How do I install claude-mem-lite?

Run these in Claude Code: npx -y skills add sdsrss/claude-mem-lite. Then prompt normally.

Does claude-mem-lite auto-invoke its skills?

Not yet. It is indexed on Flowy as a plain plugin. Request auto-invocation on its page and Flowy will route its skills for you as you prompt.

Is claude-mem-lite free?

Yes. Flowy is free and open source, with nothing gated. You can read every skill in full before you install.

Development

claude-mem-lite

claude-mem-lite is a persistent memory (also called long-term memory or cross-session context) system for Claude Code — Anthropic's CLI coding agent.

FLOW.md

sdsrss@sdsrss

GitHub

Stats

Python JavaScript Node Bash SQL

What's inside

Commands

/adoptUse when: user asks to increase claude-mem-lite's tool-invocation rate in the current project, or to (re)install the steering block. Writes a sentinel-wrapped managed block into <cwd>/CLAUDE.md plus a <cwd>/.claude/plugin_claude_mem_lite.md detail doc, and migrates away any

FAQ

claude-mem-lite is a Claude Code plugin with hand-picked skills for development work, indexed on Flowy. Install it with the command on its page. Its skills do not fire on their own yet. Request auto-invocation to have Flowy route them as you prompt. Free and open source.

What is claude-mem-lite?: claude-mem-lite is a persistent memory (also called long-term memory or cross-session context) system for Claude Code — Anthropic's CLI coding agent.
How do I install claude-mem-lite?: Run these in Claude Code: npx -y skills add sdsrss/claude-mem-lite. Then prompt normally.
Does claude-mem-lite auto-invoke its skills?: Not yet. It is indexed on Flowy as a plain plugin. Request auto-invocation on its page and Flowy will route its skills for you as you prompt.
Is claude-mem-lite free?: Yes. Flowy is free and open source, with nothing gated. You can read every skill in full before you install.

Flowy

claude-mem-lite · Flowy

README

Read on GitHub ↗

English | 中文

claude-mem-lite

claude-mem-lite is a persistent memory (also called long-term memory or cross-session context) system for Claude Code — Anthropic's CLI coding agent. It runs as an MCP server plus a set of Claude Code hooks, automatically capturing coding observations, decisions, and bug fixes during sessions, then providing hybrid full-text + semantic search to recall them later.

Compared to general-purpose LLM memory frameworks like mem0 or the MCP reference memory server, claude-mem-lite is purpose-built for Claude Code's hook lifecycle: episode batching cuts LLM calls 7–10× vs the original claude-mem (an estimated ~600× lower total cost — see the cost model below; this is an architecture estimate, not a measured benchmark), while the hybrid FTS5 + TF-IDF retriever benchmarks at 0.88 Recall@10 / 0.96 Precision@10.

中文简介：claude-mem-lite 是 Claude Code 的轻量级持久化记忆 / 长期记忆 / 跨会话上下文插件，基于 MCP 协议 + 钩子机制，自动捕获编码会话中的决策、修复和上下文，并通过 FTS5 + TF-IDF 混合检索召回。详见中文 README。

Zero external services. Single SQLite database. Minimal overhead.

Why claude-mem-lite?

A ground-up redesign of claude-mem, replacing its heavyweight architecture with a smarter, leaner approach.

Architecture comparison

	claude-mem (original)	claude-mem-lite
LLM calls	Every tool use triggers a Sonnet call	Only on episode flush (5-10 ops batched)
LLM input	Raw `tool_input` + `tool_output` JSON	Pre-processed action summaries
Conversation	Multi-turn, accumulates full history	Stateless single-turn extraction
Noise filtering	LLM decides via "WHEN TO SKIP" prompt	Deterministic code-level Tier 1 filter
Runtime	Long-running worker process (1.8MB .cjs)	On-demand spawn, exits immediately
Dependencies	Bun + Python/uv + Chroma vector DB	Node.js only (3 npm packages)
Source size	~2.3MB compiled bundles	~50KB readable source
Data directory	`~/.claude-mem/`	`~/.claude-mem-lite/` (hidden, auto-migrates)

Token & cost efficiency

For a typical 50-tool-call session (illustrative cost model — the ratios below are architecture estimates derived from batch size, token counts, and model pricing, not a measured end-to-end benchmark):

	claude-mem	claude-mem-lite	Ratio (estimated)
LLM calls	~50 (every tool use)	~5-8 (per episode)	~7-10x fewer
Tokens per call	1,000-5,000 (raw JSON + history)	200-500 (summaries only)	~5-10x smaller
Total tokens	~100K-250K	~1K-4K	~50-100x less
Model cost	Sonnet ($3/$15 per M)	Haiku ($0.25/$1.25 per M)	~12x cheaper
Combined savings			~600x lower cost (estimated)

Quality comparison

Dimension	Winner	Why
Classification accuracy	Tie	Both produce correct type/title/narrative
Noise filtering	lite	Code-level filtering is deterministic; LLM "WHEN TO SKIP" is unreliable
Observation coherence	lite	Episode batching groups related edits into one coherent observation
Code-level detail	original	Sees full diffs, but rarely useful for memory search
Search recall	Tie	Users search semantic concepts ("auth bug"), not code lines
Hook latency	lite	Async background workers; original blocks 2-5s per hook

Design philosophy

The original sends everything to the LLM and hopes it filters well. claude-mem-lite filters first with code, then sends only what matters to a smaller model. This is not a downgrade; it's a smarter architecture that produces equivalent search quality at a fraction of the cost.

Comparison: memory systems for AI coding agents

How claude-mem-lite differs from the major neighbors in the LLM-memory space (verified May 2026):

	claude-mem-lite	`mem0`	MCP reference `memory`	claude-mem (original)
Target client	Claude Code only	Any LLM app via SDK	Any MCP client	Claude Code only
Capture model	Auto via hooks	Manual `memory.add()`	Manual tool calls (`create_entities`, `add_observations`)	Auto via hooks
Code-aware retrieval	FTS5 + 100+ synonym pairs (incl. CJK↔EN)	General-purpose	Generic graph nodes	Code-aware
Search	Hybrid: FTS5 BM25 + TF-IDF cosine via RRF	Hybrid: semantic + BM25 + entity linking	Knowledge-graph traversal	FTS5 + Chroma vector
Storage	Single local SQLite	Pluggable; Qdrant or configurable vector store	Single JSONL file (knowledge graph)	SQLite + Chroma
LLM dependency	Haiku per episode (5–10 ops batched)	LLM per add/search op	None (graph CRUD only)	Sonnet per tool call
Setup	One command (`/plugin install` or `npx`)	SDK integration + vector store config	MCP install (per-client)	Bun + Python + Chroma

When to pick which: pick mem0 if you need a memory layer for a non-Claude-Code app (your own agent, multiple LLM providers). Pick the MCP reference memory server if you specifically want a knowledge-graph data model and don't mind invoking memory tools by hand. Pick claude-mem-lite if you want zero-touch automatic capture purpose-built for Claude Code's hook lifecycle, with code-domain retrieval and no external services.

Features

Automatic capture -- Hooks into Claude Code lifecycle (PostToolUse, SessionStart, Stop, UserPromptSubmit) to record observations without manual effort
Hybrid search -- FTS5 BM25 + TF-IDF vector cosine similarity, merged via Reciprocal Rank Fusion (RRF). FTS5 handles keyword matching; 512-dim TF-IDF vectors capture semantic similarity for recall beyond exact terms
Timeline browsing -- Navigate observations chronologically with anchor-based context windows
Episode batching -- Groups related file operations into coherent episodes before LLM encoding
Error-triggered recall -- Automatically searches memory when Bash errors occur, surfacing relevant past fixes
Proactive file history -- When editing a file, automatically shows relevant past observations for that file
Session summaries -- LLM-generated summaries at session end (via background workers using claude -p)
Project-scoped context -- Injects recent memory into CLAUDE.md and session startup for immediate context
Observation types -- Categorized as decision, bugfix, feature, refactor, discovery, or change
Importance grading -- LLM assigns 1-3 importance levels (routine / notable / critical) to each observation
Observation relations -- Bidirectional links between related observations based on file overlap
User prompt capture -- Records user prompts via UserPromptSubmit hook for intent tracking
Read file tracking -- Tracks files read during sessions for richer episode context
Zero data loss -- If LLM fails, observations are saved with degraded (inferred) metadata instead of being discarded
Two-tier dedup -- Jaccard similarity (5-minute window) + MinHash signatures (7-day cross-session window) prevent duplicates
Synonym expansion -- Abbreviations like K8s, DB, auth automatically expand to full forms in FTS5 search (100+ pairs including CJK↔EN cross-language mappings)
CJK synonym extraction -- Unsegmented Chinese text is scanned for known vocabulary words (数据库→database, 搜索→search, etc.) enabling cross-language memory recall
Stop-word filtering -- English stop words filtered from both TF-IDF vocabulary (reclaiming ~18% of vector dimensions) and FTS queries (preventing false negatives from noise terms like "how", "the", "does")

Platform Support

Platform	Status	Notes
Linux	Supported	Primary development and testing platform
macOS	Supported	Fully compatible (Intel and Apple Silicon)
Windows	Not supported	Uses POSIX shell scripts (`post-tool-use.sh`, `setup.sh`) and Unix file locking; WSL2 may work but is untested

Requirements

Node.js >= 20
Claude Code CLI installed and configured (claude command available)
SQLite3 support (provided by better-sqlite3, compiled on install)
Platform: Linux or macOS (see Platform Support)

Installation

Method 1: Plugin Marketplace (recommended)

/plugin marketplace add sdsrss/claude-mem-lite
/plugin install claude-mem-lite

Plugin mode manages its own hooks/runtime. On session start it only checks and reports new claude-mem-lite versions; it does not self-overwrite plugin files in place. Update plugin-mode installs through Claude's plugin workflow.

The plugin install is complete on its own — hooks, MCP tools, and the bundled slash commands (/mem, /lesson, /bug, /adopt) all run from the plugin with no second step. The slash commands invoke the bundled CLI by an absolute path resolved from the plugin directory (${CLAUDE_PLUGIN_ROOT}/cli.mjs <cmd>), so they work without anything on your PATH. A global claude-mem-lite shell command (for running queries yourself in a terminal) is optional — npm i -g claude-mem-lite — and is a separate npm install: the plugin's auto-update does not refresh it, so re-run npm i -g claude-mem-lite@latest if you want that shell command kept in sync. You do not need it for the plugin to be fully functional.

Auto-adopt fires on the first SessionStart per project (v2.82.1+). The plugin automatically writes the invited-memory sentinel (a system-authority pointer that boosts Claude's proactive use of mem_recall / mem_save) into the project's memdir — no manual /adopt needed, regardless of install path (npm, npx, /plugin, manual). Per-project opt-out: claude-mem-lite adopt --disable (--enable to re-arm). Global opt-out: export MEM_NO_AUTO_ADOPT=1. Manual /adopt remains available for re-applying after edits and for the --all batch path.

Method 2: npx (one-liner)

npx github:sdsrss/claude-mem-lite

Source files are automatically copied to ~/.claude-mem-lite/ for persistence.

Note: npx github:… installs from the repo's default branch (HEAD), which can be ahead of the latest published release. For the stable released version use the npm package (npx claude-mem-lite), or pin a release tag: npx github:sdsrss/claude-mem-lite#vX.Y.Z.

Method 3: git clone

git clone https://github.com/sdsrss/claude-mem-lite.git
cd claude-mem-lite
node install.mjs install

Source files stay in the cloned repo. Update via git pull && node install.mjs install.

What happens during installation

Install dependencies -- npm install --omit=dev (compiles native better-sqlite3)
Register MCP server -- mem-lite server with 20 tools (9 core exposed via tools/list + 11 hidden-but-callable; see the Usage section for the full table). The pre-v2.78 generic server name mem is renamed to mem-lite for namespace hygiene; the tool names themselves (mem_search, mem_recall, ...) are unchanged.
Configure hooks -- PostToolUse, SessionStart, Stop, UserPromptSubmit lifecycle hooks
Create data directory -- ~/.claude-mem-lite/ (hidden) for database, runtime, and managed resource files
Auto-migrate -- If ~/.claude-mem/ (original claude-mem) or ~/claude-mem-lite/ (pre-v0.5 unhidden) exists, migrates database and runtime files to ~/.claude-mem-lite/, preserving the original untouched
Initialize database -- SQLite with WAL mode, FTS5 indexes created on first server start

Restart Claude Code after installation to activate.

Migration

All installation methods auto-detect and migrate from previous versions:

From claude-mem (original ~/.claude-mem/):

Copy claude-mem.db → ~/.claude-mem-lite/claude-mem-lite.db (renamed)
Copy the runtime/ directory
Original ~/.claude-mem/ is preserved (no deletion, no overwrite)

From pre-v0.5 unhidden directory (~/claude-mem-lite/):

Entire directory is moved to ~/.claude-mem-lite/ (hidden)

In-place rename:

Existing claude-mem.db in ~/.claude-mem-lite/ is automatically renamed to claude-mem-lite.db

Remove old directories manually after confirming:

rm -rf ~/.claude-mem/       # original claude-mem
rm -rf ~/claude-mem-lite/   # pre-v0.5 unhidden (if not auto-moved)

Directory Structure

~/.claude-mem-lite/
  claude-mem-lite.db       # SQLite database — memory (WAL mode)
  resource-registry.db     # SQLite database — skill/agent registry
  runtime/
    session-<project>    # Active session state
    ep-<project>.json    # Episode buffer
    ep-flush-*.json      # Flushed episodes awaiting processing
    reads-<project>.txt  # Read file paths (collected on flush)
  managed/
    skills/              # Standalone skills: {name}/SKILL.md
    agents/              # Agent plugins: {group}/agents/{name}.md + skills/*/SKILL.md
    repos/               # Shallow-cloned source repos

Usage

MCP Tools (used automatically by Claude)

As of v2.70.0, the server registers 20 tools in total but only the 9 core tools appear in tools/list. The 11 hidden tools remain callable at the protocol layer (tools/call by exact name still routes normally); they're omitted from the list response so Claude Code sessions don't load 11 extra tool schemas at startup. Hidden tools are the maintenance / admin / browser surface — reach them through the CLI column in the second table.

Core (9, exposed to Claude Code)

Tool	Description
`mem_search`	FTS5 full-text search with BM25 ranking. Filters by type, project, date range, importance level.
`mem_recent`	Show most recent observations, ordered by time. Quick snapshot of latest activity.
`mem_recall`	Recall observations related to a file. Use before editing to surface past bugfixes and context.
`mem_timeline`	Browse observations chronologically around an anchor point.
`mem_get`	Retrieve full details for specific observation IDs (includes importance and related_ids).
`mem_save`	Manually save a memory/observation. Accepts `closes_deferred` array for transactional closure of deferred work.
`mem_defer`	Mark work for a future session (v2.70+). First-class carry-forward signal, surfaced in SessionStart `### Deferred Work` block.
`mem_defer_list`	List open deferred items for the current project.
`mem_defer_drop`	Drop a deferred item without fixing it; requires a `reason` for the audit trail.

Hidden-but-callable (11, CLI-routed)

Tool	CLI equivalent	Notes
`mem_update`	`claude-mem-lite update <id>`	Edit an observation in place.
`mem_stats`	`claude-mem-lite stats`	Counts, type distribution, daily activity.
`mem_delete`	`claude-mem-lite delete <id>`	Preview / confirm workflow, FTS5 cleanup.
`mem_compress`	`claude-mem-lite compress`	Roll up old low-value observations (preview default; `--execute` to apply).
`mem_maintain`	`claude-mem-lite maintain scan --ops dedup,decay`	dedup / decay / cleanup / rebuild_vectors (`scan` previews, `execute` applies).
`mem_optimize`	`claude-mem-lite optimize`	LLM-powered re-enrich / normalize / cluster-merge (preview default; `--run` to apply).
`mem_export`	`claude-mem-lite export`	JSON / JSONL dump, filters by project, type, date.
`mem_fts_check`	`claude-mem-lite fts-check <check\|rebuild>`	FTS5 integrity + rebuild.
`mem_browse`	`claude-mem-lite browse`	Tier-grouped dashboard (working / active / archive).
`mem_registry`	`claude-mem-lite registry <action>`	List / search / import / remove skills + agents.
`mem_use`	MCP only	Load a skill / agent from the registry by name.

Skill Commands (in Claude Code chat)

/mem search <query>        # Full-text search across all memories
/mem recent [n]            # Show recent N observations (default 10)
/mem recall <file>         # Show past observations for a file
/mem save <text>           # Save a manual memory/note
/mem stats                 # Show memory statistics
/mem timeline <query>      # Browse timeline around a match
/mem browse                # Tier-grouped memory dashboard
/mem <query>               # Shorthand for search
/lesson <text>             # Save a non-obvious lesson to the events table (v2.31.0)
/bug <text>                # Log a known bug + repro steps to the events table (v2.31.0)

Efficient Search Workflow

1. mem_search(query="auth bug")     -> compact ID index
2. mem_timeline(anchor=12345)       -> surrounding context
3. mem_get(ids=[12345, 12346])      -> full details

Invited Memory (v2.32+)

Opt-in mechanism that installs a slug-scoped managed block into the project's own CLAUDE.md (plus an on-demand detail doc under .claude/) so Claude Code loads the plugin's MCP-tool triggers as project instructions — a higher instruction-following authority than MCP server instructions (which are framed as tool metadata). Claude Code loads CLAUDE.md and the memdir MEMORY.md at equal weight, so steering lives in CLAUDE.md (the canonical home for project instructions) rather than polluting MEMORY.md, which is reserved for the user's own memories. The pre-v3.13 scheme wrote into MEMORY.md; it is migrated away automatically on the next SessionStart.

claude-mem-lite adopt              # install for current project
claude-mem-lite adopt --all        # install for every project under ~/.claude/projects/
claude-mem-lite adopt --status     # list adopted/disabled projects + current gating snapshot
claude-mem-lite adopt --dry-run    # preview without writing
claude-mem-lite adopt --disable    # opt out of auto-adopt for current project (writes .mem-no-auto-adopt sentinel)
claude-mem-lite adopt --enable     # re-arm auto-adopt for current project (deletes the sentinel)
claude-mem-lite unadopt            # remove sentinel + doc (runtime marker stays to honor the explicit removal)

Slash commands /adopt and /unadopt wrap the same CLI.

What adoption changes:

A … managed block is added to <cwd>/CLAUDE.md under its own ## claude-mem-lite — persistent memory header, containing a compact trigger table pointing at mem_recall / mem_save / mem_defer with their key arguments. The block is slug-scoped: only this region is managed; the rest of your CLAUDE.md is preserved verbatim, and it coexists with other plugins' blocks (e.g. code-graph-mcp) in the same file.
A <cwd>/.claude/plugin_claude_mem_lite.md detail file is written (not auto-loaded; read on demand when the CLAUDE.md block points to it). The block auto-refreshes when the shipped content drifts (version bump or template change), unless CLAUDE_MEM_NO_TEMPLATE_REFRESH=1.
Post-adopt the conservative hook layer auto-trims: MCP server instructions drop the WHEN TO USE section, SessionStart injection drops the File Lessons / Key Context sections. #ID references and the Recent table still fire so mem_get remains reachable.

When does it take effect?

The CLAUDE.md managed block and the hook-layer trim (File Lessons / Key Context / lesson suffix) apply on the next SessionStart (any new Claude Code session in the adopted project).
The MCP server instructions are built once at server boot and MCP has no "push" protocol — the WHEN TO USE / Decision rules trim only applies after Claude Code restarts and re-spawns the mem-lite MCP server. A single /exit + fresh session is enough. Same caveat applies to unadopt.

Safety:

Hash-guarded: editing the managed-block body yourself blocks automatic rewrites unless you pass --force.
Slug-scoped & dedup-guarded: only the claude-mem-lite:begin…end region is ever rewritten, and duplicate / CRLF-orphaned copies are collapsed to one. Unlike the legacy MEMORY.md scheme there is no line-budget gate — CLAUDE.md has no truncation cap.
Auto-adopt fires on the first SessionStart per project for any install path (v2.82.1+). Per-project opt-out: claude-mem-lite adopt --disable (writes a durable <memdir>/.mem-no-auto-adopt sentinel that survives marker deletion / plugin reinstalls). Global opt-out: MEM_NO_AUTO_ADOPT=1. Pre-v2.82.1 the CLAUDE_PLUGIN_ROOT gate left auto-adopt unreachable for every install.mjs-written hook (the common path) — see CHANGELOG v2.82.1.
The fallback hook layer is never removed from source — conditional trim is runtime-gated on sentinel presence, so projects without adoption get the full verbose output.

See docs/plans/2026-04-16-invited-memory-pattern.md for the full design (including the reusable template other plugins can follow).

Database Schema

Five core tables with FTS5 virtual tables for search:

observations -- Individual coding observations (decisions, bugfixes, features, etc.)

id, memory_session_id, project, type, title, subtitle,
text, narrative, concepts, facts, files_read, files_modified,
importance, related_ids, created_at, created_at_epoch,
lesson_learned, minhash_sig, access_count, compressed_into, search_aliases,
branch, superseded_at, superseded_by, last_accessed_at

session_summaries -- LLM-generated session summaries

id, memory_session_id, project, request, investigated,
learned, completed, next_steps, files_read, files_edited, notes,
remaining_items, lessons, key_decisions

sdk_sessions -- Session tracking

id, content_session_id, memory_session_id, project,
started_at, completed_at, status, prompt_counter

user_prompts -- User prompts captured via UserPromptSubmit hook

id, content_session_id, prompt_text, prompt_number

session_handoffs -- Cross-session handoff snapshots (UPSERT, max 2 per project)

project, type, session_id, working_on, completed, unfinished,
key_files, key_decisions, match_keywords, created_at_epoch

observation_files -- Normalized file membership for efficient file-based recall

obs_id, filename

observation_vectors -- TF-IDF vector embeddings for hybrid search

observation_id, vector (BLOB Float32Array), vocab_version, created_at_epoch

vocab_state -- Persisted TF-IDF vocabulary for stable vector indexing

term, term_index, idf, version, created_at_epoch

FTS5 indexes: observations_fts (title, subtitle, narrative, text, facts, concepts, lesson_learned), session_summaries_fts, user_prompts_fts

How It Works

Hook Pipeline

SessionStart
  -> Generate session ID (or save handoff snapshot on /clear)
  -> Mark stale sessions (>24h active) as abandoned
  -> Clean orphaned/stale lock files
  -> Query recent observations (24h)
  -> Inject context into CLAUDE.md + stdout

PostToolUse (every tool execution)
  -> Bash pre-filter skips noise in ~5ms (Read paths tracked to reads file)
  -> Detect Bash significance (errors, tests, builds, git, deploys)
  -> Accumulate into episode buffer
  -> Proactive file history: show past observations for edited files
  -> Flush when: buffer full (10 entries) | 5min gap | context change
  -> Collect Read file paths into episode on flush
  -> Spawn LLM episode worker for significant episodes
  -> Error-triggered recall: search memory for related past fixes

UserPromptSubmit (two parallel paths)
  -> [user-prompt-search.js] Auto-search memory via FTS5 + active file context
  -> [user-prompt-search.js] Inject relevant past observations with recency/importance weighting
  -> [user-prompt-search.js] Write injected IDs to temp file for dedup
  -> [user-prompt-search.js] L1 skill auto-load: match managed skill names in prompt
     -> Load content with portable ~ path + Read() guidance
     -> source="managed-skill|managed-agent", path="~/.claude-mem-lite/managed/..."
  -> [hook.mjs handleUserPrompt] Capture user prompt text to user_prompts table
  -> [hook.mjs handleUserPrompt] Increment session prompt counter
  -> [hook.mjs handleUserPrompt] Handoff: detect continuation intent → inject previous session context
  -> [hook.mjs handleUserPrompt] Semantic memory injection (hook-memory.mjs), deduped via temp file

Stop
  -> Flush final episode buffer
  -> Save handoff snapshot (on /exit)
  -> Mark session completed
  -> Spawn LLM summary worker (poll-based wait)

Resource Registry

The resource registry (registry.mjs, registry-retriever.mjs) indexes installed skills and agents into a searchable FTS5 database. Unlike the previous proactive dispatch system, the registry is now on-demand — it's reachable via the claude-mem-lite registry CLI (primary path for Claude Code since v2.34.0 hides the mem_registry MCP tool from tools/list) or by direct tools/call mem_registry for MCP clients that know the name.

Registry pipeline:
  -> registry-scanner.mjs discovers skills/agents on filesystem
  -> resource-discovery.mjs handles flat dirs, plugin nesting, loose .md files
  -> registry-indexer.mjs indexes content into FTS5 with metadata
  -> registry-retriever.mjs provides BM25-ranked search with synonym expansion
  -> mem_registry MCP tool exposes search/list/stats/import/remove/reindex actions

Smart invocation (three layers):
  L1 auto-load: UserPromptSubmit matches managed skill name in prompt
     -> Loads content with path="~/.claude-mem-lite/managed/.../SKILL.md"
     -> Guides: Read("path") or mem_use(name="..."), never Skill()
  L2 bridge: PreToolUse hook intercepts Skill("name") for managed resources
     -> Outputs content, prevents native handler failure
  L3 explicit: mem_use(name="...") loads full content with reload path
  Search: managed resources → Read(path), native plugins → Skill("full:name")

Composite scoring for search results: BM25 relevance (40%) + repo stars (15%) + success rate (15%) + adoption rate (10%) + freshness (10%) + exploration bonus (10%). Domain filtering ensures platform-specific resources (iOS, Go, Rust) only surface for matching projects.

Episode Encoding

Episodes are batched related operations (edits to the same file group) that get processed by a background LLM worker:

Episode buffer -> Flush to JSON -> claude -p --model haiku -> Structured observation -> SQLite

Each observation includes type, title, narrative, concepts, facts, importance (1-3), and is automatically deduplicated via two tiers: Jaccard similarity (>70% within 5 minutes) and MinHash signatures (>80% within 7 days across sessions). If the LLM call fails, a degraded observation is saved with inferred metadata (zero data loss). Related observations are linked via related_ids based on FTS5 title similarity and file overlap.

Management Commands

# Plugin install:
/plugin install claude-mem-lite       # Install / update
/plugin uninstall claude-mem-lite     # Uninstall

# git clone install:
node install.mjs install              # Install and configure
node install.mjs uninstall            # Remove (keep data)
node install.mjs uninstall --purge    # Remove and delete all data
node install.mjs status               # Show current status
node install.mjs doctor               # Diagnose issues
node install.mjs cleanup-hooks        # Remove only stale claude-mem-lite hooks from settings.json
node install.mjs update               # Force-check for updates and install them (direct install / npx mode)

# npx install:
npx claude-mem-lite                   # Install / reinstall
npx claude-mem-lite uninstall         # Remove (keep data)
npx claude-mem-lite doctor            # Diagnose issues

Notes:

Plugin mode only reports available updates; it does not self-update plugin files. To upgrade an installed plugin to the latest published version, run inside Claude Code:
```
/plugin marketplace update sdsrss
/plugin install claude-mem-lite@sdsrss
```
(The first command refreshes the local marketplace clone; the second reinstalls from it. Without the first command, /plugin install reuses the stale local clone and you stay on whichever version you originally pulled.)
Direct install / npx mode keeps auto-update enabled and uses staged replacement with rollback on install failure.
If you disabled the plugin but still have old mem hooks in ~/.claude/settings.json, run node install.mjs cleanup-hooks.

doctor

Checks Node.js version, dependencies, server/hook files, database integrity, FTS5 indexes, and stale processes.

status

Shows MCP registration, hook configuration, plugin disabled state, and database stats (observation/session counts).

Recovery (stuck install / hook errors)

If you see ERR_MODULE_NOT_FOUND on PreToolUse:Read/Edit/Skill hooks, or claude-mem-lite commands crash with import errors, you're likely hit by a partial auto-update — the updater copied new scripts but missed a sibling lib/* file, breaking the hook chain (and the next auto-update that would have healed it).

v2.84.0+ ships a repair subcommand that re-syncs from the latest GitHub release:

claude-mem-lite repair

If repair itself fails (the bin is older than v2.84.0, or the bin is also broken), run this one-liner — it pulls a fresh tarball into a temp dir and runs that tarball's install.mjs, bypassing every file on your disk:

T=$(mktemp -d) && curl -sL https://api.github.com/repos/sdsrss/claude-mem-lite/tarball | tar xz -C "$T" --strip-components=1 && node "$T/install.mjs" install

After it finishes, ~/.claude-mem-lite/ is back in sync with the latest release and claude-mem-lite repair is available for next time.

Uninstall

# Plugin:
/plugin uninstall claude-mem-lite

# git clone:
cd claude-mem-lite
node install.mjs uninstall            # Keeps ~/.claude-mem-lite/ data
node install.mjs uninstall --purge    # Deletes ~/.claude-mem-lite/ and all data

# npx:
npx claude-mem-lite uninstall
npx claude-mem-lite uninstall --purge

Data in ~/.claude-mem-lite/ is preserved by default. Delete manually if needed:

rm -rf ~/.claude-mem-lite/

Mixed-install residue (read this if you've used multiple install methods)

/plugin uninstall only removes the plugin manifest — it does not touch ~/.claude/settings.json. If you've ever run claude-mem-lite install (npx or git-clone path), hook entries pointing at ~/.claude-mem-lite/hook.mjs were written into your user-global settings, and they keep firing after /plugin uninstall. If ~/.claude-mem-lite/hook.mjs still exists they double-fire alongside the plugin; if you also ran rm -rf ~/.claude-mem-lite/ they error every session.

The safe sequence is: run claude-mem-lite uninstall first (which cleans the settings.json hooks plus the global MCP registration), then /plugin uninstall claude-mem-lite, then optionally rm -rf ~/.claude-mem-lite/.

If you already uninstalled in the wrong order, claude-mem-lite doctor flags orphan hooks under Orphan hooks: with the exact cleanup command.

Project Structure

claude-mem-lite/
  .claude-plugin/
    plugin.json      # Plugin manifest
    marketplace.json # Marketplace catalog
  .mcp.json          # MCP server definition (plugin root)
  hooks/
    hooks.json       # Hook definitions (plugin mode)
  commands/
    mem.md           # /mem command definition
  server.mjs           # MCP server: tool definitions, FTS5 search, database init
  search-scoring.mjs # Extracted search helpers: re-ranking, PRF, concept expansion
  hook.mjs             # Claude Code hooks: episode capture, error recall, session management
  hook-llm.mjs         # Background LLM workers: episode extraction, session summaries
  hook-shared.mjs      # Shared hook infrastructure: session management, DB access, LLM calls
  hook-handoff.mjs     # Cross-session handoff: state extraction, intent detection, injection
  hook-context.mjs     # CLAUDE.md context injection and token budgeting
  hook-episode.mjs     # Episode buffer management: atomic writes, pending entry merging
  hook-memory.mjs      # Semantic memory injection on user prompt
  hook-semaphore.mjs   # LLM concurrency control: file-based semaphore for background workers
  schema.mjs           # Database schema: single source of truth for tables, migrations, FTS5
  tool-schemas.mjs     # Shared Zod schemas for MCP tool validation
  tfidf.mjs            # TF-IDF vector engine: tokenization, vocabulary building, vector computation, cosine similarity, RRF merge
  tier.mjs             # Temporal tier system: activity-based time window classification
  utils.mjs            # Re-export hub: backward-compatible surface for all utility modules
  nlp.mjs              # FTS5 query building: synonym expansion, CJK bigrams, sanitization
  scoring-sql.mjs      # BM25 weight constants and type-differentiated decay half-lives
  stop-words.mjs       # Shared base stop-word set for all NLP/search modules
  synonyms.mjs         # Unified synonym source: SYNONYM_MAP (bidirectional) + DISPATCH_SYNONYMS
  project-utils.mjs    # Shared project name resolution with in-process cache
  secret-scrub.mjs     # API key, token, PEM, and credential pattern redaction
  format-utils.mjs     # String formatting: truncate, typeIcon, date/time/week formatting
  hash-utils.mjs       # MinHash signatures, Jaccard similarity for dedup
  bash-utils.mjs       # Bash output significance detection: errors, tests, builds, deploys
  # Resource registry
  registry.mjs         # Resource registry DB: schema, CRUD, FTS5, invocation tracking
  registry-retriever.mjs # FTS5 retrieval with synonym expansion and composite scoring
  registry-indexer.mjs # Resource indexing pipeline
  registry-scanner.mjs # Filesystem scanner: reads content + hashes, delegates discovery
  resource-discovery.mjs # Shared discovery layer: flat dirs, plugin nesting, loose .md files
  haiku-client.mjs     # Unified Haiku LLM wrapper: direct API or CLI fallback
  # Install & config
  install.mjs          # CLI installer: setup, uninstall, status, doctor (npx/git clone mode)
  skill.md             # MCP skill definition (npx/git clone mode)
  package.json         # Dependencies and metadata
  scripts/
    setup.sh           # Setup hook: npm install + migration (hidden dir + old dir)
    post-tool-use.sh   # Bash pre-filter: skips noise in ~5ms, tracks Read paths
    user-prompt-search.js # UserPromptSubmit hook: auto-search memory + L1 skill auto-load
    pre-skill-bridge.js  # PreToolUse hook: L2 skill bridge for managed resources
    pre-tool-recall.js   # PreToolUse hook: file lesson recall before Edit/Write
    prompt-search-utils.mjs # Shared logic: skip patterns, intent detection, name matching
    convert-commands.mjs # Converts command .md → SKILL.md in managed plugins
    index-managed.mjs  # Offline indexer for managed resources
  # Test & benchmark (dev only)
  tests/               # Unit, property, integration, contract, E2E, pipeline tests
  benchmark/           # BM25 search quality benchmarks + CI gate

Search Quality

Benchmarked on 200 observations across 30 queries (standard + hard-negative categories), measuring the production-hybrid retriever (FTS5 BM25 + TF-IDF vector + RRF) — the path mem_search / recall actually use. The CI gate (npm run benchmark:gate) runs this same path and fails on regression.

Metric	Score (production-hybrid)
Recall@10	0.90
Precision@10	0.79
nDCG@10	0.97
MRR@10	0.97
P95 search latency	~3ms

Note on the path measured. Earlier versions of this table reported the lexical FTS-only path (Precision@10 0.96, P95 0.15ms). The hybrid vector arm trades raw precision@10 for higher recall / nDCG / MRR by surfacing semantically-related candidates beyond exact lexical matches; the gate now measures the hybrid path so these numbers reflect real mem_search behavior. For field-comparable recall, see the LongMemEval section below.

Recall on LongMemEval (standard benchmark)

Beyond the in-repo micro-benchmark above, claude-mem-lite is measured on LongMemEval (Wu et al.) — a 500-question long-term-memory benchmark — so its recall is comparable to the field, not just to itself. Metric is recall_any@k: does any gold evidence session appear in the top k retrieved? This is the same session-level definition the systems we compare against report on this split — agentmemory (BM25 + vector + graph) and dense-embedding systems like MemPalace — so the rows below sit on one axis, not metric-shopped. (Note: 65% of the 500 questions have multiple gold sessions, so recall_any@k is looser than fractional recall there; all systems in this comparison report the any-hit form.) Corpus is user-turns-only (the standard raw-baseline rule). Runners: benchmark/longmemeval.mjs (lexical) and benchmark/longmemeval-rerank.mjs (rerank).

Retriever (zero embeddings)	@1	@5	@10
Lexical hybrid — FTS5 + TF-IDF + RRF	83.4%	95.2%	96.0%
+ one top-20 LLM rerank pass †	92.8%	96.8%	97.4%

n = 500 questions. The lexical row was re-measured 2026-07-18: the v3.39–v3.45 alias/synonym-pipeline work lifted it from the previously published 76.8/90.6/95.2 on the same harness and dataset (both unchanged since that run — the gain is engine-side, not metric drift). † The rerank row is the 2026-06 measurement taken against the older lexical baseline; with lexical now at 95.2 @5 its remaining headroom is ~1.6pt and a re-measurement is pending. The rerank pass hands the top 20 lexical candidates to a single Haiku call (~1.4 s/query) that reorders them; it is never worse than the lexical baseline by construction — any LLM or parse failure falls back to the original candidate order.

Stricter metric, for the record. The rows above are recall_any@k — does any gold session reach the top k — the metric agentmemory and MemPalace publish, so the comparison is like-for-like. Under the stricter standard recall@k (|gold ∩ top-k| / |gold|, the fraction of all gold sessions retrieved), the lexical stack scores @1 = 52.9% / @5 = 87.8% / @10 = 91.0%. The whole gap is the 65% of questions with multiple gold sessions — any-hit needs one, fractional needs them all, and @1 is capped at 1/|gold| there; single-gold question types score identically under both. benchmark/longmemeval.mjs reports both columns (the rerank row's fractional is not yet measured).

On embeddings, honestly. With no LLM in the loop, our zero-embedding lexical stack now ties the BM25 + vector + graph hybrid (agentmemory, 95.2% @5) at the same retrieval stage; a dense-embedding baseline (MemPalace, ~96.6% @5) still leads by ~1.4pt. The remaining gap concentrates in paraphrase (single-session-preference is our lowest category at 80.0% @5). The rerank row's point stands: a single cheap LLM call reorders the top-20 lexical candidates because the candidate set is already rich enough that ranking, not recall, is the bottleneck. An embedding-plus-rerank stack still leads when both sides spend an LLM call; the takeaway is that claude-mem-lite reaches embedding-competitive recall with no vector model, no knowledge graph, no Python, and no external service.

Per-category any@5, lexical (2026-07-18 run): knowledge-update 100.0 · single-session-user 100.0 · multi-session 94.7 · single-session-assistant 94.6 · temporal-reasoning 94.0 · single-session-preference 80.0.

Development

npm run lint              # ESLint static analysis
npm test                  # Run full test suite (vitest)
npm run test:smoke        # Run 5 core smoke tests
npm run test:coverage     # Run tests with V8 coverage (≥75% lines/functions, ≥65% branches)
npm run benchmark         # Run full search quality benchmark
npm run benchmark:gate    # CI gate: fails if metrics regress beyond 5% tolerance

Environment Variables

Variable	Description	Default
`CLAUDE_MEM_DIR`	Custom data directory. All databases, runtime files, and managed resources are stored here.	`~/.claude-mem-lite/`
`CLAUDE_MEM_MODEL`	LLM model for background calls (episode extraction, session summaries). Accepts `haiku` or `sonnet`.	`haiku`
`ANTHROPIC_API_KEY`	Anthropic API key. When set, all background LLM calls go directly to the Anthropic Messages API (with prompt caching). Highest priority.	(unset → CLI)
`OPENROUTER_API_KEY`	OpenRouter API key (OpenAI-compatible). Used for background LLM calls when `ANTHROPIC_API_KEY` is not set. If neither key is set, calls fall back to the `claude -p` CLI.	(unset)
`OPENROUTER_MODEL`	Overrides the OpenRouter model slug for all background calls (e.g. `openai/gpt-4o-mini`, `qwen/qwen-2.5-72b-instruct`). When unset, the `CLAUDE_MEM_MODEL` tier maps to `anthropic/claude-haiku-4.5` (haiku) or `anthropic/claude-sonnet-4.5` (sonnet).	(tier default)
`CLAUDE_MEM_DEBUG`	Enable debug logging (`1` to enable).	(disabled)
`MEM_QUIET_HOOKS`	Low-noise hooks. `1` drops the `File Lessons` / `Key Context` sections from SessionStart injection, the lesson suffix from `[mem] Related memories`, and the `WHEN TO USE` / `Decision rules` blocks from MCP server instructions. IDs and the `Recent` table still surface so `mem_get(ids=[…])` remains reachable. Intended for users running the invited-memory adopt path or who otherwise want minimal auto-injection. Since v2.82.0 this env no longer gates auto-adopt — use `MEM_NO_AUTO_ADOPT=1` for that.	(disabled)
`MEM_NO_AUTO_ADOPT`	Global opt-out for auto-adopt (v2.82.0+). `1` prevents the first-SessionStart auto-write of the invited-memory sentinel across projects. For per-project opt-out use instead (writes a durable sentinel that survives marker deletion).

FAQ

What is a memory system for Claude Code?

A memory system lets Claude Code remember context — coding decisions, bug fixes, file history — across sessions. By default Claude Code's context resets each session; claude-mem-lite persists observations to a local SQLite database and re-injects them at session start and on relevant prompts.

Does Claude Code have built-in long-term memory?

No. Claude Code's CLAUDE.md and MEMORY.md files act as static instruction memory, but there is no native dynamic recall of past sessions, bug fixes, or decisions. claude-mem-lite adds that layer via MCP and hooks, with no manual note-taking required.

How is claude-mem-lite different from mem0 or MCP's reference memory server?

mem0 and the MCP memory server are general-purpose LLM memory frameworks designed for any client. claude-mem-lite is purpose-built for Claude Code's hook lifecycle: it captures episodes (batched tool calls), uses domain-specific synonym expansion for code terms (K8s, DB, 数据库, ...), and surfaces past observations proactively before file edits via the PreToolUse:Edit hook.

Why "lite"? What did the original claude-mem do differently?

The original called an LLM on every tool use with raw JSON inputs. claude-mem-lite batches 5–10 operations per LLM call, uses a smaller model (Haiku), and runs a deterministic code-level filter before sending anything to the model. Net result: an estimated ~600× lower cost (an architecture estimate from the cost model above, not a measured benchmark) with equivalent search quality. See the Architecture comparison above.

Does this work cross-project? Cross-machine?

Project-scoped by default — each project has its own memory namespace. Single-machine only (SQLite, not networked). Use mem_export (JSON / JSONL) to back up or migrate between machines.

What about privacy? Does it call external APIs?

Only the Haiku summarization step calls Anthropic's API (or the local claude -p CLI if no API key is set). All search, storage, and retrieval is local SQLite — no telemetry, no third-party services.

中文常见问题

Claude Code 怎么跨会话记住内容？ 默认不能。claude-mem-lite 通过 MCP 协议和钩子自动把决策、bug 修复、文件历史持久化到本地 SQLite，下次会话开始时再注入。

和 mem0、官方 MCP memory server 有什么区别？ 那两个是通用 LLM 记忆框架；claude-mem-lite 是为 Claude Code 钩子生命周期定制的：批量 episode 处理、代码领域同义词扩展（K8s/DB/数据库等）、文件编辑前主动召回相关历史。

支持中文吗？ 完整支持。FTS5 + 中英文同义词扩展（100+ 对，含 CJK ↔ EN 跨语言映射），中文记忆也可用英文关键词召回，反之亦然。

License

MIT

File tree

461

sdsrss/claude-mem-liteView on GitHub ↗

.claude-plugin/
  marketplace.json
  plugin.json
.github/
  workflows/
    ci.yml
    publish.yml
.gitignore
.mcp.json
.npmignore
adopt-cli.mjs
adopt-content.mjs
bash-utils.mjs
benchmark/
  adoption-cosine.mjs
  adoption-estimator.mjs
  adoption-overlap.mjs
  adoption-rankers.mjs
  adoption-replay.mjs
  baseline-vocab-mismatch.json
  baseline.json
  benchmark.mjs
  ci-gate.mjs
  cite-recall-baseline.json
  cite-recall.mjs
  cjk-straddle-prevalence.mjs
  confine-tools.js
  cross-source-probes.mjs
  datasets/
    download-longmemeval.sh
    README.md
  deferred-probes.mjs
  denoise-ab.mjs
  efficacy-commits.json
  efficacy-harness.mjs
  efficacy-observational.mjs
  efficacy-power.mjs
  efficacy-README.md
  events-pipeline-probes.mjs
  fixtures/
    aacab0c-bug-reintroduce.patch
    bac2e85-bug-reintroduce.patch
    longmemeval-sample.json
    rewrites-vocab-mismatch.json
    seed-data-cjk.json
    seed-data.json
    test-queries-cjk.json
    test-queries-vocab-mismatch.json
    test-queries.json
    ups-identifier-queries.json
  longmemeval-rerank.mjs
  longmemeval.mjs
  multiscript-guard.mjs
  ups-ab.mjs
CHANGELOG.md
CLAUDE.md
claudemd.mjs
cli/
cli-path.mjs
cli.mjs
  activity.mjs
  common.mjs
  doctor.mjs
  fts-check.mjs
commands/
  adopt.md
  bug.md
  lesson.md
  mem.md
  memory.md
  tools.md
  unadopt.md
  update.md
deep-search.mjs
docs/
  plans/
    2026-04-16-invited-memory-pattern.md
    baselines/
      v2.30.1.json
  superpowers/
    plans/
      2026-03-26-pretooluse-file-recall.md
      2026-03-31-llm-database-optimization.md
    specs/
      2026-03-21-phase2-tfidf-vector-search-design.md
      2026-03-21-three-tier-memory-and-browse-design.md
      2026-03-26-pretooluse-file-recall-design.md
      2026-03-28-smart-ingestion-design.md
      2026-03-31-llm-database-optimization-design.md
  templates/
    invited-memory-template.md
eslint.config.mjs
experiment/
  .gitignore
  analyze-results.mjs
  corpus/
    example-fk-cascade.task.json
    README.md
    shuffled-pool.json
  lib/
    arms.mjs
    metrics.mjs
    real-deps.mjs
    runner.mjs
    seed-db.mjs
    stats.mjs
  README.md
  run-experiment.mjs
  task-schema.json
format-utils.mjs
haiku-client.mjs
hash-utils.mjs
hook-context.mjs
hook-episode.mjs
hook-handoff.mjs
hook-llm.mjs
hook-memory.mjs
hook-optimize.mjs
hook-precompact.mjs
hook-semaphore.mjs
hook-shared.mjs
hook-update.mjs
hook.mjs
hooks/
  hooks.json
install-metadata.mjs
install.mjs
knip.json
lib/
  activity.mjs
  atomic-write.mjs
  binding-probe.mjs
  citation-tracker.mjs
  cite-back-hint.mjs
  cli-flags.mjs
  compress-core.mjs
  db-backup.mjs
  dedup-constants.mjs
  deferred-work.mjs
  delete-core.mjs
  doctor-benchmark.mjs
  doctor-drift.mjs
  edge-attribution.mjs
  efficacy-arms.mjs
  efficacy-bridge-select.mjs
  err-sampler.mjs
  events-injection.mjs
  export-columns.mjs
  file-edge-match.mjs
  file-intel.mjs
  git-state.mjs
  hook-telemetry.mjs
  id-routing.mjs
  import-jsonl.mjs
  json-shapes.md
  lesson-bridge.mjs
  lesson-idents.mjs
  low-signal-patterns.mjs
  maintain-core.mjs
  mem-override.mjs
  metrics.mjs
  native-binding-hint.mjs
  obs-types.mjs
  observation-write.mjs
  persist-reminder.mjs
  plan-reader.mjs
  private-strip.mjs
  proc-lock.mjs
  recall-core.mjs
  recent-core.mjs
  release-digest.mjs
  reread-guard.mjs
  resolve-data-dir.mjs
  rrf.mjs
  save-enrich.mjs
  save-nudge.mjs
  save-observation.mjs
  scrub-record.mjs
  search-core.mjs
  startup-dashboard.mjs
  stats-core.mjs
  stats-quality.mjs
  summary-extractor.mjs
  task-imperative.mjs
  task-reader.mjs
  timeline-core.mjs
  tmp-fixture-sweep.mjs
  upgrade-banner.mjs
LICENSE
llms.txt
mem-cli.mjs
memdir.mjs
nlp.mjs
package-lock.json
package.json
plugin-cache-guard.mjs
project-utils.mjs
README.md
README.zh-CN.md
registry/
registry-enricher.mjs
registry-github.mjs
registry-importer.mjs
registry-recommend.mjs
registry-retriever.mjs
registry-scanner.mjs
registry.mjs
  preinstalled.json
rerank.mjs
resource-discovery.mjs
schema.mjs
scoring-sql.mjs
scripts/
  convert-commands.mjs
  extract-repos.mjs
  hook-launcher.mjs
  index-managed.mjs
  launch-preflight.mjs
  launch.mjs
  mock-claude.mjs
  p0-forward-probe.mjs
  post-tool-recall.js
  post-tool-use.sh
  pre-agent-inject.js
  pre-commit.sh
  pre-skill-bridge.js
  pre-tool-recall.js
  prompt-search-utils.mjs
  setup.sh
  sign-release.mjs
  smoke-tarball.mjs
  user-prompt-search.js
search-engine.mjs
search-scoring.mjs
secret-scrub.mjs
server/
server.mjs
  fts-check.mjs
skill.md
skip-tools.mjs
source-files.mjs
stop-words.mjs
synonyms.mjs
tests/
  activity-promote.test.mjs
  activity.test.mjs
  adopt-cli.test.mjs
  adopted-detection.test.mjs
  adoption-cosine.test.mjs
  adoption-estimator.test.mjs
  adoption-imperative-rank.test.mjs
  adoption-overlap.test.mjs
  adoption-rankers.test.mjs
  adoption-replay.test.mjs
  adoption-searchbyfts-snapshot.test.mjs
  atomic-write.test.mjs
  audit-fixes.test.mjs
  bash-utils-signif.test.mjs
  benchmark-baseline-age.test.mjs
  benchmark-deep-search.test.mjs
  benchmark-longmemeval-rerank.test.mjs
  benchmark-longmemeval.test.mjs
  benchmark-multiscript.test.mjs
  benchmark-production-hybrid.test.mjs
  benchmark-splits.test.mjs
  benchmark-vocab-mismatch.test.mjs
  browse.test.mjs
  citation-decay-immediate.test.mjs
  citation-decay-text-floor.test.mjs
  citation-decay-userprompt-e2e.test.mjs
  citation-decay.test.mjs
  citation-funnel.test.mjs
  citation-promote-r4.test.mjs
  citation-stats-cli.test.mjs
  citation-tracker-userprompt.test.mjs
  citation-tracker.test.mjs
  cite-back-hint.test.mjs
  cite-factor.test.mjs
  cite-recall-error-recall.test.mjs
  cite-recall-imperative.test.mjs
  cjk-precision.test.mjs
  claudemd.test.mjs
  cli-defer.test.mjs
  cli-e2e.test.mjs
  cli-flags.test.mjs
  cli-path-invocation.test.mjs
  cli-routing-contract.test.mjs
  cli-write-scrub.test.mjs
  cli.test.mjs
  compress-core.test.mjs
  confine-tools.test.mjs
  context-fallback-lowsignal-r3.test.mjs
  contract.test.mjs
  date-bounds-tz.test.mjs
  db-backup.test.mjs
  deep-search-auto.test.mjs
  deep-search-rerank.test.mjs
  deep-search.test.mjs
  deferred-work.test.mjs
  delete-core.test.mjs
  denoise-ab.test.mjs
  doctor-benchmark.test.mjs
  doctor-drift.test.mjs
  doctor-summary.test.mjs
  domain-modules.test.mjs
  e2e.test.mjs
  edge-attribution.test.mjs
  efficacy-arms.test.mjs
  efficacy-bridge-select.test.mjs
  ensuredb-deferred-cleanups.test.mjs
  err-sampler.test.mjs
  error-recall-format.test.mjs
  events-consumption-r5.test.mjs
  events-fts-selfheal-r5.test.mjs
  events-injection.test.mjs
  events-pipeline-probes.test.mjs
  experiment-metrics.test.mjs
  experiment-runner.test.mjs
  experiment-stats.test.mjs
  export-restore-text-r4.test.mjs
  file-intel.test.mjs
  fixtures/
    sample-claude-jsonl/
      sample.jsonl
  fts-unmatchable-token.test.mjs
  get-time-format.test.mjs
  git-state.test.mjs
  global-setup.mjs
  haiku-client.test.mjs
  handoff-git-anchor-r3.test.mjs
  handoff-simulation.test.mjs
  handoff-window-percc-r3.test.mjs
  handoff.test.mjs
  hook-context.test.mjs
  hook-episode.test.mjs
  hook-latency.test.mjs
  hook-launcher.test.mjs
  hook-llm.test.mjs
  hook-optimize-project-filter.test.mjs
  hook-optimize.test.mjs
  hook-precompact.test.mjs
  hook-semaphore.test.mjs
  hook-shared.test.mjs
  hook-task-imperative.test.mjs
  hook-telemetry.test.mjs
  hook-update.test.mjs
  hook-upgrade-banner.test.mjs
  hooks-pretool-whitelist-sync.test.mjs
  hybrid-search.test.mjs
  import-graph.test.mjs
  import-jsonl-bom-r4.test.mjs
  import-jsonl.test.mjs
  injection-tracking.test.mjs
  install-bsqlite-probe.test.mjs
  install-bumpfield.test.mjs
  install-e2e.test.mjs
  install-ergonomics.test.mjs
  install-hook-scripts.test.mjs
  install-legacy-db-backup.test.mjs
  install-lifecycle.test.mjs
  integration-scenarios.test.mjs
  integration.test.mjs
  is-mem-hook-r3.test.mjs
  launch-preflight.test.mjs
  lesson-bridge.test.mjs
  lesson-idents.test.mjs
  lifecycle-e2e.test.mjs
  llm-episode-narrative-preserve-r3.test.mjs
  low-signal-block.test.mjs
  low-signal-sync.test.mjs
  maintain-core.test.mjs
  mcp-export-parity-r5.test.mjs
  mcp-protocol.test.mjs
  mcp-save-limits.test.mjs
  mcp-tools-snapshot.test.mjs
  mem-use.test.mjs
  memdir.test.mjs
  memory-inject.test.mjs
  memory-input-guard.test.mjs
  meta-trigger-r3.test.mjs
  metrics.test.mjs
  native-binding-hint.test.mjs
  noise-gauge-r5.test.mjs
  normalize-gate-project.test.mjs
  npm-tarball-completeness.test.mjs
  obs-types-invariant.test.mjs
  observation-files.test.mjs
  optimize-preserve-r3.test.mjs
  persist-reminder.test.mjs
  phase1-temporal.test.mjs
  plan-reader.test.mjs
  plugin-cache-guard.test.mjs
  plugin-manifest.test.mjs
  post-tool-recall.test.mjs
  post-tool-use-disabled.test.mjs
  pre-agent-inject.test.mjs
  pre-skill-bridge.test.mjs
  pre-tool-recall-bind.test.mjs
  pre-tool-recall-bridge.test.mjs
  pre-tool-recall-defang.test.mjs
... 87 more

claude-mem-lite adopt --disable

<memdir>/.mem-no-auto-adopt

claude-mem-lite

Commands

claude-mem-lite

Commands

Hooks

MCP

README

claude-mem-lite

Why claude-mem-lite?

Architecture comparison

Token & cost efficiency

Quality comparison

Design philosophy

Comparison: memory systems for AI coding agents

Features

Platform Support

Requirements

Installation

Method 1: Plugin Marketplace (recommended)

Method 2: npx (one-liner)

Method 3: git clone

What happens during installation

Migration

Directory Structure

Usage

MCP Tools (used automatically by Claude)

Skill Commands (in Claude Code chat)

Efficient Search Workflow

Invited Memory (v2.32+)

Database Schema

How It Works

Hook Pipeline

Resource Registry

Episode Encoding

Management Commands

doctor

status

Recovery (stuck install / hook errors)

Uninstall

Mixed-install residue (read this if you've used multiple install methods)

Project Structure

Search Quality

Recall on LongMemEval (standard benchmark)

Development

Environment Variables

FAQ

What is a memory system for Claude Code?

Does Claude Code have built-in long-term memory?

How is claude-mem-lite different from mem0 or MCP's reference memory server?

Why "lite"? What did the original claude-mem do differently?

Does this work cross-project? Cross-machine?

What about privacy? Does it call external APIs?

中文常见问题

License

File tree