# 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.

Repository: https://github.com/nvk/llm-wiki
Canonical: https://ross.abutalabs.com/products/llm-wiki
Homepage: https://llm-wiki.net/
Language: Python
License: MIT
License Family: permissive
Topics: agentic-ai, agentic-skills, agentic-workflow, claude-code, codex, llm, plugin, wiki
Last push: 2026-08-24T23:09:42+00:00

## Health v2 (maintenance only)
Score: 77/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 99, release rhythm 87, longevity 10
- inputs: {"age_days": 151, "days_push": 9, "days_rel": 10, "gap_med": 0.0, "n_releases_24m": 65}
- flags: young
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1070, forks 104 (observed 2026-08-28T04:03:27.628242+00:00)

## What it is
A plugin that lets AI agents (Claude Code, OpenAI Codex, OpenCode, portable agents) compile and maintain LLM-curated knowledge bases as plain Markdown wikis. It orchestrates parallel multi-agent research, source ingestion, wiki compilation, read-only querying, session memory, and artifact generation, and is Obsidian-compatible.

## Use cases
- build a wiki knowledge base with AI agents
- run parallel multi-agent research on a topic
- ingest sources and compile them into cross-referenced articles
- generate reports, slide decks, and study guides from research
- query a knowledge base token-efficiently
- keep session memory across agent runs
- export project knowledge checkpoints for handoffs

## When to choose
- you use Claude Code, Codex, or OpenCode and want a persistent, agent-compiled knowledge base
- you want Obsidian-compatible Markdown files you fully own
- you need multi-agent research with provenance-rich source catalogs
- you want to turn rough ideas into researched, approved project briefs

## When to avoid
- you need a hosted wiki or web UI rather than local Markdown files
- you want a traditional RAG pipeline with vector embeddings instead of agent-compiled articles
- your agent runtime is not Claude Code, Codex, OpenCode, or AGENTS.md-compatible

## Facets
- artifact type: plugin
- maturity: active
- function: agent-framework, rag, documentation, search-engine, workflow-automation, llm-inference
- domain: artificial-intelligence, large-language-models, developer-tools, documentation
- platform: cli, cross-platform, python
- tags: claude-code, agentic-workflow, knowledge-base, obsidian, multi-agent-research, markdown, wiki, codex, opencode, ai-agents, retrieval-augmented-generation, knowledge-management

## Member repositories
- nvk/llm-wiki (main) score 77

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:27.628242+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T06:54:06.084212+00:00, confidence not recorded.
  - readme: https://github.com/nvk/llm-wiki (fetched 2026-08-28T04:03:27.628242+00:00, sha d2f544a6132d)
  - homepage: https://llm-wiki.net/ (fetched 2026-08-29T12:56:34.820341+00:00, sha 36ae2bcb9342)
- Data as of 2026-08-30T08:39:29.467469+00:00.