A command for configuring and running scheduled memory maintenance. The maintenance combines related memories, forms conclusions, and removes outdated entries when Kimi starts a session.

Use it to turn automatic maintenance on or off, set its minimum interval, run it once, or check when it last ran.

It keeps the memory store organized over time without requiring a continuously running background process.

dreaming — Command for Claude Code by cbuntingde/kimi-memory

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Clone the repo

git clone --depth 1 https://github.com/cbuntingde/kimi-memory

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/commands/cbuntingde/kimi-memory/dreaming/github.svg)](https://agentmods.dev/commands/cbuntingde/kimi-memory/dreaming)

Your own site

<a href="https://agentmods.dev/commands/cbuntingde/kimi-memory/dreaming"><img src="https://agentmods.dev/badge/commands/cbuntingde/kimi-memory/dreaming/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/commands/cbuntingde/kimi-memory/dreaming"><img src="https://agentmods.dev/badge/commands/cbuntingde/kimi-memory/dreaming.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 110 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,906 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00110	$0.01906
Opus 5.5	$0.00044	$0.00762
Sonnet 5.5	$0.00022	$0.00381
Haiku 4.5	$0.00011	$0.00191

Measured 1mo ago against content hash 467f47a8355a, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

dreaming scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

commands/dreaming.md · 187 lines

How it starts

The opening of the file, as written. The whole thing — 187 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/kimi-memory:dreaming

Configure the dreaming subsystem — the background pass that consolidates memories into conclusions, combines duplicates, and prunes stale rows on a schedule. The user-facing verb covers the three existing internal passes (consolidate + dream + auto-GC) so they share one schedule and one status surface.

Modes

off — never auto-run. Only fires on explicit /kimi-memory:dreaming run.
auto — the historical behaviour: activity-threshold + 30-minute debounce (env-tunable via KIMI_MEMORY_DREAM_DEBOUNCE_MS). Switching to auto is a no-op upgrade for existing users.
on — wall-clock floor regardless of session activity. Default interval 24h, overridable via --interval. A SessionStart that opens after the floor has elapsed runs the pass immediately. There is no background daemon — the plugin never wakes itself up. If the user never opens Kimi, dreaming never runs. That trade-off is intentional.

Usage

/kimi-memory:dreaming on                       # turn on, default 24h interval
/kimi-memory:dreaming on --interval 3h         # 3-hour floor
/kimi-memory:dreaming off                      # never auto-run
/kimi-memory:dreaming auto                     # default behaviour (alias for the historical debounce path)

/kimi-memory:dreaming run                      # one-shot, force a pass now
/kimi-memory:dreaming run --include consolidate,dream
/kimi-memory:dreaming run --exclude gc         # skip the prune/archive/tier pass

/kimi-memory:dreaming status                   # mode + interval + last run + next due
/kimi-memory:dreaming last                     # last run's saved/merged/pruned counts

Add --scope project|global to on|off|auto|status to write the mode to the per-project file or to the system-wide default. Per-project wins over global when both exist.

What this does

One call runs three passes in order, controlled by --include:

consolidate (runConsolidate) — clusters memories by embedding cosine + tag overlap, writes conclusion rows, records synthesizes edges, and merges tight duplicates. Writes one consolidation_runs row at the end.
dream (enqueueDreamJob → generateProposalsForJob → applyDreamJob) — durable staged job lifecycle in dream_jobs + dream_proposals. One enqueue per call; one apply if a job is ready. Honours the partial unique index idx_dream_jobs_active so two concurrent enqueues are safe.
gc (runAutoGc) — prune dead rows (deleted >30d, superseded >90d, embed-failed >30d, cold low-confidence >365d), archive old audit rows, run L0→L1→L2→L3 tier promotion. Bounded by KIMI_MEMORY_AUTO_GC=off.

Read the full file on GitHub · 187 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

1mo ago Changed · +2 lines 467f47a8355a
1mo ago Changed · -3 lines 58e957096af0
1mo ago Changed · +23 lines 00cd9de75999
2mo ago First seen · 165 lines · 110 tokens per session scan A 8c9b07bece59

Subscribe to this mod's changes

dreaming is a command published in the GitHub repository cbuntingde/kimi-memory (0 stars, last pushed 1mo ago), licensed MIT. It adds 110 tokens to every session and 1,906 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Memory and context Productivity

dreaming next to 6 commands from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
dreamingcbuntingde/kimi-memory	Command	0	1mo ago	MIT	A	110	Claude Code
setup-contextmohitagw15856/pm-claude-skills	Command	1.5k	today	MIT	A	21	Claude Code
brainmohitagw15856/pm-claude-skills	Command	1.5k	today	MIT	A	17	Claude Code
pull-learningsclosedloop-ai/claude-plugins	Command	123	yesterday	Apache-2.0	A	12	Claude Code
vitaecontext-vitaegraphvitaecontext/vitaecontext	Command	89	5d ago	MIT	A	12	Claude Code
perf-difficult-conversationfrankxai/Starlight-Intelligence-System	Command	10	today	MIT	A	93	Claude Code
culture-onboarding-90frankxai/Starlight-Intelligence-System	Command	10	today	MIT	A	101	Claude Code