__ __ __ __ __
| \ \ | \ \ | \
| ▓▓ ▓▓______ ____ __ __ __ \▓▓ ▓▓ __ \▓▓
| ▓▓ ▓▓ \ \ | \ | \ | \ \ ▓▓ / \ \
| ▓▓ ▓▓ ▓▓▓▓▓▓\▓▓▓▓\ | ▓▓ | ▓▓ | ▓▓ ▓▓ ▓▓_/ ▓▓ ▓▓
| ▓▓ ▓▓ ▓▓ | ▓▓ | ▓▓ | ▓▓ | ▓▓ | ▓▓ ▓▓ ▓▓ ▓▓| ▓▓
| ▓▓ ▓▓ ▓▓ | ▓▓ | ▓▓ | ▓▓_/ ▓▓_/ ▓▓ ▓▓ ▓▓▓▓▓▓\| ▓▓
| ▓▓ ▓▓ ▓▓ | ▓▓ | ▓▓ \▓▓ ▓▓ ▓▓ ▓▓ ▓▓ \▓▓\ ▓▓
\▓▓\▓▓\▓▓ \▓▓ \▓▓ \▓▓▓▓▓\▓▓▓▓ \▓▓\▓▓ \▓▓\▓▓
github.com/nvk/llm-wiki
LLM-compiled knowledge bases for any AI agent. Parallel multi-agent research, thesis-driven investigation, source ingestion, wiki compilation, querying, and artifact generation. Ships as a Claude Code plugin or a portable AGENTS.md for Codex and others. Obsidian-compatible.
What's New in v0.0.10
Research Quality & Resilience — 5 improvements backed by empirical research from the agentic AI knowledge base:
- Session Registry — Multi-round research (
--min-time) now persists state to .research-session.json. If interrupted, resume from the last completed round instead of starting over.
- Subagent Prompt Template — Standardized prompt structure (Objective/Context/Constraints/Deliverables) for all research agents. "Most sub-agent failures aren't execution failures — they're invocation failures."
- Credibility Critic — New Phase 2b: independent credibility assessment of sources before ingestion. Scores peer-review status, recency, author authority, and bias. Prevents the "fox guarding the henhouse" problem.
- Progress Scoring — Each round now produces a 0-100 progress score. Enables principled termination (>=80 = quality ceiling) and low-yield detection (<40 = change strategy).
- Plan Reflection — Explicit reflection step between rounds that re-evaluates the overall research direction, not just picks gaps. Scores gaps by impact x feasibility x specificity. Catches 34% more cross-topic connections.
Install
Claude Code (native plugin):
/install-plugin github:nvk/llm-wiki
OpenAI Codex / Any LLM Agent (idea file):
# Copy AGENTS.md into your agent's context or project root
cp AGENTS.md ~/your-project/AGENTS.md
The AGENTS.md file contains the complete wiki protocol as a single portable document — works with any LLM agent that can read/write files and search the web.
New to a topic? One command, from anywhere:
/wiki:research "gut microbiome" --new-topic --min-time 1h
Creates a topic wiki, launches parallel agents, and keeps researching for an hour — drilling into subtopics each round finds. Come back to a fully compiled wiki.
Quick Start
/wiki:research "nutrition" --new-topic # Create wiki + research in one shot
/wiki:research "gut-brain axis" --wiki nutrition # Add more research to existing wiki
/wiki:research "fasting" --deep --min-time 2h # 8 agents, keep going for 2 hours
/wiki:research "keto" --retardmax # 10 agents, max speed, ingest everything
/wiki:research "What makes long form articles go viral?" --new-topic # Question → decompose → playbook
/wiki:thesis "fiber reduces neuroinflammation via SCFAs" # Thesis-driven: evidence for + against → verdict
/wiki:thesis "cold exposure upregulates BDNF" --min-time 1h # Deep thesis investigation
/wiki:query "How does fiber affect mood?" # Ask the wiki
/wiki:query "compare keto and mediterranean" --deep # Deep cross-referenced answer
/wiki:ingest https://example.com/article # Manually ingest a source
/wiki:ingest --inbox # Process files dropped in inbox/
/wiki:compile # Compile any unprocessed sources
/wiki:output report --topic gut-brain # Generate a report
/wiki:output slides --retardmax # Ship a rough slide deck NOW
/wiki:assess /path/to/my-app --wiki nutrition # Gap analysis: repo vs wiki vs market
/wiki:lint --fix # Clean up inconsistencies
Commands
