |
| `/wiki-query <question>` | Search wiki, synthesize answer with citations |
| `/wiki-lint` | Check for orphans, broken links, contradictions, gaps |
| `/wiki-graph` | Build knowledge graph (`graph.json` + `graph.html`) |
Or describe what you want in plain English — Claude Code follows `CLAUDE.md` and does the right thing.
### Standalone Python (optional — requires `ANTHROPIC_API_KEY`)
| Command | What it does | | Command | What it does |
|---|---| |---|---|
| `python tools/ingest.py <file>` | Read a source, update wiki pages, append to log | | `python tools/ingest.py <file>` | Ingest a source |
| `python tools/query.py "<question>"` | Search wiki, synthesize answer with citations | | `python tools/query.py "<question>"` | Query the wiki |
| `python tools/query.py "<question>" --save` | Same, and file the answer back as a wiki page | | `python tools/query.py "<question>" --save` | Query and file answer back |
| `python tools/lint.py` | Check for orphans, broken links, contradictions, gaps | | `python tools/lint.py` | Lint the wiki |
| `python tools/build_graph.py` | Build `graph.json` + `graph.html` from wiki | | `python tools/build_graph.py` | Build graph |
| `python tools/build_graph.py --no-infer` | Build graph without semantic inference (faster) | | `python tools/build_graph.py --no-infer` | Build graph (skip inference, faster) |
| `python tools/build_graph.py --open` | Build and open in browser | | `python tools/build_graph.py --open` | Build and open in browser |
## The Graph ## The Graph