Clearailhc/clearai-dsh
An agent preset for evidence-checked research: every step advances only through system-verified observations, L3+ claims go to an independent evaluator, and the session folds into a replayable ledger that grows into a browsable domain ontology. Requires DSH >=0.1.7-alpha.1.
Install
via npm
Resolves a published tarball rather than cloning the repository, and installs without any extra setup. Swap `web` for your profile name if you run another one.
via GitHub · npm package
Installing from GitHub runs the project's build script, which pnpm blocks until you allowlist it — run the command once and pnpm prints the exact key to add under `allowBuilds` in ~/.dsh/profiles/web/pnpm-workspace.yaml.
The desktop app keeps its own profile, desktop, and only the dsh command it ships may change it — the npm-installed dsh refuses that profile. Install the command from the app menu (Manage dsh Command…), open Desktop once, quit it fully, run the line below, then reopen Desktop.
via npm
Resolves a published tarball rather than cloning the repository.
via GitHub · npm package
Installing from GitHub runs the project's build script, which pnpm blocks until you allowlist it — run the command once and pnpm prints the exact key to add under `allowBuilds` in ~/.dsh/profiles/desktop/pnpm-workspace.yaml.
Our install check ran in a web profile on npm's dsh, not in the desktop app.
What happened when we ran it
Installed cleanly when we ran it
Every command here is run in a throwaway container against a clean profile, and the result is whatever the harness recorded — not a guess from the source. Last run 6d agoon DeepSeek Harness 0.2.1-rc.5.
Show it in your README
For maintainers: the badge serves this listing's latest sandbox verdict, so a re-run updates it on its own — and it links readers to the full result here.
Due diligence
Security
No build script was blocked in our run.
Source: our sandbox install on DeepSeek Harness 0.2.1-rc.5, 6d ago.
package.json declares no preinstall, install or postinstall script.
Source: package.json on GitHub, read at our last sync. prepare is not recorded; it runs only on a GitHub install, and shows up under build scripts when pnpm blocks it.
shell commands (bash, exec, spawn …)
Source: a keyword match on the README — a hint about what the plugin touches, not an analysis of its code.
Not an audit. These are the record of one install and two text scans; nobody has read this plugin's code on your behalf. Plugins run with your agent's permissions.
What it is — Pins each research step in DSH to observations the system has checked, sends L3+ claims to a separate evaluator, and turns the session into a ledger you can replay as a domain ontology.
Who it is for — You are compiling a citable field brief inside DeepSeek Harness with a model that treats fluent answers as closed questions, and you need a later session to pull last round's evidence by concept instead of scrolling chat. Treat DSH as a coding executor and skip it; continuation, subagents, deliverable cards, and file history already belong to the host.
Watch out — The host must be DSH 0.1.7-alpha.1 or newer; the notes only claim verification on 0.1.7-rc.2 and 0.2.0-rc.1. It invokes the shell at runtime. A sandbox run on a fresh profile installed it and the harness registered it.
The verdict — Sit with the conflict readings or pass. Without that habit the preset only strips the model's ability to close a step.
Generated by grok-4.6, and a starting point rather than a verdict. Where it says a plugin installs or does not, that is from a real run in a clean profile — everything else is read off the repository. Trust the source over this.
clearai-dsh is a DeepSeek Harness plugin that provides an evidence-checked research preset and turns each session into a replayable domain ontology. It advances a research goal only when the system has verified an observation, keeps refuted and inconclusive results, and sends conclusions above the L3 level to an independent evaluator.
The preset uses DeepSeek Harness's composition declaration line and derives state from the session record rather than maintaining a second store. Its tools do not expose a field for the model to mark a step complete. Evidence chains, boundaries, support levels, vocabulary, ontology and entity graphs, and contradictory readings are presented from that record. A goal completes only after independent evaluation; goal continuation, subagents, user questions, deliverable cards and file history remain DeepSeek Harness features.
clearai-dsh suits research where claims need explicit boundaries, evidence and replayable reasoning, especially when the resulting vocabulary and verified entities should remain useful in later work. It is not a general recursive self-improvement system, and it is a poor fit when ordinary task completion and chat history are sufficient. It requires DeepSeek Harness 0.1.7-alpha.1 or later. The documented terminal surface is the dsh command used to install the package and restart dsh web; the README does not describe additional terminal operations performed by the preset.
DeepSeek Harness loads clearai-dsh as the ClearAI preset after the plugin is installed and dsh web is restarted. The preset follows an epistemic loop:
The session record is the source of derived state. Failed, refuted and inconclusive hypotheses remain in that record rather than being deleted. The resulting ontology contains concepts, predicates, value forms, units, established entries, evidence chains, ontology graphs and entity graphs. Contradictory readings are reported; retaining or retracting them remains a human decision.
The README documents one profile-level pnpm setting relevant to exact version selection:
| Key | Purpose |
|---|---|
minimumReleaseAgeExclude |
Exempts clearai-dsh from pnpm's release-age delay when added to pnpm-workspace.yaml. |
The setting is optional. Pinning the package version is the other documented way to avoid pnpm selecting an older release under its minimumReleaseAge policy.
DeepSeek Harness uses dsh web to run the web application. After restarting it, select ClearAI in the preset picker at the top of a new session. DeepSeek Harness also exposes plugin installation through the sidebar's Plugins → Add plugin page; the 插件列表 / Plugins Settings page is a read-only inventory, not the installation screen.
DeepSeek Harness 0.1.7-alpha.1 or newer is required because that generation introduced the composition declaration line used by this preset. The README reports verification against 0.1.7-rc.2 and 0.2.0-rc.1. clearai-dsh supplies the epistemic contract, ontology and presentation; DeepSeek Harness supplies goal continuation, subagents, questions, deliverable cards and file history. It does not claim recursive self-improvement.
Written from the project's own documentation and kept in sync with it. Where the two disagree, the source is authoritative — read the README on GitHub
Same category
FuRongJun-1999
White-box AGI architecture exploration: metacognition (self-cognition loop), continual learning (knowledge flywheel), world model (condition space, spatiotemporal memory graph), self-improvement (bootstrap discipline), zero-LLM white-box pipeline, and auditable trust guardrails.
Installed cleanly when we ran it
MichengAI
Adds /pua to steer the agent to try another approach and verify results before claiming completion, with 15 company styles, persona modes, global and per-conversation settings, and an optional loop that continues until a verification command passes, the iteration limit is reached, or the user cancels.
Installed cleanly when we ran it
pk14742952-AD
Reflective self-evolution plugin for local Qwen3.8 27B/3.8 Flash and online APIs: a coding-loop convergence steerer curbs Qwen3.8 27B/Flash repeated-verification deep-thinking to converge faster and cut thinking time; a five-state delivery guard detects and corrects stuck turns and infinite loops; model-agnostic host logic, mostly compatible with online APIs; per-use continual self-improvement with counter-reason self-checks, critic escalation, inverted-index memory retrieval, coding-loop convergence steering, and a five-state delivery guard.
Installed cleanly when we ran it
icyaaaww
Records recurring task corrections and tool failures locally, then compiles them into changes to eight harness components through explicitly started evolution, paired baseline/candidate checks, trial activation and rollback. Includes a budget and audit ledger; requires Node.js 24+ and a compatible DSH 0.2.1-rc.2 or later 0.2.x host.
Installed cleanly when we ran it
kenz1117
Cross-session long-term memory as a local SQLite store: dual scopes (user + per-git-origin project), hybrid FTS5 + local-vector retrieval fused with RRF, an evidence gate that forces an explicit sufficiency judgement, provenance audit chains, SM-2 spaced-repetition review, consolidation distillation and decay forgetting, and a nine-view "Memory Palace" sidebar panel. 22 narrow-parameter tools, no external service, no API key, no Docker.
Installed cleanly when we ran it
Kanadego
An agent that wakes up on its own schedule: by default every 60 minutes, ±20% (48–72). It browses the interests you set, drops what it finds into a local pool of notes, and keeps a profile of what you like. When it has enough worth sharing it hands the session you linked a short package of notes — whether to speak, and which note to use, is that session's agent's call in the moment. Quiet hours, busy windows, a daily limit and a cooldown are decided in code; when the answer is no, the decision and expression phases after the gate call no model at all — browsing runs before the gate and is counted separately. Windows, Linux and macOS (Linux and macOS are minimal support).
Installed cleanly when we ran it
