duckduckgo-search

Name: duckduckgo-search
Author: AlexAI-MCP

132stars24forks

How to install duckduckgo-search?

alexai-mcp/hermes-ccc/duckduckgo-search

$npx -y skills add AlexAI-MCP/hermes-CCC --skill duckduckgo-search

Installs into the current project.

Summary

Free web search via DuckDuckGo - no API key needed. Text, news, images. Use as fallback when other search tools unavailable.

Files · 1

View on GitHub

SKILL.md

1	# DuckDuckGo Search
2
3	## Purpose
4
5	- Use this skill for lightweight web search without an API key.
6	- It is useful as a fallback when paid search APIs or first-party tools are unavailable.
7	- The library supports text, news, and image search.
8	- This is a pragmatic option for prototyping, research helpers, and lightweight retrieval.
9
10	## Install
11
12	```bash
13	pip install duckduckgo-search
14	```
15
16	## Why Use It
17
18	- No API key required.
19	- Easy Python integration.
20	- Useful CLI for quick terminal searches.
21	- Supports regions and time filters for fresher results.
22	- Good fallback for general web discovery.
23
24	## Python API
25
26	- The main entry point is the `DDGS` class.
27	- Create a client and call the relevant search method.
28	- Iterate the generator or cast results to a list.
29
30	## Text Search Example
31
32	```python
33	from duckduckgo_search import DDGS
34
35	with DDGS() as ddgs:
36	results = ddgs.text("vector databases for rag", max_results=10)
37	for item in results:
38	print(item["title"])
39	print(item["href"])
40	print(item["body"])
41	print()
42	```
43
44	- `text()` is the default choice for general web results.
45	- Use concise queries first, then refine.
46	- Extract only the fields you actually need for downstream processing.
47
48	## News Search Example
49
50	```python
51	from duckduckgo_search import DDGS
52
53	with DDGS() as ddgs:
54	results = ddgs.news(
55	keywords="open source llm releases",
56	max_results=10,
57	region="us-en",
58	timelimit="w",
59	)
60	for item in results:
61	print(item["title"])
62	print(item["date"])
63	print(item["url"])
64	```
65
66	- News search is better than general text search when recency matters.
67	- Useful parameters include `keywords`, `max_results`, `region`, and `timelimit`.
68	- Prefer short keyword-focused queries over verbose natural language.
69
70	## Image Search Example
71
72	```python
73	from duckduckgo_search import DDGS
74
75	with DDGS() as ddgs:
76	results = ddgs.images("server rack diagram", max_results=10)
77	for item in results:
78	print(item["title"])
79	print(item["image"])
80	```
81
82	- `ddgs.images(keywords, max_results)` is the simplest path for image discovery.
83	- Verify licensing and usage rights before reuse.
84	- Image results are best for inspiration, references, and visual discovery rather than authoritative facts.
85
86	## CLI Usage
87
88	```bash
89	ddgs text -k "query" -m 10
90	```
91
92	- `text` runs a standard web search.
93	- `-k` sets the keywords.
94	- `-m 10` limits the maximum number of results.
95	- This is useful for shell scripts or quick ad hoc research.
96
97	## CLI Patterns
98
99	```bash
100	ddgs text -k "python async queue patterns" -m 10
101	ddgs news -k "gpu inference news" -m 5
102	ddgs images -k "er diagram examples" -m 8
103	```
104
105	- Use CLI mode when you want zero boilerplate.
106	- Use Python mode when you need structured post-processing.
107
108	## Regions
109
110	- `wt-wt` for global results
111	- `us-en` for United States English
112	- `kr-ko` for Korea Korean
113	- regional values can materially change ranking and language mix
114
115	Region examples:
116
117	```python
118	results = ddgs.text("open banking regulation", region="wt-wt", max_results=10)
119	results = ddgs.text("AI policy", region="us-en", max_results=10)
120	results = ddgs.news("반도체 투자", region="kr-ko", max_results=10)
121	```
122
123	## Time Limits
124
125	- `d` for day
126	- `w` for week
127	- `m` for month
128	- `y` for year
129
130	Use time limits when:
131
132	- tracking current events
133	- watching new releases
134	- checking recent blog or news coverage
135	- reducing stale results
136
137	## Rate Limiting
138
139	- Do not hammer the service with rapid repeated requests.
140	- Add a short sleep between loops or batches.
141	- Cache results locally when queries repeat.
142	- If you are scraping many queries, batch slowly and keep scope tight.
143
144	Simple pattern:
145
146	```python
147	import time
148	from duckduckgo_search import DDGS
149
150	queries = ["llm evals", "vector db benchmarks", "open source agents"]
151
152	with DDGS() as ddgs:
153	for q in queries:
154	results = list(ddgs.text(q, max_results=5))
155	print(q, len(results))
156	time.sleep(2)
157	```
158
159	## Query Strategy
160
161	- Start broad, then narrow.
162	- Prefer keywords over long questions.
163	- Use quotes only when exact phrase matching matters.
164	- Switch to news mode when freshness matters more than general authority.
165	- Use the region parameter intentionally rather than leaving locality to chance.
166
167	## Fallback Positioning
168
169	- No API key required means this is a practical fallback.
170	- It is well suited to a `WebSearch` fallback path in tools or scripts.
171	- When other providers fail, DDG search can still return useful retrieval candidates.
172	- It should not be treated as a guaranteed enterprise-grade SLA service.
173
174	## Practical Research Workflow
175
176	1. Run a text search for broad discovery.
177	2. Switch

People who liked this also viewed

6 picks

Type

microsoft-foundryDeploy, evaluate, fine-tune, and manage Foundry agents end-to-end with azd: hosted agent scaffold/run/deploy, prompt agent create, batch eval, continuous eval, prompt optimizer, Agent Optimizer scaffoSkillsJul 2026476k1.3k
azure-deployExecute Azure deployments for ALREADY-PREPARED applications that have existing .azure/deployment-plan.md and infrastructure files. DO NOT use this skill when the user asks to CREATE a new application SkillsJul 2026472k1.3k
azure-preparePrepare azd-based Azure projects for deployment: generates azure.yaml, infrastructure (Bicep/Terraform), and Dockerfiles for the Azure Developer CLI (azd) workflow. USE ONLY when the user explicitly wSkillsJul 2026471k1.3k
azure-validate--- name: azure-validate description: "Pre-deployment validation for Azure readiness. Run deep checks on configuration, infrastructure (Bicep or Terraform), RBAC role assignments, managed identity pSkillsJul 2026471k1.3k
azure-aigatewayConfigure Azure API Management as an AI Gateway for AI models, MCP tools, and agents. WHEN: semantic caching, token limit, content safety, load balancing, AI model governance, MCP rate limiting, jailbSkillsJul 2026470k1.3k
azure-hosted-copilot-sdkOfficial agent plugin providing skills and MCP server configurations for Azure scenarios.SkillsJul 2026424k1.3k

duckduckgo-search

132stars24forks

View on GitHub

How to install duckduckgo-search?

alexai-mcp/hermes-ccc/duckduckgo-search

$npx -y skills add AlexAI-MCP/hermes-CCC --skill duckduckgo-search

Installs into the current project.

Summary

Free web search via DuckDuckGo - no API key needed. Text, news, images. Use as fallback when other search tools unavailable.

Files · 1

View on GitHub

SKILL.md

1	# DuckDuckGo Search
2
3	## Purpose
4
5	- Use this skill for lightweight web search without an API key.
6	- It is useful as a fallback when paid search APIs or first-party tools are unavailable.
7	- The library supports text, news, and image search.
8	- This is a pragmatic option for prototyping, research helpers, and lightweight retrieval.
9
10	## Install
11
12	```bash
13	pip install duckduckgo-search
14	```
15
16	## Why Use It
17
18	- No API key required.
19	- Easy Python integration.
20	- Useful CLI for quick terminal searches.
21	- Supports regions and time filters for fresher results.
22	- Good fallback for general web discovery.
23
24	## Python API
25
26	- The main entry point is the `DDGS` class.
27	- Create a client and call the relevant search method.
28	- Iterate the generator or cast results to a list.
29
30	## Text Search Example
31
32	```python
33	from duckduckgo_search import DDGS
34
35	with DDGS() as ddgs:
36	results = ddgs.text("vector databases for rag", max_results=10)
37	for item in results:
38	print(item["title"])
39	print(item["href"])
40	print(item["body"])
41	print()
42	```
43
44	- `text()` is the default choice for general web results.
45	- Use concise queries first, then refine.
46	- Extract only the fields you actually need for downstream processing.
47
48	## News Search Example
49
50	```python
51	from duckduckgo_search import DDGS
52
53	with DDGS() as ddgs:
54	results = ddgs.news(
55	keywords="open source llm releases",
56	max_results=10,
57	region="us-en",
58	timelimit="w",
59	)
60	for item in results:
61	print(item["title"])
62	print(item["date"])
63	print(item["url"])
64	```
65
66	- News search is better than general text search when recency matters.
67	- Useful parameters include `keywords`, `max_results`, `region`, and `timelimit`.
68	- Prefer short keyword-focused queries over verbose natural language.
69
70	## Image Search Example
71
72	```python
73	from duckduckgo_search import DDGS
74
75	with DDGS() as ddgs:
76	results = ddgs.images("server rack diagram", max_results=10)
77	for item in results:
78	print(item["title"])
79	print(item["image"])
80	```
81
82	- `ddgs.images(keywords, max_results)` is the simplest path for image discovery.
83	- Verify licensing and usage rights before reuse.
84	- Image results are best for inspiration, references, and visual discovery rather than authoritative facts.
85
86	## CLI Usage
87
88	```bash
89	ddgs text -k "query" -m 10
90	```
91
92	- `text` runs a standard web search.
93	- `-k` sets the keywords.
94	- `-m 10` limits the maximum number of results.
95	- This is useful for shell scripts or quick ad hoc research.
96
97	## CLI Patterns
98
99	```bash
100	ddgs text -k "python async queue patterns" -m 10
101	ddgs news -k "gpu inference news" -m 5
102	ddgs images -k "er diagram examples" -m 8
103	```
104
105	- Use CLI mode when you want zero boilerplate.
106	- Use Python mode when you need structured post-processing.
107
108	## Regions
109
110	- `wt-wt` for global results
111	- `us-en` for United States English
112	- `kr-ko` for Korea Korean
113	- regional values can materially change ranking and language mix
114
115	Region examples:
116
117	```python
118	results = ddgs.text("open banking regulation", region="wt-wt", max_results=10)
119	results = ddgs.text("AI policy", region="us-en", max_results=10)
120	results = ddgs.news("반도체 투자", region="kr-ko", max_results=10)
121	```
122
123	## Time Limits
124
125	- `d` for day
126	- `w` for week
127	- `m` for month
128	- `y` for year
129
130	Use time limits when:
131
132	- tracking current events
133	- watching new releases
134	- checking recent blog or news coverage
135	- reducing stale results
136
137	## Rate Limiting
138
139	- Do not hammer the service with rapid repeated requests.
140	- Add a short sleep between loops or batches.
141	- Cache results locally when queries repeat.
142	- If you are scraping many queries, batch slowly and keep scope tight.
143
144	Simple pattern:
145
146	```python
147	import time
148	from duckduckgo_search import DDGS
149
150	queries = ["llm evals", "vector db benchmarks", "open source agents"]
151
152	with DDGS() as ddgs:
153	for q in queries:
154	results = list(ddgs.text(q, max_results=5))
155	print(q, len(results))
156	time.sleep(2)
157	```
158
159	## Query Strategy
160
161	- Start broad, then narrow.
162	- Prefer keywords over long questions.
163	- Use quotes only when exact phrase matching matters.
164	- Switch to news mode when freshness matters more than general authority.
165	- Use the region parameter intentionally rather than leaving locality to chance.
166
167	## Fallback Positioning
168
169	- No API key required means this is a practical fallback.
170	- It is well suited to a `WebSearch` fallback path in tools or scripts.
171	- When other providers fail, DDG search can still return useful retrieval candidates.
172	- It should not be treated as a guaranteed enterprise-grade SLA service.
173
174	## Practical Research Workflow
175
176	1. Run a text search for broad discovery.
177	2. Switch

People who liked this also viewed

6 picks

Type