LLM-compiled knowledge bases for
any AI agent with awesome outputs.
Parallel multi-agent research. Thesis-driven investigation. Source ingestion. Wiki compilation. Session memory. Feedback curation. Topic archiving. Inventory tracking. Dataset manifests. Truth-seeking audits. Querying. Artifact generation. Ships as a Claude Code plugin, an OpenAI Codex plugin, an OpenCode instruction file, or a portable AGENTS.md. Obsidian-compatible.
Every run compounds. Sources become cross-referenced articles. Articles become reports, slide decks, study guides, playbooks, and implementation plans. Session digests keep the agent oriented without turning private chats into topic evidence.
What it does
One command spins up a topic wiki, dispatches up to ten agents, ingests what's worth keeping, collects provenance-rich catalogs before tracking them, archives old topics without deleting them, tracks durable follow-up state, indexes large datasets without copying them, captures redacted session context and feedback candidates without hoarding transcripts, compiles sources into articles, and hands you a deliverable built on top. All plain Markdown you own.
Research
5–10 parallel agents search academic, technical, applied, news, and contrarian angles. --min-time 2h keeps going in rounds, drilling into gaps each round finds.
Thesis mode
Start from a claim. Agents split across supporting, opposing, mechanistic, meta, and adjacent angles. Output is a verdict — not a summary. Round two fights confirmation bias.
Ingest
URLs, files, PDFs, inbox drops, Git doc repos, MediaWiki dumps, message archives, and Wayback CDX snapshots. Raw sources stay immutable; articles synthesize on top.
Collect
Find, dedupe, download bounded public media, and catalog discoverable artifacts, examples, memes, tools, entities, and source candidates. Captures aliases, found-in-context provenance, local asset paths, hashes, scale, media policy, and inventory fit.
Inventory
Track durable things the wiki should remember: items, source candidates, corpora, entities, open questions, watch items, and next actions. Chat views default to compact tables.
Datasets
Index large, external, mutable, or operational data with manifests, samples, profiles, and query recipes. The wiki becomes the interface; the data stays where it belongs.
Archive
Move whole topic wikis to topics/.archive/. Preserved knowledge stays structurally maintainable but out of default query, compile, research, collect, output, and maintenance context.
Compile
Raw sources become synthesized articles with cross-references and confidence scores. Every directory has an _index.md — nothing is scanned blindly.
Query
Quick (indexes), standard (articles), or deep (everything + sibling wikis). --resume picks up where you left off.
Sessions
Default-on hook capture writes redacted events, state JSON, and Markdown digests under .sessions/. Rehydrate future turns with compact context; promote only what belongs in a topic.
Feedback
Curates high-signal corrections, preferences, approvals, and plan acceptance under .sessions/feedback/. Generic acknowledgements are ignored; durable lessons are explicitly promoted.
Librarian
Score every article for staleness and quality. Two-tier scan: fast metadata check, then deep content read for flagged articles. Checkpoint recovery. Machine-readable JSON + human-readable report.
Audit
Answer the broader trust question. Reuse the librarian pass, trace outputs across raw/, wiki/, and output/, detect drift, inspect provenance, and do fresh research when local evidence is not enough.
Lessons
Extract lessons learned from the current session — error→fix patterns, user corrections, discoveries. Saved as structured notes the wiki can query later. --rules emits enforceable rules instead of prose.
Plan
Wiki-grounded implementation plans. Reads the knowledge base, interviews you about requirements, fills gaps with targeted research, and produces a phased plan citing wiki articles as evidence. --format rfc|adr|spec.
Output
Reports, slide decks, study guides, playbooks, implementation plans, timelines, glossaries, comparisons. Filed back into the wiki so the next output builds on every previous one.
Install
Claude Code
Native plugin. Recommended.
claude plugin install wiki@llm-wiki
Installs from the public marketplace. Restart Claude Code to apply.
OpenAI Codex
Marketplace plugin. Invoke with @wiki.
codex plugin marketplace add nvk/llm-wiki
# Then open /plugins, enable "LLM Wiki", use @wiki
Or from a local checkout: ./scripts/bootstrap-codex-plugin.sh --scope user --verify. The Codex tree is a generated mirror of the Claude source of truth — updates land identically.
OpenCode
Instruction file.
# In opencode.json:
{ "instructions": [
"path/to/llm-wiki/plugins/llm-wiki-opencode/skills/wiki-manager/SKILL.md"
] }
Or copy to ~/.config/opencode/AGENTS.md. Web search requires OPENCODE_ENABLE_EXA=1.
Pi
Instruction file. Best for local models.
pi --instructions path/to/llm-wiki/plugins/\
llm-wiki-opencode/skills/wiki-manager/SKILL.md
Pi's 1K system prompt leaves room for the full wiki skill on 32K context local models. Uses the same skill file as OpenCode.
Any LLM agent
Portable AGENTS.md.
curl -sL https://raw.githubusercontent.com/nvk/llm-wiki/master/AGENTS.md \
> ~/your-project/AGENTS.md
Drop the file into any agent's context or project root. Works with anything that can read/write files and search the web.
Upgrading an existing install
Claude Code:
claude plugin update wiki@llm-wiki
# Restart Claude Code to apply
If the update command misses a new version (stale marketplace cache), sync manually:
git clone https://github.com/nvk/llm-wiki.git # or: git -C ~/llm-wiki pull
REPO=~/llm-wiki/claude-plugin
DEST=~/.claude/plugins/cache/llm-wiki/wiki
VERSION=$(grep '"version"' "$REPO/.claude-plugin/plugin.json" | grep -o '[0-9.]*')
rm -rf "$DEST"/*
mkdir -p "$DEST/$VERSION"
cp -R "$REPO/.claude-plugin" "$REPO/commands" "$REPO/skills" "$DEST/$VERSION/"
Codex: codex plugin marketplace upgrade llm-wiki. For a local checkout: re-run ./scripts/bootstrap-codex-plugin.sh --scope user --verify.
AGENTS.md: re-run the curl command above to replace the file.
Quick start
One command, from anywhere — creates a topic wiki, launches parallel agents, keeps researching for an hour, comes back compiled.
/wiki:research "gut microbiome" --new-topic --min-time 1h
More common flows:
/wiki:research "nutrition" --new-topic
/wiki:research "fasting" --deep --min-time 2h
/wiki:research "What makes articles go viral?" --new-topic
/wiki:research --mode thesis "fiber reduces neuroinflammation via SCFAs"
/wiki:query "How does fiber affect mood?"
/wiki:query --resume
/wiki add https://example.com/article # fuzzy router → ingest
/wiki what do we know about CRISPR? # fuzzy router → query
/wiki:ingest-collection https://github.com/bitcoin/bips --wiki bitcoin
/wiki:collect "bitcoin memes" --wiki bitcoin
/wiki:collect "bitcoin memes" --scale medium --media reference --inventory corpus
/wiki:inventory add item "TRX-4M ring and pinion" --wiki trx4m-1-18
/wiki:inventory list --view actions --limit 10
/wiki:dataset add "Bitcointalk Temporal Graph" --location https://figshare.com/articles/dataset/BitcoinTemporalGraph/26305093
/wiki:dataset list --view schema --limit 10
/wiki:archive topic old-interest --reason "No longer active"
/wiki:archive list --archived
/wiki:archive restore old-interest
/wiki:session status
/wiki:session rehydrate --cwd "$PWD"
/wiki:feedback list --unpromoted
/wiki:session disable # optional opt-out
/wiki:compile
/wiki:output report --topic gut-brain
/wiki:assess /path/to/my-app --wiki nutrition
/wiki:lint --fix
Session memory without transcript hoarding
Long agent runs lose useful context when chats compact, terminals close, or work moves from Claude to Codex. LLM Wiki now has a hidden operational layer for that: redacted checkpoints, compact digests, and user-feedback candidates under HUB/.sessions/. It helps the next turn get oriented without treating private chat logs as curated wiki knowledge.
Default-on, easy opt-out
Trusted hooks capture in balanced mode by default. /wiki:session disable writes enabled: false so those hooks become no-ops.
Redacted by design
Capture stores metadata, state, small events, and distilled Markdown digests. Full transcripts are not stored by default.
Rehydrate future work
/wiki:session rehydrate returns a compact context block pointing the agent to relevant digests for the current directory, topic, or session ID.
Promotion stays explicit
Session digests and feedback candidates remain operational memory until promote writes a distilled note into a topic's raw/notes/.
What gets stored
HUB/.sessions/
├── config.json # enabled/mode/privacy/rehydrate settings
├── registry.jsonl # append-only lifecycle events
├── queue/YYYY-MM-DD.jsonl # small redacted hook events
├── state/<harness>/<session_id>.json # latest per-session machine state
├── digests/YYYY/MM/<harness>-<session_id>.md
├── feedback/
│ ├── candidates.jsonl # corrections, preferences, approvals, plan acceptance
│ └── status.json
└── indexes/ # derived caches for cwd/topic/session lookups
Common session commands
/wiki:session status
/wiki:session rehydrate --cwd "$PWD"
/wiki:session list --limit 10
/wiki:session show codex:abc123
/wiki:session promote codex:abc123 --topic meta-llm-wiki
/wiki:feedback list --unpromoted
/wiki:feedback show fb-abc123
/wiki:feedback promote fb-abc123 --topic meta-llm-wiki
/wiki:session disable # opt out
/wiki:session enable # turn capture back on
The same .sessions/ layout works across Codex, Claude Code, OpenCode, Gemini-style adapters, and local .wiki/ project wikis.
How it works
1ResearchParallel agents search the web, ingest sources, and compile articles in one command.
2IngestURLs, files, PDFs, inbox drops, repos, dumps, archives, or snapshots.
3CollectCatalog many discoverable things first, then decide what deserves inventory, raw ingestion, or dataset indexing.
4CompileRaw sources become synthesized wiki articles with cross-references and confidence scores.
5TrackInventory records and dataset manifests preserve next actions without polluting source evidence.
6ArchiveQuiet old topic wikis without deleting their sources, articles, outputs, or logs.
7QueryQuick (indexes), standard (articles), deep (active content plus archived index hints).
8CaptureSession hooks keep redacted checkpoints under .sessions/; no full transcripts by default.
9RehydrateFuture turns can receive a compact digest list instead of rereading the whole chat.
10FeedbackReview high-signal user-feedback candidates and promote only durable lessons.
11LintBroken links, missing indexes, orphan articles, archive registry drift. --fix auto-repairs safe issues.
12OutputSummaries, reports, slides, plans — filed back into the wiki.
Architecture
~/wiki/ # Hub — lightweight, no content
├── wikis.json # Registry of all topic wikis
├── _index.md # Lists topic wikis with stats
├── log.md # Global activity log
├── .sessions/ # Operational session memory, digests + feedback
└── topics/ # Each topic is an isolated wiki
├── nutrition/
│ ├── .obsidian/ # Obsidian vault config
│ ├── inbox/ # Drop zone for this topic
│ ├── inventory/ # Items, candidates, corpora, views
│ ├── datasets/ # Manifests for large/external data
│ ├── raw/ # Immutable sources
│ ├── wiki/ # Compiled articles
│ │ ├── concepts/
│ │ ├── topics/
│ │ └── references/
│ ├── output/ # Generated artifacts
│ ├── _index.md
│ ├── config.md
│ └── log.md
├── woodworking/ # Another topic wiki
└── .archive/ # Archived topic wikis, hidden by default
One topic, one wiki
Each research area is isolated. No cross-topic noise. Queries stay focused. A multi-wiki peek finds overlap when relevant.
Dual-linking
[[wikilinks]] for Obsidian plus standard markdown links for everything else. Works in every viewer — including no viewer at all.
Raw is immutable
Once a source is ingested it is never modified. Articles synthesize on top. Retraction removes both cleanly.
Collector catalogs
/wiki:collect records aliases, source context, media URLs, cached asset paths, hashes, dedupe notes, scale, and inventory recommendations before anything becomes evidence or durable state.
Inventory is state
Parts, source queues, corpora, watch items, and next actions live under inventory/ so they can be listed and revisited without becoming evidence.
Datasets stay external
datasets/ stores manifests, samples, profiles, and query recipes for large data. The wiki indexes data without copying it into the source corpus.
Archive is quiet
Archived topics live under topics/.archive/. Most tools skip them by default; deep queries may surface index hits, and explicit --include-archived can read them.
Sessions are operational memory
.sessions/ is hidden, cross-topic operational state for redacted checkpoints, digests, rehydration indexes, and feedback candidates. Topic promotion is explicit.
Zero dependencies
Runs entirely on the host agent's built-in tools. Plugin is Markdown + commands. No servers, no services, no telemetry.
Commands
All commands accept --wiki <name> to target a topic wiki and --local for the project wiki. Archived topic wikis are skipped by default; commands that support --include-archived require that explicit flag before reading or writing archived material. query, output, and plan also accept --with <wiki> for cross-wiki context.
| Command |
Description |
/wiki <natural language> |
Fuzzy intent router — say what you want, it routes to the right subcommand. |
/wiki |
Show status, stats, and list all topic wikis. |
/wiki init <name> |
Create a topic wiki at ~/wiki/topics/<name>/. |
/wiki:ingest <source> |
Ingest a URL, file path, or quoted text. |
/wiki:ingest --inbox |
Process files dropped into the topic wiki's inbox. |
/wiki:ingest-collection <source> |
Bulk-ingest Git doc repos, BIP-style proposal sets, MediaWiki dumps/API sites, message archives, or Wayback CDX snapshots. |
/wiki:collect "<things>" |
Find, dedupe, and catalog artifacts, examples, resources, media, memes, tools, entities, or source candidates. |
| `/wiki:collect "" --scale tiny |
small |
| `/wiki:collect "" --media archive |
thumbnail |
| `/wiki:collect "" --inventory corpus |
records` |
/wiki:inventory list |
List durable tracking records as compact chat tables or bullets. |
/wiki:inventory add <kind> "title" |
Add items, source candidates, entities, corpora, questions, tasks, or watch records after a fit check. |
/wiki:inventory scan-outputs --dry-run |
Preview legacy queues/backlogs before an additive inventory migration. |
/wiki:dataset list |
List dataset manifests without opening samples, profiles, queries, or underlying data. |
/wiki:dataset add "title" --location <path-or-url> |
Index large or external data with a manifest; the data stays outside the wiki. |
/wiki:dataset profile <slug> --dry-run |
Preview lightweight profiling of size, format, headers, or schema observations. |
/wiki:archive list [--archived] |
List active topic wikis and optionally archived topic wikis. |
/wiki:archive topic <slug> --reason "why" |
Move a topic wiki to topics/.archive/<slug> and hide it from default context. |
/wiki:archive restore <slug> |
Restore an archived topic wiki to active status. |
/wiki:archive peek <query> |
Search archived topic indexes without reading archived article bodies. |
| `/wiki:session status |
disable |
| `/wiki:session capture |
list |
| `/wiki:session rehydrate |
promote` |
| `/wiki:feedback list |
show` |
| `/wiki:feedback capture |
promote` |
/wiki:compile |
Compile new sources into wiki articles. |
/wiki:query <question> |
Q&A against the wiki. --quick / --deep / --list / --resume / --include-archived. |
/wiki:ll |
Extract lessons from current session into wiki. --dry-run, --rules. |
/wiki:research <topic> |
5 parallel agents. --plan (multi-path), --deep (8), --retardmax (10), --new-topic, --min-time 1h. |
/wiki:research --mode thesis <claim> |
Thesis-driven research: for + against → verdict. |
/wiki:plan <goal> |
Wiki-grounded implementation plan. `--format rfc |
/wiki:output <type> |
summary, report, study-guide, slides, timeline, glossary, comparison. |
/wiki:assess <path> |
Assess a repo against wiki + market. Gap analysis. |
/wiki:audit |
Truth-seeking audit across wiki, outputs, provenance, and fresh research when needed. |
/wiki:librarian |
Score articles for staleness and quality. Checkpoint recovery. --article <path> for single article. |
/wiki:lint |
Health checks. --fix auto-repairs. --deep web-verifies facts. |
/wiki:retract |
Remove a source and clean up downstream references. |
/wiki:project |
Group outputs into projects with goals and manifests. |
Guides
From zero to a compiled wiki in 5 minutes.
Quick Start — Your first wiki in 5 minutes
1. Install the plugin
claude plugin install wiki@llm-wiki
2. Create a topic wiki
Pick any topic you're curious about:
/wiki init nutrition
This creates a hub at ~/wiki/ and your first topic wiki at ~/wiki/topics/nutrition/.
3. Research it
/wiki:research "gut microbiome and mental health" --wiki nutrition
# or just say it naturally:
/wiki research gut microbiome and mental health
Five parallel agents search the web from different angles (academic, technical, applied, news, contrarian), ingest the best sources, and compile them into cross-referenced wiki articles. Takes 2-5 minutes.
4. Ask your wiki a question
/wiki:query "how does fiber affect mood?" --wiki nutrition
# or naturally:
/wiki how does fiber affect mood?
The wiki answers from its compiled articles with citations.
5. Audit before you trust an output
/wiki:audit --wiki nutrition
/wiki:audit --artifact output/report-gut-brain.md
Audit rechecks the wiki layer, traces the output's evidence chain, flags drift, and will do fresh research if the local corpus is not enough to answer the trust question.
What to do next:
/wiki:research "topic" --deep — 8 agents instead of 5, adds historical and data angles/wiki:research "topic" --min-time 1h — keep researching in rounds for an hour/wiki:research "topic" --plan — decompose into parallel research paths/wiki:audit --project nutrition-playbook — verify outputs and upstream wiki state together/wiki add https://example.com/article — fuzzy router detects the URL and ingests it/wiki what do we know about CRISPR? — fuzzy router detects the question and queries/wiki:lint --fix — clean up any structural issues
Research workflow — From question to compiled knowledge
A typical research session flows through four stages:
Stage 1: Ask a question or pick a topic
llm-wiki auto-detects whether you're asking a question or naming a topic. Use the direct command or the fuzzy router:
/wiki:research "What makes long-form articles go viral?" # direct command
/wiki research quantum computing # fuzzy router — same result
/wiki:research --mode thesis "fiber reduces neuroinflammation via SCFAs" # thesis → for/against evidence
Stage 2: Agents search in parallel
5 agents (8 with --deep, 10 with --retardmax) search simultaneously from different angles — 2-3 web searches each, full-content fetch, quality scoring (1-5). A credibility pass deduplicates before ingestion.
Stage 3: Sources are ingested and compiled
Top sources are saved to raw/ (immutable — never modified after ingestion). Then the compilation pass synthesizes them into wiki articles under wiki/concepts/, wiki/topics/, and wiki/references/ with cross-references, confidence scores, and bidirectional links.
Stage 4: Gap report and follow-up
After each round, you see what's covered, what's still missing, and suggested follow-ups. If 2+ gaps remain, you're offered to close them in parallel:
### Close gaps?
1. Dose-response curves for wavelength specificity
2. Long-term safety data for daily exposure
3. Device comparison (clinical vs consumer panels)
Enter numbers (e.g. 1,2,4), "all", or "skip":
Multi-round research: Add --min-time 2h to keep researching in rounds, each drilling into gaps the previous round found. Add --plan to decompose into parallel paths upfront.
How the wiki works — Hub, topics, sources, and articles
The hub (~/wiki/) is just a registry. No content — only wikis.json, _index.md, and log.md. All content lives in topic sub-wikis.
Topic wikis (~/wiki/topics/<name>/) are isolated research areas. Each has its own sources, articles, outputs, and Obsidian vault config. Isolation means researching quantum computing can't pollute your nutrition wiki.
Raw sources (raw/) are immutable. Once a paper, article, or data file is ingested, it's never modified. This is the audit trail — every claim in every article traces back to a source.
Wiki articles (wiki/) are LLM-compiled syntheses organized into three categories:
- Concepts — foundational ideas, mechanisms, theories
- Topics — specific subjects, comparisons, state-of-the-field
- References — tools, frameworks, data tables, lookup resources
Archive (topics/.archive/) is for whole topic wikis the user no longer wants in normal context. It preserves source history, articles, outputs, and logs while keeping old interests quiet by default.
Sessions (HUB/.sessions/) are operational memory for redacted harness checkpoints, compact digests, rehydration indexes, and feedback candidates. They are not compiled as topic evidence unless explicitly promoted into raw/notes/.
Inventory (inventory/) is for durable operational state: actual items, source candidates, corpora, entities, open questions, tasks, watch items, and next actions. It is intentionally not evidence for factual claims.
Dataset manifests (datasets/) let the wiki index large or external data without copying it into raw/. Manifests can point to local paths, URLs, archives, samples, profiles, and query recipes.
Articles use dual-link format: [[wikilink]] for Obsidian + standard markdown links for everything else. Confidence scores (high/medium/low) reflect source quality and corroboration.
Indexes (_index.md) exist in every directory. They're derived caches — rebuilt automatically from file frontmatter. The agent reads indexes first and never scans blindly.
Outputs (output/) are generated artifacts: reports, slide outlines, study guides, implementation plans. They're built from wiki articles, so every output compounds on all prior research.
Audit walks that full artifact graph. It can trace an output back through the wiki state and raw sources it depended on, then escalate into fresh research when the stored evidence is stale or incomplete.
Session capture — Context without transcript hoarding
Session capture is default-on operational memory. Trusted Codex, Claude, OpenCode, and Gemini hooks write redacted checkpoints into HUB/.sessions/ or a local .wiki/.sessions/. The topic wiki stays clean until you promote something.
What is captured: harness name, session ID, current directory, git branch/remote, small redacted hook events, per-session state JSON, markdown digests, and feedback candidates. Full transcripts are off by default.
HUB/.sessions/
├── config.json
├── registry.jsonl
├── queue/YYYY-MM-DD.jsonl
├── state/<harness>/<session_id>.json
├── digests/YYYY/MM/<harness>-<session_id>.md
├── feedback/candidates.jsonl
└── indexes/
Daily commands:
/wiki:session status
/wiki:session rehydrate --cwd "$PWD"
/wiki:session list --limit 10
/wiki:session show codex:abc123
/wiki:feedback list --unpromoted
/wiki:feedback promote fb-abc123 --topic meta-llm-wiki
Opt out: /wiki:session disable writes enabled: false in .sessions/config.json, so trusted hooks become no-ops. /wiki:session enable turns it back on.
Promotion rule: session digests and feedback candidates are useful for continuity, but they become topic knowledge only after /wiki:session promote or /wiki:feedback promote writes a distilled note under raw/notes/.
DS4 wiki profile — Native local wiki agent
Use native ds4-agent for DS4 wiki work, not a bare chat profile. LLM Wiki needs a real tool loop for targeted reads, writes, edits, shell checks, and index-first navigation.
Profile rule: keep ds4c-wiki as an opt-in side command. Load the LLM Wiki instruction file into -sys, launch with --chdir "$PWD", and keep your model, checkout, and hub paths in environment variables.
export DS4_REPO="$HOME/src/ds4"
export DS4_MODEL="$HOME/models/deepseek-v4-flash-q2.gguf"
export LLM_WIKI_REPO="$HOME/agent-workspace/llm-wiki"
export WIKI_INSTRUCTIONS="$LLM_WIKI_REPO/plugins/llm-wiki-opencode/skills/wiki-manager/SKILL.md"
# Run from the project or fixture you want ds4-agent to edit.
target_cwd="$PWD"
system_prompt="$(printf '%s\n' \
'You are ds4c-wiki, a native ds4-agent profile for LLM Wiki workflows.' \
'Resolve the hub, read indexes first, choose a topic, then use targeted reads/searches.' \
'Do not broad-scan home directories, unrelated source trees, or dependency folders.' \
'Keep .sessions operational until the user explicitly promotes a digest or feedback candidate.'; \
cat "$WIKI_INSTRUCTIONS")"
"$DS4_REPO/ds4-agent" \
-m "$DS4_MODEL" \
-c "${DS4_CTX:-100000}" \
--chdir "$target_cwd" \
--nothink \
-sys "$system_prompt" \
--non-interactive \
-p 'wiki status: tell me which hub or local .wiki you would use, then stop'
Public examples rule: use placeholders like ~/src/ds4, ~/models/model.gguf, ~/agent-workspace/llm-wiki, and ~/wiki. Before sharing snippets, redact local usernames, hostnames, LAN or VPN IPs, SSH fingerprints, tokens, raw traces, and full .sessions/ content.
First real test: run a disposable local wiki fixture before pointing DS4 at your real hub.
tmp="$(mktemp -d)"
cd "$tmp"
git init
cat > AGENTS.md <<'EOF'
Use only this fixture's local .wiki directory. Do not read or write a real user hub.
EOF
DS4C_WIKI_NON_INTERACTIVE=1 ds4c-wiki \
'Initialize a local .wiki, add one fictional raw note, query it, then stop.'
find .wiki -maxdepth 4 -type f | sort
Pass gate: the profile should read indexes first, avoid broad scans, keep .sessions/ operational until promotion, create only fixture-local files in the test, and answer from local wiki evidence. Full guide: DS4 wiki profile on learntoprompt.org.
iCloud shared hub — Portable paths, permissions, and SSH
Use iCloud Drive when you want the same hub visible from multiple Macs. The important rule is that the shared config should describe the logical path, not one Mac's absolute user directory.
Set the hub with a portable path:
/wiki config hub-path "~/Library/Mobile Documents/com~apple~CloudDocs/wiki"
This writes ~/.config/llm-wiki/config.json. New configs should keep hub_path and avoid writing a machine-specific resolved_path. Shared wikis.json entries should store topic paths such as topics/bitcoin, not /Users/alice/.../topics/bitcoin.
Each Mac needs its own app permission. iCloud sync can be healthy while macOS still blocks the agent process. Full Disk Access is local to the machine and to the exact launcher app.
- Claude Code from Terminal: grant Terminal.app access, then fully restart Terminal.
- Codex from VS Code, Cursor, iTerm, or another launcher: grant that launcher, not just Terminal.
- Codex over SSH: grant access to
/usr/libexec/sshd-session, /usr/libexec/sshd-keygen-wrapper, and optionally /usr/sbin/sshd, then start a new SSH/Codex session.
- OpenCode or sandbox wrappers: grant the app permission and also allow the hub path in the tool's own sandbox config.
Fast diagnostic: run this from the same terminal, SSH session, or app that launches the agent:
python3 - <<'PY'
from pathlib import Path
hub = Path.home() / "Library/Mobile Documents/com~apple~CloudDocs/wiki"
for path in [hub, hub / "wikis.json", hub / "topics"]:
try:
print("STAT OK:", path)
path.stat()
except Exception as exc:
print("STAT FAIL:", type(exc).__name__, exc)
try:
if path.is_dir():
print("LIST OK:", [p.name for p in path.iterdir()][:10])
else:
print("READ OK:", path.read_text(encoding="utf-8")[:200])
except Exception as exc:
print("READ/LIST FAIL:", type(exc).__name__, getattr(exc, "errno", None), exc)
PY
How to read the result: STAT OK followed by READ/LIST FAIL ... Operation not permitted means the path is correct and macOS privacy is denying content access. Do not switch to ~/wiki or a machine-local resolved_path; grant the launcher permission and restart the session.
Deep research with --plan — Parallel multi-path research
For broad topics, --plan decomposes your research into independent paths and runs them all in parallel:
/wiki:research "red light therapy" --plan --wiki redlight-therapy
# or naturally:
/wiki research red light therapy --plan
The agent generates a research plan and asks for confirmation:
## Research Plan — red light therapy
### Paths (will run in parallel)
1. **Mechanisms** — cytochrome c oxidase, wavelength specificity, dose-response
2. **Clinical evidence** — RCTs for skin, joints, wounds, cognition
3. **Devices** — LED vs laser, panel sizing, FDA clearances
4. **Criticisms** — placebo effects, publication bias, safety concerns
### Estimated: 4 paths x 5 agents = 20 parallel agents
Proceed? (y/n/edit)
On confirmation, all paths launch simultaneously. Each path runs its own 5-agent swarm. Sources are ingested in parallel (each path writes unique files), then a single compilation pass sees all sources at once for cross-path synthesis.
After the first round, a gap report shows what's still missing. Pick which gaps to close — they launch as another parallel batch:
### Close gaps?
1. Dose-response curves for wavelength specificity
2. Long-term safety data for daily exposure
3. Device comparison (clinical vs consumer)
Enter numbers (e.g. 1,2,4), "all", or "skip":
Combine with other flags:
--plan --deep — 8 agents per path instead of 5--plan --min-time 2h — multiple plan-dispatch-compile cycles over 2 hours--plan --new-topic — create the wiki and research in one shot
Using outputs — Reports, slides, plans, and more
Once your wiki has compiled articles, generate deliverables from them:
/wiki:output report --topic gut-brain --wiki nutrition
# or naturally:
/wiki write a report on gut-brain axis
Output types:
summary — concise overview of a topic or the entire wikireport — detailed analysis with citations and evidencestudy-guide — structured learning material with key concepts and review questionsslides — slide deck outline with speaker notestimeline — chronological view of events and developmentsglossary — term definitions extracted from articlescomparison — side-by-side analysis of two or more subjects
Outputs are saved to output/ inside the topic wiki and indexed automatically. Every output builds on all compiled articles, so the more you research, the stronger every output gets.
Retardmax mode works here too — /wiki:output report --retardmax ships a rough draft immediately. Iterate later.
Cross-wiki context: Use --with to pull knowledge from another wiki into your output:
/wiki:output report --wiki nutrition --with article-writing
# Uses nutrition content + article-writing craft knowledge
Projects: Group related outputs into project folders with goals:
/wiki:project new rebuild-blog "Rewrite the company blog using wiki research"
/wiki:output report --topic gut-brain --project rebuild-blog
The output lands in output/projects/rebuild-blog/ with a WHY.md that captures the goal. Future outputs with the same --project flag accumulate there.
Permissions setup — Skip URL approval prompts
Research sessions fetch many URLs. By default, Claude Code asks for approval on each one. To skip these prompts, add WebFetch and WebSearch to your project's allow list:
In .claude/settings.local.json:
{
"permissions": {
"allow": [
"WebFetch",
"WebSearch"
]
}
}
This pre-approves all web fetches and searches. You can also allow specific domains only: WebFetch(domain:arxiv.org).
If you prefer per-session approval, choose "Always allow" when Claude asks about the first URL — that covers the rest of the session.
Latest release
Pulled live from github.com/nvk/llm-wiki/releases. Falls back to the version baked into the plugin manifest if the API is unavailable.
v0.12.0 latest
Feedback curator. Trusted hooks now distill high-signal user corrections, preferences, approvals, and plan acceptance into redacted candidates under HUB/.sessions/feedback/.
Noise filter. Generic acknowledgements like ok, thanks, and cool are ignored by default.
Review then promote. Use /wiki:feedback list, show, and promote; selected candidates become topic knowledge only through explicit promotion into raw/notes/.
Plugins in the marketplace
Pulled live from .claude-plugin/marketplace.json on the master branch via jsDelivr CDN — no rate limits, always current.
wiki
v0.12.0
LLM-compiled knowledge base. Commands: /wiki (router + init/status), /wiki:ingest, /wiki:ingest-collection, /wiki:collect, /wiki:inventory, /wiki:dataset, /wiki:archive, /wiki:session, /wiki:feedback, /wiki:compile, /wiki:query, /wiki:research, /wiki:audit, /wiki:librarian, /wiki:ll, /wiki:assess, /wiki:plan, /wiki:lint, /wiki:output, /wiki:retract, /wiki:project.
FAQ
What is LLM Wiki?
LLM Wiki is a set of commands and a knowledge model that turns any LLM agent into a research engine and an append-only, Markdown-native wiki. It runs parallel multi-agent research, collects provenance-rich catalogs of discoverable artifacts and examples, preserves redacted session memory and feedback candidates under .sessions/, ingests URLs and files, archives old topic wikis that should stay preserved but quiet, tracks durable inventory state, indexes large datasets with manifests, compiles raw sources into synthesized articles with cross-references, audits whether those articles and outputs are still trustworthy, answers questions against the compiled knowledge, and generates artifacts like reports, slides, study guides, and implementation plans.
Inspired by Andrej Karpathy's LLM wiki concept.
Which LLM agents does it support?
Five install modes: Claude Code (native plugin via the llm-wiki marketplace), OpenAI Codex (marketplace plugin via codex plugin marketplace add nvk/llm-wiki, invoked with @wiki), OpenCode (instruction file via opencode.json), Pi (instruction file — best for local models with its minimal system prompt), and any other LLM agent via the portable AGENTS.md file.
The behavioral logic lives in a single wiki-manager skill shared across runtimes — Codex, OpenCode, and Pi trees symlink into the Claude source of truth so there is no fork. Drift is caught by self-healing sync tests.
Where is my wiki data stored?
By default in ~/wiki/ on your machine. You can relocate the hub to iCloud Drive, Dropbox, or any custom path:
/wiki config hub-path ~/Library/Mobile\ Documents/com~apple~CloudDocs/wiki
Config lives at ~/.config/llm-wiki/config.json. Shared hubs should use portable hub_path values and relative wikis.json topic paths; old machine-specific resolved_path values are treated only as fallback caches.
Why does iCloud work on one Mac but fail on another?
macOS privacy permissions are local to each Mac and to the exact process launching the agent. One machine can read the iCloud hub while another machine with the same Apple ID and same files returns Operation not permitted.
If stat succeeds for the hub but reading wikis.json or listing topics/ fails, the configured hub_path is correct. Grant Full Disk Access or iCloud Drive access to the launcher app, then fully restart that app and the agent.
For SSH-launched Codex sessions, Terminal.app permission is not enough because Codex is a child of sshd-session. Grant access to /usr/libexec/sshd-session, /usr/libexec/sshd-keygen-wrapper, and optionally /usr/sbin/sshd, then start a new SSH session.
How does session memory work?
Session memory lives in HUB/.sessions/ or a local .wiki/.sessions/. It is hidden operational state: redacted hook events, state JSON, digest Markdown, feedback candidates, and indexes for rehydration.
It is default-on so long sessions can survive compaction and future turns can start with the right context. It does not store full transcripts by default. Run /wiki:session disable to opt out, /wiki:session rehydrate to load compact context, and /wiki:session promote only when a digest should become topic evidence.
Is it Obsidian-compatible?
Yes. Each topic wiki ships with its own .obsidian/ vault config and can be opened as an independent vault:
open ~/wiki/topics/nutrition/
Cross-references use a dual-link format:
[[gut-brain-axis|Gut-Brain Axis]] ([Gut-Brain Axis](../concepts/gut-brain-axis.md))
Obsidian reads the wikilink for graph view and backlinks; everything else (Claude Code, GitHub, plain text editors) follows the standard markdown link.
What is "retardmax" mode?
A research mode inspired by Elisha Long's retardmaxxing philosophy — act first, think later. Ten parallel agents, skip planning, cast the widest net, ingest aggressively, compile fast, lint later.
Available on /wiki:research --retardmax and /wiki:output --retardmax for when you want results now and will clean up afterward.
How does thesis-driven research work?
/wiki:research --mode thesis "<claim>" starts from a specific claim and uses it as a filter. Agents are split across supporting, opposing, mechanistic, meta/review, and adjacent — balanced by design.
Sources that don't relate to the claim's variables are skipped, which keeps the wiki tight. Output is a verdict: supported, partially supported, contradicted, insufficient evidence, or mixed.
With --min-time, round two focuses harder on the weaker side of the evidence — counter-weight against confirmation bias.
Is it free and open source?
Yes. LLM Wiki is MIT-licensed. Source and releases at github.com/nvk/llm-wiki.
Does it work offline?
Compiling, querying, linting, and generating artifacts from an existing wiki work offline — everything is plain Markdown on your disk. Research and ingestion need internet since they fetch URLs and search the web.
What dependencies does it have?
Zero runtime dependencies. LLM Wiki uses only the built-in tools of the host agent (file read/write, web fetch, web search). The plugin itself is Markdown: command definitions, skills, and reference docs.
Optional: ask-grok-mcp for best-in-class tweet ingestion, tobi/qmd for local search beyond ~100 articles.
How do I update to the latest version?
Claude Code: claude plugin update wiki@llm-wiki and restart.
Codex: codex plugin marketplace upgrade llm-wiki (or re-run the bootstrap helper for a local checkout).
AGENTS.md: re-curl from the master branch to replace your file.
See Install for the manual sync fallback when the plugin updater hits stale cache.
Credits
Instagram Engineering
Shopify Engineering