ClawHub
Code PluginExecutes codesource-linked

Deep Research

Native OpenClaw deep research plugin with local research state, source capture, and synthesis tools

Community code plugin. Review compatibility and verification before install.
deep-research · runtime id deep-research
Install
openclaw plugins install clawhub:deep-research
Latest Release
Version 0.1.0
Compatibility
{
  "builtWithOpenClawVersion": "2026.3.23-2",
  "pluginApiRange": ">=2026.3.23"
}
Capabilities
{
  "bundledSkills": [],
  "capabilityTags": [
    "executes-code"
  ],
  "channels": [],
  "commandNames": [],
  "configSchema": true,
  "configUiHints": false,
  "executesCode": true,
  "hooks": [],
  "httpRouteCount": 0,
  "materializesDependencies": false,
  "providers": [],
  "runtimeId": "deep-research",
  "serviceNames": [],
  "setupEntry": false,
  "toolNames": []
}
Security Scan
VirusTotalVirusTotal
Pending
View report →
OpenClawOpenClaw
Suspicious
medium confidence
✓
Purpose & Capability
Name, description, and registered tools align with the code: the plugin implements local research sessions, resource capture, and synthesis persisted to a JSON file. Declared dependencies (@sinclair/typebox, openclaw) and the files included are appropriate for this functionality.
ℹ
Instruction Scope
SKILL.md instructs normal build/install steps and to use web_search for gathering evidence. It tells the plugin to persist data to a JSON file under the user's home (~/.openclaw/state/deep-research/research.json) which is consistent with the stated purpose. However, the skills/deep-research/SKILL.md front-matter includes metadata {"openclaw":{"always":true}} which expands the plugin's runtime scope (force-enabled everywhere) and conflicts with the registry-level flag (always: false).
✓
Install Mechanism
No remote download or extraction steps. The SKILL.md uses standard npm build/install and the package is installed locally via openclaw plugins install — this is low risk and expected for an OpenClaw plugin.
✓
Credentials
The plugin requests no environment variables, no credentials, and accesses only a local storage path for persisting research state. There are no other declared secrets or unrelated service credentials.
!
Persistence & Privilege
The SKILL.md includes metadata that sets always:true (force-enable the plugin), while the registry metadata shows always:false. If the platform honors the SKILL.md metadata, the plugin would be force-included in all agents, increasing its blast radius even though it only stores local JSON. Always:true combined with autonomous invocation (standard) is a notable privilege escalation and should be confirmed before enabling.
What to consider before installing
This plugin appears to do what it says: provide local research workspaces persisted to a JSON file. Before installing, check two things: (1) confirm which 'always' setting the platform will honor — the SKILL.md contains metadata setting always:true while the registry lists always:false; always:true would force-enable the plugin in every agent run and increases risk. (2) Verify the storage path (~/.openclaw/state/...) is acceptable for your environment and that sensitive notes are stored appropriately (consider file permissions or encrypting sensitive research). Also confirm you trust the plugin author and repository (it installs locally via npm build) since the plugin will write and read files under your home directory. If you need greater assurance, inspect the resolveStoragePath function (truncated in the provided bundle) to confirm it expands and restricts paths safely and does not allow unexpected filesystem locations.
Verification
{
  "hasProvenance": false,
  "scanStatus": "pending",
  "scope": "artifact-only",
  "sourceCommit": "b341a45",
  "sourceRepo": "clawic/plugins",
  "sourceTag": "main",
  "summary": "Validated package structure and linked the release to source metadata.",
  "tier": "source-linked"
}
Tags
{
  "latest": "0.1.0"
}

Deep Research Plugin

Native OpenClaw plugin for managing multi-step research projects locally.

It gives the agent a persistent research workspace with:

  • multiple research sessions tracked by id and title
  • an active research context so follow-up steps can keep using the same workspace
  • captured resources with URLs, summaries, notes, and source metadata
  • synthesis entries by phase so findings can evolve from framing to reporting

Install

npm install
npm run build
openclaw plugins install .
openclaw plugins enable deep-research
openclaw gateway restart

Config

{
  plugins: {
    entries: {
      "deep-research": {
        enabled: true,
        config: {
          storagePath: "~/.openclaw/state/deep-research/research.json",
        },
      },
    },
  },
}

If storagePath is omitted, the plugin stores data in ~/.openclaw/state/deep-research/research.json.

Tools

  • deep_research_create
  • deep_research_list
  • deep_research_get
  • deep_research_update
  • deep_research_focus
  • deep_research_add_resource
  • deep_research_add_synthesis

Usage

After enabling deep-research, ask for things like:

  • Research the latest browser MCP support across major AI coding tools and give me a sourced comparison.
  • Build a brief on EU AI Act enforcement timelines with exact dates, primary sources, and open questions.
  • Compare three vendors in the passwordless auth space and separate confirmed facts from marketing claims.

The agent can create a research session, keep it active across steps, save resources as they are found, and append synthesis notes for each phase.