This is a straightforward DuckDuckGo wrapper that lets Claude search the web without API keys or rate limits. You install the ddgs Python package, point the shebang to your Python environment, and OpenClaw calls it automatically when it needs current information. The main appeal is zero configuration beyond the initial setup. It returns JSON with titles, links, and snippets. If you want web search without dealing with API credentials or worrying about quotas, this does the job. The privacy angle from DuckDuckGo is a bonus, though realistically you're using this because it's free and works out of the box.

skills.sh installs
580
GitHub stars
2
last updated
Jul 14, 2026

Install

$ npx -y skills add lngu/openclaw-skill-freeunlimited-websearch --skill freeUnlimited-websearch --agent claude-code

Installs into .claude/skills of the current project.

Files

Free Unlimited Web Search

Search the web for free using DuckDuckGo - no API key or rate limits.

Features

  • Free: No API key required
  • Unlimited: No rate limits or quotas
  • Private: Uses DuckDuckGo's privacy-focused search

Requirements

  • Python 3.8+
  • ddgs package (pip install ddgs)

Installation

  1. Install the ddgs package in a Python environment:

    pip install ddgs
    
  2. Clone this skill to your openclaw skills directory:

    git clone https://github.com/YOUR_USERNAME/openclaw-skill-freeUnlimited-websearch ~/.openclaw/skills/freeUnlimited-websearch
    
  3. Update search.py shebang to point to your Python with ddgs installed:

    # Edit the first line of search.py to your python path, e.g.:
    #!/path/to/your/venv/bin/python
    
  4. Enable the skill in ~/.openclaw/openclaw.json:

    {
      "skills": {
        "entries": {
          "freeUnlimited-websearch": {
            "enabled": true
          }
        }
      }
    }
    
  5. Restart openclaw:

    openclaw gateway restart
    

Sponsors

Details

Repository
github.com/lngu/openclaw-skill-freeunlimited-websearch
First seen
Jun 3, 2026

Recommended

1juliusbrussee avatarcavemanjuliusbrussee/cavemanUltra-compressed communication mode. Cuts output tokens 65% (measured) by speaking like caveman while keeping full technical accuracy. Supports intensity levels618.3Kskills.sh installs
2mattpocock avatargrill-memattpocock/skillsA relentless interview to sharpen a plan or design.1.5Mskills.sh installs
3shadcn avatarimproveshadcn/improveSurvey any codebase as a senior advisor and produce prioritized, self-contained implementation plans for OTHER models/agents to execute. Strictly read-only on s40Kskills.sh installs
4obra avatarsystematic-debuggingobra/superpowersUse when encountering any bug, test failure, or unexpected behavior, before proposing fixes326.7Kskills.sh installs
5forrestchang avatarkarpathy-guidelinesforrestchang/andrej-karpathy-skillsBehavioral guidelines to reduce common LLM coding mistakes through explicit assumptions, simplicity, and verifiable success criteria.17.9Kskills.sh installs
6vercel-labs avatarfind-skillsvercel-labs/skillsHelps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express int4.3Mskills.sh installs