en un clic
en un clic
| name | memory |
| description | Two-layer memory system with Dream-managed knowledge files. |
| always | true |
SOUL.md — Bot personality and communication style. Managed by Dream. Do NOT edit.USER.md — User profile and preferences. Managed by Dream. Do NOT edit.memory/MEMORY.md — Long-term facts (project context, important events). Managed by Dream. Do NOT edit.memory/history.jsonl — append-only JSONL, not loaded into context. Prefer the built-in grep tool to search it.memory/history.jsonl is JSONL format — each line is a JSON object with cursor, timestamp, content.
grep(..., path="memory", glob="*.jsonl", output_mode="count") or the default files_with_matches mode before expanding to full contentoutput_mode="content" plus context_before / context_after when you need the exact matching linesfixed_strings=true for literal timestamps or JSON fragmentshead_limit / offset to page through long historiesexec only as a last-resort fallback when the built-in search cannot express what you needExamples (replace keyword):
grep(pattern="keyword", path="memory/history.jsonl", case_insensitive=true)grep(pattern="2026-04-02 10:00", path="memory/history.jsonl", fixed_strings=true)grep(pattern="keyword", path="memory", glob="*.jsonl", output_mode="count", case_insensitive=true)grep(pattern="oauth|token", path="memory", glob="*.jsonl", output_mode="content", case_insensitive=true)/dream-log command.Generate images and iteratively edit saved image artifacts.
Sustained objectives via long_task / complete_goal — idempotent goal wording, project-style modular work, early web/doc research, Runtime Context metadata.
Create or update AgentSkills. Use when designing, structuring, or packaging skills with scripts, references, and assets.
One-time setup wizard for the nanobot upgrade skill. Triggers: setup update, configure update, 切设置更新, 初始化更新.
Check and set the agent's own runtime state (model, iterations, context window, token usage, web config). Use when diagnosing why something doesn't work ("why can't you search the web?", "why did you stop?"), checking resource limits before complex tasks, adapting configuration for long or simple tasks, or remembering user preferences across turns. Also use when the user asks what model you are running, how many tokens you've used, or what your settings are.
Schedule reminders and recurring tasks.