Pangram verdict · v3.3
We believe that this document is primarily AI-generated with some human-written content
AI likelihood · overall
AIArticle text · 1,571 words · 6 segments analyzed
LLM-compiled knowledge bases forany 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.