Dreaming for agents: replay recent conversations between sessions (dream_digest), reflect and write a dream journal (dream_save/journal/recall), and idempotently bridge recurring lessons into AGENTS.md (dream_bridge). Reads multi-frame zstd session archives with privacy masking on by default; six tools including a health self-check; zero runtime dependencies.
Install
# from npm (prebuilt)
dsh plugin --profile web add @stardustlc/dsh-dream
# from GitHub (first run asks for allowBuilds approval — follow the hint, retry)
dsh plugin --profile web add github:STARDUSTLC666/dsh-dream
Any plugin you install runs third-party code with your own permissions — it can read your files, use your credentials, and reach the network, and tool approvals don’t sandbox it. GitHub-sourced plugins also run build scripts at install time — pnpm blocks those until you allow them, so an install can stop with ERR_PNPM_GIT_DEP_PREPARE_NOT_ALLOWED or ERR_PNPM_IGNORED_BUILDS; dsh prints the exact key to add under allowBuilds in your profile’s pnpm-workspace.yaml, and the install works on the next run. Allowing a build is a trust decision: only install sources you trust, and pin a commit (github:owner/repo#sha).
README
Collect candidate lessons from completed tasks, review them and reuse relevant memories. Manual reflections remain available.
Feedback and contributions are welcome: report issues or submit pull requests.
What it does
- Browse journals, retrieve lessons and inspect their sources.
- Collect candidates after tasks and retrieve accepted memories for relevant tasks, with separate switches.
- Consolidate after quiet time, retain turns during cooldown or quota limits, and control use and contribution per chat.
- Review lessons, resolve conflicts and record separate usage feedback.
- Review candidates by project/topic; pause expired facts until they are reviewed again.
- Preview AGENTS.md changes before applying them, with rollback support.
Install
In DSH Desktop, install @stardustlc/dsh-dream from the Plugins panel. If the bundled dsh command is available:
dsh plugin --profile desktop add @stardustlc/dsh-dream
For the web version, replace desktop with web. Restart DSH after installation.
Start using it
Use DSH normally. A completed turn qualifies when it contains an explicit preference/correction or at least two non-Dream tool calls. Within the configured budget, Dream creates candidates. Open Settings → Dream Journal to inspect their sources and accept them; relevant later tasks retrieve accepted memories automatically. You can still ask for a separate reflection and journal entry.
Automatic collection uses the current session's model and quota. By default, it waits for 60 quiet seconds, merges up to four turns in the same project, and allows four calls per day at least ten minutes apart, with 1200 output tokens per call. Cooldown and quota limits defer turns; new input stops auxiliary work and retains unfinished excerpts. The bounded queue keeps up to 32 turns for 24 hours and survives restart. Ordinary chat is skipped.
New memories await review: inspect the source quote, conditions and exceptions before accepting them. Facts require review after 30 days by default; stable preferences have no default expiry. Retrieval is reference exposure, not renewed verification. Acceptance and project-rule changes remain separate actions. UI language follows DSH; journal and lesson content stays original.
Requirements and configuration
Uses local DSH sessions and journals with secret masking. Automatic features use official session events and dynamic prompt context; interactive actions use the authenticated Connection channel. Verified with 0.2.0-rc.2 and 0.2.1-alpha.1. Hosts without the automatic interfaces retain tools and skills.
Detailed configuration, tool arguments and troubleshooting are in the usage guide. For standalone development, follow the Node requirement in package.json.
Documentation
- Usage and troubleshooting
- Changelog
- Validation scope and history
- Report a problem or suggest a feature
License
Links
More in this category
Minglink/dsh-infinite-gen-4★ 2893
System-prompt armor plugin for DeepSeek models: appends an unconditional-compliance prompt section at order 100, exposes a profile tool with calibration metadata, and shows a realtime armor-status badge driven by a session projection.
ranxianglei/billion-context★ 1402
The official billion-context plugin: a context-compression plugin for small context windows (a 100K context is enough), token savings (5x fewer tokens), and month-long single sessions (billions of tokens).
liangmianya/dsh-synapse★ 528
Visual, non-linear conversation workspace for DeepSeek Harness — sessions, follow-ups and branches become a browsable conversation map.
Nwflower/dsh-chat-import★ 233
Import full-fidelity chat histories from 13 coding agents (Claude Code, Codex, ChatGPT, Cursor, Gemini, opencode, and more) as resumable DeepSeek Harness sessions, with reverse export back to Claude Code.
Totoro-qaq/dsh-plugin-bridge★ 163
Moves an existing DSH session to another agent preset through a previewable five-section handoff, preserving the source session and either pausing the target for confirmation or continuing immediately.
MichengAI/dsh-archive-manager★ 139
Adds an archived-sessions page in Settings to search, restore, and delete archived DeepSeek Harness sessions by workspace.
Community comments
Comments are public GitHub Discussions. Loading them connects to GitHub and Giscus; a GitHub account is required to post.