Score breakdown
Popularity is tracked separately. Support, ads, sponsorships, and tips never affect these signals.
Why it matters
Useful for developer teams using AI coding agents who want a persistent memory layer with zero infrastructure (no RAG stack, no vector database, no Docker, no cloud) and full version control (the memory is plain Markdown in a git-versioned LLM wiki): LLM Wiki Memory is the MIT zero-infra persistent memory for AI coding agents (Claude Code / Cursor / Codex) as plain Markdown in a versioned LLM wiki
Who should use it
Who should skip it
Move on from ctxr-dev/llm-wiki-memory if the licensing terms, language support, or platform requirements do not fit your project.
About this signal
ctxr-dev/llm-wiki-memory is tracked by RepoRadar as a zero-infra persistent memory for in the MIT zero-infra persistent memory for AI coding a section. It was first seen on 2026-06-25 and last updated on 2026-06-25. The current verdict is 'try now' with a Silver tier and easy setup difficulty. The standout signals for ctxr-dev/llm-wiki-memory are setup ease (8.8) and open-source/build quality (8.4), while momentum (6.0) trails — that balance shapes where it fits best. 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 ctxr-dev/llm-wiki-memory a composite score of 7.2 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 101.0 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 evaluate an AI tool before you adopt it for the checklist behind this score.
Risk explanation
**The LLM wiki is the source of truth — commit it to git for durability.** The design is intentionally zero-infra, which means the LLM wiki (plain Markdown in the project's git repo) is the source of truth for the memory. A missed commit means the memory is not versioned, which defeats the durability claim. For any production adoption, set up an automatic commit of the wiki (a pre-commit hook, a cron job, or a CI workflow) before relying on the memory for a workflow that depends on it surviving; **101 stars and an early-stage project — verify the recall quality on the team's target use case.** LLM Wiki Memory is at 101 stars with last push 2026-06-14, and the project's differentiator is the zero-infra design (no RAG stack, no vector database, no Docker, no cloud) and the version-controlled LLM wiki. The recall is a local MCP server with BGE on-device embeddings, and the recall quality is conditional on the BGE model and the consolidation loop. For any production adoption, run a representative workflow against the team's existing Claude Code / Cursor / Codex setup and confirm the agent recalls the right context at the right moment (a gap in recall quality would surface as the agent failing to apply a stored lesson); **The companion `skill-llm-wiki` repo is a separate dependency — verify its maintenance cadence.** The LLM-wiki authoring surface lives in the companion `ctxr-dev/skill-llm-wiki` repo, and the two repos together form the closed loop. The risk surface is the maintenance cadence of the companion repo — if the companion stops being maintained, the memory layer's authoring surface degrades. Confirm the companion repo's commit cadence before committing to a production workflow that depends on both repos.