Score breakdown
Popularity is tracked separately. Support, ads, sponsorships, and tips never affect these signals.
Why it matters
Most AI researchers / knowledge workers building thesis-driven investigations today have been either (a) hand-curating wikis in Obsidian / Notion / Logseq (high maintenance burden, no LLM integration), (b) using closed-source research tools (Elicit / Consensus / Perplexity Pro) that lock-in the user's data and tool choices, or (c) maintaining a custom research-orchestration workflow that requires
Who should use it
Who should skip it
Skip llm-wiki: MIT LLM-Compiled Knowledge Bases for Any AI Agent (Claude Code / Codex / OpenCode Plugins, Obsidian-Compatible) if the source link, documentation, or setup requirements do not align with your current workflow or stack.
About this signal
llm-wiki: MIT LLM-Compiled Knowledge Bases for Any AI Agent (Claude Code / Codex / OpenCode Plugins, Obsidian-Compatible) is tracked by RepoRadar as a tool in the Radar section. It was first seen on 2026-07-08 and last updated on 2026-07-08. The current verdict is 'try now' with a Silver tier and easy setup difficulty. llm-wiki: MIT LLM-Compiled Knowledge Bases for Any AI Agent (Claude Code / Codex / OpenCode Plugins, Obsidian-Compatible) leads on workflow potential (8.9) and setup ease (8.8); its lowest signal is maturity (5.7), so factor that in before investing setup time. This page summarizes the evidence RepoRadar has captured from captured source metadata. The score, tier, risk label, and verdict on this page are never influenced by sponsorship, ads, or tips — they reflect only the usefulness, popularity, novelty, momentum, maturity, and evidence signals described in the RepoRadar methodology.
How this item is evaluated
RepoRadar assigned llm-wiki: MIT LLM-Compiled Knowledge Bases for Any AI Agent (Claude Code / Codex / OpenCode Plugins, Obsidian-Compatible) a composite score of 7.8 out of 10, placing it in the Silver tier. This score combines weighted sub-signals: usefulness (35%), novelty (18%), momentum (14%), maturity (10%), open-source/build quality (7%), evidence quality (6%), workflow potential (6%), and setup ease (4%). Popularity is tracked separately at 0.0 and never affects the composite score or tier. The risk label of 'low' reflects inherent user-impacting hazards, not generic novelty. Items with no risk flag may still require normal code review before production use.
Putting this into practice? Read How to vet an AI agent or MCP server before you wire it in for the checklist behind this score.
Risk explanation
The 810* / 31-fork / 4-subscriber repo is at active maintenance but the consumer SHOULD note the LICENSE file lives on the `master` branch; not `main` -- the consumer SHOULD verify the LICENSE file is fetched from `master` (raw.githubusercontent.com/nvk/llm-wiki/master/LICENSE); not `main` (which returns 404); the consumer SHOULD note the install surface is plugin-based (Claude Code plugin or Codex plugin) -- the consumer SHOULD verify the target AI agent supports one of the supported plugins.