开源MCP工具：本地Git版本化记忆

Requirements

Node 20 or newer, and git. No Docker, no Python. The embedding model downloads on first recall (set embed.backend: lexical in settings.yaml to skip it entirely).

Install

Paste this one-liner into your AI coding agent (copy button on the right) — it covers both a fresh install and an update of an existing one. The full procedure lives in AI-INSTALL-PROMPT.md; the agent fetches and follows it:

Set up llm-wiki-memory in this project: fetch https://raw.githubusercontent.com/ctxr-dev/llm-wiki-memory/main/AI-INSTALL-PROMPT.md and follow it EXACTLY (it covers fresh install and update; if already installed, the same file is local at @.llm-wiki-memory/src/AI-INSTALL-PROMPT.md).

Or run it yourself — fresh install:

git clone https://github.com/ctxr-dev/llm-wiki-memory ./.llm-wiki-memory/src
./.llm-wiki-memory/src/bootstrap.sh                    # add --commit-memory to commit the wiki
./.llm-wiki-memory/src/bootstrap.sh --schedule daily   # optional: hourly cron / launchd

Update an existing install:

```bash git -C .llm-wiki-memory/src fetch origin

Full cron-job (compile + consolidate + attempt log entry).

node scripts/cli.mjs cron-job

Configuration

Settings live in two files in ./.llm-wiki-memory/settings/:

• .env — secrets, provider switches, deployment paths, workspace identity, test seams. Things that genuinely need shell precedence. See templates/env.example.
• settings.yaml — every other knob, nested by concern: consolidate, flush, hook, embed, recall, compile, gc, gate, providers, crossCuttingAreas. See templates/settings.yaml.

The .env file's strict subset overrides the YAML where it overlaps (e.g. MEMORY_LLM_PROVIDER collapses the YAML chain). As of the 2026-06-03 v2 release, every MEMORY_* env var that's NOT on the strict allow-list is a silent no-op — application config moved into settings.yaml. The runbook covers the migration.

Strict-subset .env keys:

Highlights from settings.yaml:

<details> <summary><strong>Full schema</strong></summary>

See templates/settings.yaml for the complete annotated set with every knob in each of the nine config sections plus the top-level crossCuttingAreas list.

</details>

<details> <summary><strong>Choosing an embedding model</strong></summary>

Recall ranks queries with an on-device transformers.js model, set by embed.model in settings.yaml. The default Xenova/bge-large-en-v1.5 gives the best routing quality; lighter models trade some accuracy for a much smaller download. Sizes below are the quantized ONNX weights transformers.js downloads by default (full-precision is ≈ 4× larger), lightest first:

Set a lighter model in settings.yaml:

embed:
  model: Xenova/bge-small-en-v1.5

Changing the model invalidates the embedding cache automatically. Stay within the MiniLM / BGE / GTE / mxbai families: they're mean-pooled with no query prefix, which is how this engine embeds. Prefix-based models (e5, nomic) underperform here because the engine doesn't add the query: / search_document: prefixes they expect.

</details>

Capture pipeline — chunked & recoverable

The flush worker (PostCompact / SessionEnd hooks) chunks oversized transcripts and runs each chunk through a provider/model chain. A clean "nothing durable" verdict writes no leaf at all (the breadcrumb log keeps visibility); a partial or total failure preserves the full body to a stash so cli.mjs redistill can re-attempt later with no data loss.

The audit fields recorded on every leaf — chunks_total, chunks_succeeded, failed_chunks, provider_chain_tried, final_provider — make every distillation reproducible from frontmatter alone. Redistilled leaves carry redistilled_from, redistill_attempts, and original_outcome.