memory_compress

MCP tool from Toon Memory by LuiggiVal08

LLM-powered two-step compression: summarize + overwrite. Uses anthropic/openai CLI if available, otherwise returns prompt for manual compression

How to use it

memory_compress is exposed by the Toon Memory MCP server. Add the server to your MCP client (Claude Desktop, Cursor, Windsurf and others), and the memory_compress 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-memory

FULL TOON MEMORY LISTING

Other tools in Toon Memory (35)

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_diff

Incremental briefing: git commits + modified files + new/updated memory + active sessions since last session

context_export

Export memory as markdown: injectable context for system prompts (full or compact)

context_focus

Hyper-focused briefing: only relevant memory + related source files + callers + test files for a query

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_health

Memory health audit: orphan links, duplicates, broken file refs, expired TTL, stale sessions, score 0–100

memory_archive

Archive old entries (>30 days) and expired TTL entries

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_decrypt

Disable encryption

memory_diff

Show changes since a date (24h, 7d, or exact date)

memory_encrypt

Enable AES-256-GCM encryption

memory_export_gist

Export memory entries to a GitHub Gist (public or private). Uses GITHUBTOKEN or gh CLI

memory_export_global

Write current project memory to the global file (~/.toon-memory/memory/global.toon). One-shot share of cross-project conventions

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 supersededby link to newkey

memory_graph_path

BFS shortest path between two entries in the knowledge graph. Shows how concepts are connected

memory_import_gist

Import entries from a GitHub Gist. Merges with existing entries (union of tags, max confidence)

memory_import_global

Merge cross-project conventions from the global file into this project (one-shot, deterministic, offline). merge: false replaces instead

memory_merge_sessions

Merge observations across parallel sessions for a file. Deduplicates and optionally auto-promotes to memory

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_primer

One-call context primer: top memories + categories + session file changes. Auto-injected at session start

memory_recall

Search memory (use BEFORE reading files, filters expired TTL). mode: "graph" expands a relationship-aware subgraph for higher precision. budget: "tiny"

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 evid

memory_search

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

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 TOONMEMORYKEY

memory_sessions

Show active agent sessions (branch, files, last-seen) and soft conflicts for parallel work

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, budgettokens caps output by estimated tokens. Use at the START of every task. Returns compact, token-efficient output

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_suggest

Find related entries for a given context

memory_summary

Save/retrieve file summaries

memory_tag

Batch tag operations: add, remove, or set tags on one or more entries by key or id

memory_unpin

Unpin an entry: remove the priority flag

summarize_project_context

Analyze current TOON memory and generate a compact project summary. Optional intent parameter to focus on a specific area