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.
git clone --depth 1 https://github.com/cbuntingde/kimi-memoryWrote 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.
[](https://agentmods.dev/commands/cbuntingde/kimi-memory/memos)<a href="https://agentmods.dev/commands/cbuntingde/kimi-memory/memos"><img src="https://agentmods.dev/badge/commands/cbuntingde/kimi-memory/memos/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.
<a href="https://agentmods.dev/commands/cbuntingde/kimi-memory/memos"><img src="https://agentmods.dev/badge/commands/cbuntingde/kimi-memory/memos.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00029 | $0.00538 |
| Opus 5.5 | $0.00012 | $0.00215 |
| Sonnet 5.5 | $0.00006 | $0.00108 |
| Haiku 4.5 | $0.00003 | $0.00054 |
Grade A, and why
memos scanned grade A with 1 finding 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 13d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- curl with a 2-second timeout, or `Test-NetConnection 127.0.0.1 -Port 8765` What it actually says
/kimi-memory:memos
Open the local kimi-memos-dashboard in the user's default browser. The dashboard
runs as a standalone companion app under ~/.kimi-code/plugins/managed/kimi-memos-dashboard/
and is intentionally NOT a Kimi plugin (per its own AGENTS.md) — this slash
command is a thin integration, not a control surface.
Steps:
- Probe whether
http://127.0.0.1:8765/is responding (HEAD request via Bash- curl with a 2-second timeout, or
Test-NetConnection 127.0.0.1 -Port 8765on PowerShell).
- curl with a 2-second timeout, or
- If not responding, tell the user:
kimi-memos-dashboard is not running. Start it with:cd ~/.kimi-code/plugins/managed/kimi-memos-dashboard && npm startand then re-run/kimi-memory:memos. Do not start it for them — the dashboard binds a port and the user should opt in. - If responding, open the dashboard URL in the default browser:
- Windows (Git Bash / cmd):
start "" "http://127.0.0.1:8765/" - Windows (PowerShell):
Start-Process "http://127.0.0.1:8765/" - macOS:
open "http://127.0.0.1:8765/" - Linux:
xdg-open "http://127.0.0.1:8765/"
- Windows (Git Bash / cmd):
- Report the URL back to the user.
Notes:
- The dashboard reads the same SQLite files that this plugin writes to, with
PRAGMA query_only=ONenforced, so opening it cannot mutate memory data. - The dashboard binds
127.0.0.1by default; LAN exposure is not provided here. - Optional bearer-token auth is respected by the dashboard itself; this command does not bypass it.
- The default port (
127.0.0.1:8765) and token scheme are owned bykimi-memos-dashboard, not by this plugin. If the dashboard re-binds or changes its auth, the probe in step 1 will return a connection error and the user must adjust the URL or restart the dashboard before re-running/kimi-memory:memos.
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.
- 13d ago Changed 190e5d7429b6
- 1mo ago First seen · 42 lines · 29 tokens per session scan A 8c8e8f741514
memos is a command published in the GitHub repository cbuntingde/kimi-memory (0 stars, last pushed 14d ago), licensed MIT. It adds 29 tokens to every session and 538 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
minutes-ideas
Surface recent voice memos and ideas captured from any device. Use when the user asks "what ideas did I have?", "what were my recent memos?", "what did I record while walking?", or wants to recall a captured thought.
learn
Force claude-smart to extract learnings from this session now.
memory-store
Store an insight, decision, or pattern to memory.
analyze-context
USE WHEN you want to analyze project context before starting work on a task. Calls context + recall, then synthesizes goals, decisions, gotchas, and relevant memories into a pre-task brief.
cc-memory
Configure persistent memory that survives across sessions using a layered approach: split rule files for always-loaded context, auto-memory for organic learning, and optional MCP-backed long-term memory for large codebases.
lians-recall
Recall current (non-stale) facts from Lians memory, optionally as-of a past date.