memory_merge_sessions
Merge observations across parallel sessions for a file. Deduplicates and optionally auto-promotes to memory
How to use it
memory_merge_sessions is exposed by the Toon Memory MCP server. Add the server to your MCP client (Claude Desktop, Cursor, Windsurf and others), and the memory_merge_sessions tool becomes available to the model automatically. See the full listing for setup details and every tool this server provides.
Install Toon Memory
npx toon-memoryOther tools in Toon Memory (35)
One-call context briefing: memory + sessions + health in compact markdown. Use instead of 5-6 separate memory calls. Zero LLM, pure deterministic aggregation
Incremental briefing: git commits + modified files + new/updated memory + active sessions since last session
Export memory as markdown: injectable context for system prompts (full or compact)
Hyper-focused briefing: only relevant memory + related source files + callers + test files for a query
Full project briefing: combines project structure, git state, memory entries, and active sessions in one call. Replaces 5-6 manual tool calls
Memory health audit: orphan links, duplicates, broken file refs, expired TTL, stale sessions, score 0–100
Archive old entries (>30 days) and expired TTL entries
Create timestamped backup of memory file (auto-prunes to 10 most recent)
List activity auto-captured by hooks (opt-in) or clear the log
Session checkpoint: creates a snapshot of current memory state with 7d TTL. Useful for rollback reference during long sessions
LLM-powered two-step compression: summarize + overwrite. Uses anthropic/openai CLI if available, otherwise returns prompt for manual compression
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
Disable encryption
Show changes since a date (24h, 7d, or exact date)
Enable AES-256-GCM encryption
Export memory entries to a GitHub Gist (public or private). Uses GITHUBTOKEN or gh CLI
Write current project memory to the global file (~/.toon-memory/memory/global.toon). One-shot share of cross-project conventions
Lifecycle ops by key or id: action: "soft" (default) marks obsolete, "hard" permanently removes, "restore" brings back to active, "supersede" retires it with a supersededby link to newkey
BFS shortest path between two entries in the knowledge graph. Shows how concepts are connected
Import entries from a GitHub Gist. Merges with existing entries (union of tags, max confidence)
Merge cross-project conventions from the global file into this project (one-shot, deterministic, offline). merge: false replaces instead
Pin an entry with priority 1-5: pinned entries always appear first in recall results sorted by priority, even without a keyword match
One-call context primer: top memories + categories + session file changes. Auto-injected at session start
Search memory (use BEFORE reading files, filters expired TTL). mode: "graph" expands a relationship-aware subgraph for higher precision. budget: "tiny"
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 evid
Unified search with filters: same as memoryrecall plus category, tags, fromdate, todate filters. Tag filter uses AND logic — all specified tags must match. budget controls output verbosity. pathscope filters by glob pattern. sessionBias boosts entries from the current git branch
Encrypted secrets vault (secrets.toon, AES-256-GCM): store/get/list/forget. Keeps data.toon readable while sensitive values stay encrypted at rest. Requires TOONMEMORYKEY
Show active agent sessions (branch, files, last-seen) and soft conflicts for parallel work
Unified recall: BM25 + graph + decay + quality in one call. sessionBias boosts entries from the current git branch. explain: true appends per-entry reasons, budgettokens caps output by estimated tokens. Use at the START of every task. Returns compact, token-efficient output
View memory state (including TTL stats, quality distribution, origin/status breakdown, cold memories below quality/access thresholds, and hit rate / duplicate / obsolete metrics)
Find related entries for a given context
Save/retrieve file summaries
Batch tag operations: add, remove, or set tags on one or more entries by key or id
Unpin an entry: remove the priority flag
Analyze current TOON memory and generate a compact project summary. Optional intent parameter to focus on a specific area