toon-memory
> The Continuity Layer for AI Agents — AI agents shouldn't have to relearn your project every session.
Table of Contents
- Overview
- Blog Post
- Features
- Installation
- Supported Agents
- MCP Tools
- Coordinación multi-sesión
- Memory Graph (recall basado en grafo)
- Tips & Best Practices
- CLI Commands
- Configuration
- How It Works
- Why TOON?
- Troubleshooting
- FAQ
- Development
- Contributing
- Security & Privacy
- License
Overview
Ever had that feeling where your AI agent forgets everything from yesterday's session? You explain the same architecture decision for the third time, and it still suggests the approach you already rejected?
toon-memory fixes this. It's the Continuity Layer for AI Agents — a lightweight system that preserves your project's knowledge, decisions, and conventions across sessions, so every session starts where the last one ended. Fully local and private, over MCP — no cloud, no server.
📖 Read the documentation
Real-world use cases
| Scenario | What toon-memory does |
|---|---|
| Design debates | "We chose Redis over Memcached because of pub/sub support" |
| Framework choices | "This project uses Zod for validation, not Joi" |
| Bug fixes | "Redis pool exhaustion — fix was max_connections=20" |
| Architecture notes | "Broker service uses RESP protocol, not HTTP" |
| Onboarding | "The deploy script lives in scripts/deploy.sh" |
| Team context | "PR #142 reverted the caching change — don't re-add it" |
Blog Post
Read How toon-memory Makes Your AI Agent Smarter to see a real-world demo of persistent memory in action.
Features
- A complete memory toolkit — Full memory management via Model Context Protocol, including
memory_smart_recall(unified recall with session bias),memory_sessionsfor multi-session coordination,context_*tools for one-call context generation (briefing, diff, focus, health audit, export),memory_compress(LLM-powered compression),memory_consolidate(deterministic dedup/merge/cleanup),memory_primer(auto-injected context),memory_merge_sessions(cross-session merge),memory_pin/memory_unpin(pin important entries with priority 1-5),memory_checkpoint(session snapshot with 7d TTL),memory_search(unified search with tag filters + session bias),memory_tag(batch tag operations),memory_export_gist/memory_import_gist(GitHub Gist sync),memory_secret(encrypted secrets vault),memory_export_global/memory_import_global(cross-project conventions),memory_forget(soft/hard delete, restore, supersede),memory_reflect(staleness/quality reflection), andmemory_promote(auto-promote low-confidence drafts) - MCP Resources — Read memory as context without tool invocations, including a System Primer (auto-generated knowledge map)
- 22 agents supported — OpenCode, VS Code, Claude Code, Cursor, Windsurf, Cline, Continue, Codex CLI, Gemini CLI, Zed, Antigravity, Aider, KiloCode, OpenClaw, Kiro, Qwen, Kimi, Goose, Junie, Amp, Grok, Trae
- Interactive installer — Select which agents to configure from a menu
- SessionStart hooks — Auto-reminders for Claude Code, Codex CLI, Gemini CLI, Antigravity
- TOON format — 22% fewer tokens than JSON (measured), better LLM comprehension
- Per-project memory — Each project gets its own memory file
- Zero config — Just install and use
- Auto gitignore — Automatically adds
.toon-memory/memory/to.gitignore - Date filtering — Search memory by date range
- Auto-archive — Old entries (>30 days), expired TTL entries, or 100+ entries moved to archive automatically
- Encryption — AES-256-GCM encryption for sensitive data
- Watch mode — Auto-backup every N minutes
- Memory TTL — Configurable per-entry expiration (7d, 30d, or exact dates)
- Tag inference — Auto-detect tags from content when tags are empty (built-in vocabulary + project dependencies)
- Memory diff — See what changed since your last session
- Related entries — Auto-suggest related memories when saving
- Memory graph — Connect entries with
links/[[key]]refs;memory_recallcan expand a relationship-aware subgraph for more precise, lower-token recall (no embeddings, no LLM) - Token-efficient recall —
memory_recall({ compact: true })returns numeric-indexed entries, dropsid/date/file, renders graph edges as->2, and truncates graph neighbors to snippets - BM25 + centrality ranking — Recall re-ranks by BM25 relevance and graph centrality (hubs surface even without the query word); per-hop decay keeps distant nodes low
- Auto-tag from dependencies —
toon-memory initscanspackage.json/Cargo.toml/requirements.txt/go.modand writes a project vocabulary so entries mentioning a dependency get auto-tagged with it - Smart Recall —
memory_smart_recallcombines BM25 + graph + decay + quality in one call; the LLM calls this at the start of every task - Quality scoring — Every entry gets a 0–1 quality score based on structure (tags, links, content specificity, recency, access count); high-quality entries surface first
- Merge-dedup — Saving with the same
keymerges attributes (union of tags, max confidence, latest date, combined links) instead of overwriting - Near-duplicate detection — Consolidation detects near-duplicates via Jaccard similarity (threshold 0.7) and merges them
- Confidence score — Each entry tracks reliability: user-asserted = 1.0, inferred = 0.65–0.75
- LLM-powered compression —
memory_compressuses AI to summarize long entries;memory_consolidate(mode: "low-quality")does batch cleanup deterministically - Cross-session merge —
memory_merge_sessionsmerges observations across parallel sessions for a file - GitHub Gist sync —
memory_export_gistandmemory_import_gistsync memory entries via GitHub Gist (zero dependencies) - Verbatim mode —
config.verbatimpreserves original entries instead of overwriting on save - Context generation tools —
context_generate(full briefing),context_diff(incremental),context_focus(targeted),context_health(audit),context_export(markdown) — each replaces 5-6 manual tool calls. Zero LLM, pure deterministic aggregation - System Primer — Auto-injected at session start via
systemPrimer(), showing top 5 memories for instant context - Path Scoping — Entries can be scoped to file paths via glob patterns (
path_scope); recall filters by scope automatically - Budget Control — Three output levels:
budget: "tiny"(key+1 line, ~50 tokens),"normal"(compact with tags/edges),"deep"(all fields with origin/scope/status). Backward compatible withcompact: true - Origin Tracking — Each entry tracks its origin (
human,agent,inferred); human assertions get a quality boost - Soft Delete —
memory_forgetsoft-deletes by default (setsstatus=obsolete). Restore withmemory_forget(key, action: "restore"), hide withaction: "soft", permanent removal viaaction: "hard" - Enhanced Health Audit —
context_healthnow detects missing-evidence (path_scope without file) and stale-claims (overlapping content in same category) - Typed graph edges — Edges carry types (
superseded_by,supersedes,relates), written astype:keyin the graph. Explicitlinksbecomerelates:key, so you can tell how entries are related, not just that they are - RRF ranking — Recall fuses BM25 (×3) and graph-centrality ranks with Reciprocal Rank Fusion and an adaptive
k = clamp(3..60, round(sqrt(n))). Benchmark (8 gold queries): nDCG 0.776, MRR 0.917 — exact parity with the previous linear scoring. Passrrf: falseto fall back - Memory reflect —
memory_reflectranks entries by staleness, quality, and over-connection to surface what needs attention or cleanup. Deterministic, zero LLM - Memory supersede —
memory_forget(key, action: "supersede", new_key)marks an entry as replaced by a newer one (superseded_bylink +supersededOndate).memory_recall({ as_of })re-includes old entries for point-in-time queries before their supersession - Auto-promote —
memory_promotepromotes low-confidence drafts to active entries deterministically (threshold 0.65, Jaccard dedup), withdryRunby default - Explain WHY —
memory_recall/memory_smart_recallacceptexplain: trueand append a deterministic reason line to every returned entry (↳ 100% relevance · used 14× · used today · importance HIGH) — why it was retrieved, no LLM - Token budgets —
budget_tokenscaps the recall output by estimated token count; entries accumulate greedily and the tail that would exceed the budget is dropped (0= no limit) - Version supersession —
memory_consolidate(mode: "versions")detects entries describing the same subject at different library versions (e.g. "Use React 18" vs "Use React 19") and retires the older ones in favor of the newest - Negative memories — a
warningcategory for "do NOT do this" facts;warningentries get a recall boost so the agent sees the landmines before repeating them - Language + folder ranking — recall boosts entries written in the same script family (latin/CJK/cyrillic/…) and entries whose
path_scopematches the current file - Explicit importance —
memory_remember({ importance })setscritical,high,medium, orlow. Critical decisions surface first (+0.3), low notes stay out of the way (−0.1); empty = auto (recency + frequency). Re-saving keeps the higher level - Evidence layer — every
memory_remembersave is annotated with an evidence level:verifiedwhen its referenced file exists on disk,unverifiedwhen it doesn't,conflictwhen it overlaps a warning or critical/high decision. Conflicts get a +0.15 recall boost (verified +0.03, unverified −0.02) and a ⚠️ CONTRADICTION warning on save — but never block the write - Secrets vault —
memory_secretstores credentials in an encrypted sidecar (secrets.toon, AES-256-GCM) sodata.toonstays a readable open format while sensitive values never hit plaintext - Global memory import/export —
memory_export_globalwrites project memory to~/.toon-memory/memory/global.toon;memory_import_globalpulls cross-project conventions back with a one-shot, deterministic, offline merge (never a live dual source) - ~1 MB install — three tiny prompt packages (
@inquirer/checkbox/select/confirm); the MCP SDK, zod, and the TOON parser are bundled into the shipped binary — a singlenpm i -gdownloads ~1 MB (was ~14 MB) and lands ~4.4 MB on disk (was ~33 MB)
Installation
1. Install```bash
macOS / Linux
curl -fsSL https://raw.githubusercontent.com/LuiggiVal08/toon-memory/main/install.sh | sh
Windows (PowerShell)
irm https://raw.githubusercontent.com/LuiggiVal08/toon-memory/main/install.ps1 | iex
Or with npm (any platform)
npm i -g toon-memory
> **Tip:** The npm install is the most reliable method. The curl/irm scripts are convenience wrappers.
> **Size:** A bare `npm i -g toon-memory` downloads ~1 MB and installs ~4.4 MB — three tiny prompt packages; everything else (MCP SDK, zod, TOON parser) ships bundled.
### 2. Configure your agent(s)```bash
# Interactive installer — detects agents and configures MCP
npx toon-memory
The installer will:
1. Detect which AI agents you have installed
2. Ask which ones to configure
3. Add the MCP server config automatically
3. Use it
That's it! In your next agent session, try:```bash
memory_stats # See what's in memory
memory_recall # Search memory before reading files
memory_remember # Save important decisions
> **Tip:** Always run `memory_recall` at the start of a session. Your agent will have context from previous sessions instantly.
### MCP Client Quick Setup
#### Cursor
Add to `.cursor/mcp.json`:```json
{
"mcpServers": {
"toon-memory": {
"command": "npx",
"args": ["-y", "toon-memory", "mcp"]
}
}
}
Claude Desktop
Add to claude_desktop_config.json:```json
{
"mcpServers": {
"toon-memory": {
"command": "npx",
"args": ["-y", "toon-memory", "mcp"]
}
}
}
#### Windsurf
Add to `~/.codeium/windsurf/mcp_config.json`:```json
{
"mcpServers": {
"toon-memory": {
"command": "npx",
"args": ["-y", "toon-memory", "mcp"]
}
}
}
Supported Agents
| Agent | Config Location | Format | Hooks | Auto-Setup |
|---|---|---|---|---|
| OpenCode | .opencode/opencode.json + .opencode/plugins/toon-memory.ts |
Plugin | SessionStart (plugin, no top-level hooks) |
✅ |
| VS Code / Copilot | .vscode/mcp.json |
JSON | — | ✅ |
| Claude Code | .mcp.json (MCP) + .claude/settings.json (hooks) |
JSON | SessionStart + PostToolUse + Stop | ✅ |
| Cursor | .cursor/mcp.json |
JSON | — | ✅ |
| Windsurf | ~/.codeium/windsurf/mcp_config.json |
JSON | — | ✅ |
| Cline | .cline/mcp.json |
JSON | — | ✅ |
| Continue | .continue/config.json |
JSON | — | ✅ |
| Codex CLI | .codex/config.toml |
TOML | SessionStart + PostToolUse + Stop ([[hooks]] event=) |
✅ |
| Gemini CLI | .gemini/settings.json |
JSON | SessionStart + PostToolUse + Stop (hooks.*) |
✅ |
| Zed | ~/.config/zed/settings.json |
JSONC | — | ✅ |
| Antigravity | .agents/mcp_config.json + .agents/hooks.json |
hooks.json | PreInvocation + PostToolUse + Stop (no SessionStart event) | ✅ |
| Aider | — | — | — | 📝 Instructions |
| KiloCode | ~/.kilocode/mcp_settings.json |
JSON | — | ✅ |
| OpenClaw | .openclaw.json |
JSON | — | ✅ |
| Kiro | .kiro/settings/mcp.json |
JSON | — | ✅ |
> Tip: You can configure toon-memory for multiple agents at the same time. Each agent gets the same shared memory file at .toon-memory/memory/.
MCP Tools
Tool · Description
memory_remember · Save a decision, pattern, bug, knowledge, or warning (negative "do NOT do this" memory, recalled with a boost) — optional TTL, auto-tag inference, links to build the memory graph, merge-dedup on same key, auto quality score and confidence. Write-path intelligence: each save is annotated with an evidence level — verified when the referenced file exists on disk, unverified when it doesn't, conflict when it overlaps a warning or critical/high decision (recalled with a boost and surfaced with a ⚠️ CONTRADICTION warning, but never blocks the write)
memory_recall · Search memory (use BEFORE reading files, filters expired TTL). mode: "graph" expands a relationship-aware subgraph for higher precision. budget: "tiny" · "normal" · "deep" controls output verbosity (backward compat with compact: true). path_scope filters by glob pattern. sessionBias boosts entries from the current git branch. explain: true appends a per-entry reason line (why it was retrieved). budget_tokens caps output by estimated tokens (0 = no limit). Quality-weighted ranking
memory_smart_recall · Unified recall: BM25 + graph + decay + quality in one call. sessionBias boosts entries from the current git branch. explain: true appends per-entry reasons, budget_tokens caps output by estimated tokens. Use at the START of every task. Returns compact, token-efficient output
memory_forget · Lifecycle ops by key or id: action: "soft" (default) marks obsolete, "hard" permanently removes, "restore" brings back to active, "supersede" retires it with a superseded_by link to new_key
memory_stats · View memory state (including TTL stats, quality distribution, origin/status breakdown, cold memories below quality/access thresholds, and hit rate / duplicate / obsolete metrics)
memory_summary · Save/retrieve file summaries
memory_archive · Archive old entries (>30 days) and expired TTL entries
memory_diff · Show changes since a date (24h, 7d, or exact date)
memory_suggest · Find related entries for a given context
memory_encrypt · Enable AES-256-GCM encryption
memory_decrypt · Disable encryption
memory_backup · Create timestamped backup of memory file (auto-prunes to 10 most recent)
memory_captured · List activity auto-captured by hooks (opt-in) or clear the log
memory_checkpoint · Session checkpoint: creates a snapshot of current memory state with 7d TTL. Useful for rollback reference during long sessions
memory_consolidate · Cleanup ops, deterministic (no LLM): mode: "identical" (default) dedupes identical-content entries, "similar" merges near-duplicates (Jaccard >50%), "low-quality" batch-removes low-quality entries (minQuality, dryRun), "versions" retires older library-version entries in favor of the newest
memory_sessions · Show active agent sessions (branch, files, last-seen) and soft conflicts for parallel work
memory_compress · LLM-powered two-step compression: summarize + overwrite. Uses anthropic/openai CLI if available, otherwise returns prompt for manual compression
memory_primer · One-call context primer: top memories + categories + session file changes. Auto-injected at session start
memory_merge_sessions · Merge observations across parallel sessions for a file. Deduplicates and optionally auto-promotes to memory
memory_export_gist · Export memory entries to a GitHub Gist (public or private). Uses GITHUB_TOKEN or gh CLI
memory_import_gist · Import entries from a GitHub Gist. Merges with existing entries (union of tags, max confidence)
memory_secret · Encrypted secrets vault (secrets.toon, AES-256-GCM): store/get/list/forget. Keeps data.toon readable while sensitive values stay encrypted at rest. Requires TOON_MEMORY_KEY
memory_export_global · Write current project memory to the global file (~/.toon-memory/memory/global.toon). One-shot share of cross-project conventions
memory_import_global · Merge cross-project conventions from the global file into this project (one-shot, deterministic, offline). merge: false replaces instead
memory_graph_path · BFS shortest path between two entries in the knowledge graph. Shows how concepts are connected
context_brief · One-call context briefing: memory + sessions + health in compact markdown. Use instead of 5-6 separate memory_ calls. Zero LLM, pure deterministic aggregation
context_generate · Full project briefing: combines project structure, git state, memory entries, and active sessions in one call. Replaces 5-6 manual tool calls
context_diff · Incremental briefing: git commits + modified files + new/updated memory + active sessions since last session
context_focus · Hyper-focused briefing: only relevant memory + related source files + callers + test files for a query
context_health · Memory health audit: orphan links, duplicates, broken file refs, expired TTL, stale sessions, score 0–100
context_export · Export memory as markdown: injectable context for system prompts (full or compact)
memory_pin · Pin an entry with priority 1-5: pinned entries always appear first in recall results sorted by priority, even without a keyword match
memory_unpin · Unpin an entry: remove the priority flag
memory_search · Unified search with filters: same as memory_recall plus category, tags, from_date, to_date filters. Tag filter uses AND logic — all specified tags must match. budget controls output verbosity. path_scope filters by glob pattern. sessionBias boosts entries from the current git branch
memory_tag · Batch tag operations*: add, remove, or set tags on one or more entries by key or id
MCP Resources
Memory is also exposed as MCP resources for direct context reading:
| Resource | URI | Description |
|---|---|---|
| Memory Entries | toon://memory/entries |
Full memory dump |
| Current Memory | toon://memory/current |
Current memory state with recent entries |
| Memory Stats | toon://memory/stats |
Category counts and TTL info |
| System Primer | toon://memory/summaries |
Auto-generated knowledge map (top entries, categories, patterns) |
MCP Prompts
| Prompt | Description |
|---|---|
summarize_project_context |
Analyze current TOON memory and generate a compact project summary. Optional intent parameter to focus on a specific area |
Examples
Remember a decision```typescript
memory_remember({
category: "decision",
key: "use-zod",
content: "Use Zod for validation — simpler than Joi, better TS support",
file: "src/types.ts",
tags: "validation;types"
})
// 🧠 Guardado: decision/use-zod (a1b2c3d4)
// Quality score: 0.65 (2 tags, detailed content)
// 🔗 Entradas relacionadas:
// [pattern] zod-schemas — Shared Zod schemas for API validation
> **Tip:** Use descriptive keys like `use-zod` instead of vague ones like `validation`. Your agent searches by key and content, so specificity helps. Saving with the same key auto-merges (union of tags, max confidence).
#### Remember with TTL```typescript
memory_remember({
category: "knowledge",
key: "sprint-deadline",
content: "Sprint ends July 18, feature freeze is July 16",
ttl: "7d"
})
// 🧠 Guardado: knowledge/sprint-deadline (x1y2z3w4)
// ⏰ TTL: 2026-07-19
// Quality score is calculated automatically.
> Tip: Use TTL for temporary context like deadlines, sprint info, or time-sensitive notes. Entries with expired TTL are automatically filtered from search results.
Set explicit importance```typescript
memory_remember({
category: "decision",
key: "db-choice",
content: "We chose Postgres over MySQL — JSONB for flexible schemas, better extension ecosystem",
importance: "critical"
})
// 🧠 Guardado: decision/db-choice (a1b2c3d4)
// 🎯 Importance: critical (+0.3 boost) — surfaces above routine entries
> **Tip:** Mark foundational decisions `critical` so they always rank near the top of recall. `importance` accepts `critical`, `high`, `medium`, or `low`; leave it empty to let the system rank by recency and frequency automatically.
#### Auto-inferred tags```typescript
memory_remember({
category: "bug",
key: "redis-connection-timeout",
content: "Redis connection timeout in production, increased pool size"
// tags left empty — auto-inferred from content
})
// 🧠 Guardado: bug/redis-connection-timeout (a1b2c3d4)
// 🏷️ Tags inferidos: redis
// Quality score is calculated automatically based on inferred tags and content.
> Tip: Leave tags empty and the system will infer them from your content using a built-in vocabulary of 20+ categories (redis, auth, api, db, security, etc.) plus a project vocabulary derived from your dependencies at init time. So if your project depends on redis, any entry mentioning "redis" gets auto-tagged redis.
Search memory```typescript
memory_recall({ query: "redis" })
// [bug] redis-pool-fix (i9j0k1l2)
// Added max_connections=20
// File: redis.ts | Tags: redis;fix | Date: 2026-07-10
> **Tip:** Search before you read files. This saves tokens and gives your agent context it wouldn't get from code alone. Quality-weighted ranking ensures the most useful entries surface first. Or use `memory_smart_recall` for a more comprehensive result.
#### Search with date filter```typescript
memory_recall({
query: "redis",
from_date: "2026-07-01",
to_date: "2026-07-31"
})
> Tip: Use date filters when you remember roughly when something happened but not exactly what. Quality-weighted ranking still applies.
Archive old entries```typescript
memory_archive()
// 📦 Archivadas 5 entradas antiguas
// 📋 Quedan 42 entradas activas
> **Tip:** Run this periodically to keep memory lean. Archived entries are still searchable via `memory_recall` with date filters. Entries with expired TTL are also archived automatically. Low-quality entries get lower recall priority. Low-quality entries get lower recall priority.
#### Show changes since last session```typescript
memory_diff({ since: "24h" })
// 📋 Cambios desde 2026-07-11:
//
// ➕ Nuevas (2):
// [decision] use-zod (a1b2c3d4)
// Use Zod for validation
// [bug] redis-timeout (e5f6g7h8)
// Redis connection timeout fix
> Tip: Use memory_diff at the start of a session to see what your agent learned since you last worked on the project. New entries include quality scores. New entries include quality scores.
Find related entries```typescript
memory_suggest({ context: "redis cache configuration" })
// 🔍 Sugerencias para "redis cache configuration":
//
// [decision] redis-cache-config (a1b2c3d4)
// Redis cache layer for session storage
// File: src/cache.ts | Tags: redis;cache | Date: 2026-07-10
//
// [bug] redis-pool-fix (i9j0k1l2)
// Added max_connections=20
// File: redis.ts | Tags: redis;fix | Date: 2026-07-10
> **Tip:** Use `memory_suggest` when you need context about a topic but aren't sure what to search for. Or use `memory_smart_recall` for a more comprehensive result.
#### Smart Recall (unified)```typescript
memory_smart_recall({ intent: "diseño de base de datos para backend" })
// [1] decision/use-postgres
// Choose Postgres for ACID compliance and JSON support
// tags: db;decision · edges: ->2
//
// [2] pattern/db-migrations
// Use sequential migration files, never edit committed ones
// tags: db;pattern · edges: ->1
//
// [3] bug/redis-timeout
// Redis connection timeout — increased pool to 20
// tags: redis;bug
> Tip: Use memory_smart_recall at the START of every task. It combines BM25 + graph + decay + quality in one call — no need to guess what to search for.
Explain WHY a result was returned```typescript
memory_recall({ query: "redis", explain: true })
// [decision] redis-cache-config (a1b2c3d4)
// Redis cache layer for session storage
// File: src/cache.ts | Tags: redis;cache | Date: 2026-07-10
// ↳ 92% relevance · used 14× · used today · importance HIGH
The `↳` reason line is deterministic (relevance %, access count, last-used, importance) — no LLM involved. Use `explain: true` when you want to know *why* the agent was shown those entries.
#### Cap output with `budget_tokens````typescript
memory_recall({ query: "redis", budget_tokens: 300 })
// Entries accumulate greedily; the tail that would exceed the estimate is dropped.
// budget_tokens: 0 (default) = no limit.
> Tip: Combine budget_tokens with budget: "deep" for a context window that stays inside a hard token ceiling regardless of memory size.
Full project briefing (one call)```typescript
context_generate({})
// # Project Briefing (full)
//
// ## Project
// - Name: my-app
// - Root: /path/to/project
// - Package Manager: npm
// - TypeScript: ✓ (v5.3)
//
// ## Git Status
// - Branch: main
// - 3 uncommitted, 0 untracked
//
// ## Memory (42 entries, 12 patterns, 8 bugs)
// [1] decision/use-postgres
// Choose Postgres for ACID compliance
// tags: db;decision
//
// ## Sessions
// - egraterol (main, 2m ago): 42 files touched
> **Tip:** Use `context_generate` at the start of a session to get full context in one call. Replaces 5-6 separate tool calls.
#### Memory health audit```typescript
context_health({})
// # Memory Health (score: 87/100)
//
// ## Summary
// - 42 entries (12 patterns, 8 bugs, 15 decisions, 7 knowledge)
// - 65.3% average quality
//
// ## Issues (3)
// - Orphan link: pattern/db-migrations → pattern/db-seed (key not found)
// - Duplicate: [bug] redis-pool-fix has identical content
// - Expired TTL: [knowledge] sprint-deadline (expired 2026-07-20)
//
// ## Stale Files (1)
// - src/legacy.ts (deleted, 2 refs)
> Tip: Run context_health when memory feels cluttered. Shows orphan links, duplicates, expired TTL entries, broken file references, missing-evidence entries (path_scope without file), and stale claims (overlapping content).
Merge-dedup (automatic)
When you save with the same key, attributes are merged instead of overwritten:```typescript
// First save
memory_remember({
category: "decision",
key: "use-zod",
content: "Use Zod for validation",
tags: "types"
})
// 🧠 Guardado: decision/use-zod (a1b2c3d4)
// Later save with same key — merges automatically
memory_remember({
category: "decision",
key: "use-zod",
content: "Use Zod for validation — also handles API response parsing",
tags: "types;api"
})
// 🧠 Actualizado: decision/use-zod (a1b2c3d4)
// 🔗 Merge: tags combinados, fecha y links actualizados
// Tags now: "types;api" (union of both)
> **Tip:** Use descriptive, stable keys. The same key = merge, different key = new entry.
#### Quality scoring
Every entry gets an automatic quality score (0–1) based on structure:
| Factor | Weight | What it measures |
|--------|--------|------------------|
| Tags | 0.3 max | More specific tags = higher quality |
| Links | 0.2 max | Connected entries = higher quality |
| Content length | 0.3 max | Detailed > vague |
| Recency | 0.1 max | Recent entries score higher |
| Specificity | 0.1 max | Unique words vs repeated words |
| Origin | +0.1/−0.05 | Human assertions boosted, inferred slightly penalized |
High-quality entries surface first in recall. Check quality with `memory_stats`:```typescript
memory_stats()
// ...
// Calidad promedio: 0.58 (12 con score)
Confidence score
Each entry tracks how reliable the information is:
| Source | Confidence | Meaning |
|---|---|---|
| User assertion | 1.0 | "We use Postgres" — direct statement |
| Inferred | 0.65–0.75 | Agent inferred from context |
| Uncertain | 0.50 | Agent is guessing |
Confidence is preserved on merge (max of both entries).
System Primer
The System Primer is an auto-generated knowledge map exposed as an MCP resource. Agents load it at session start for instant context:```typescript
// Exposed as toon://memory/summaries
…(正文过长,页面只展示前面部分,完整内容见仓库)
```
