Nimble
@nimble_search
Expert-level web search for AI agents. Higher accuracy, lower token costs, full auditability — built for production.
6 Following 4.4K Followers
Nimble is now an OpenAI plugin for ChatGPT and Codex, giving OpenAI models deeper context from the web.
With Nimble, ChatGPT and Codex can:
- Discover more complete web context by combining web search with computer use to navigate and paginate websites, capturing data that doesn’t show up in search results
- Improve web search efficiency with self-learning agents that optimize web retrieval methodology after every run
- Govern web retrieval with source controls, confidence scores, and evidence for every data point
Available now in the Plugins tab.
Learn more here:
Show more
Token Efficiency is a critical metric here. @Tiny_Fish , @nimble_search & @p0 are the Search APIs that give maximally efficient information to the Agent by having least median LLM token costs per ticket.
Show more
agents can run for longer than ever.
now the hard part is keeping them reliable as the work compounds.
with @OpenAI @bfl_ai @liquidai @nimble_search @broccolicom
we’re bringing you a hack this Friday built around long-horizon agents and the infra they need to stay consistent
📆 Sep 25 · SF
👥 Solo or teams of up to 4
🏆 Cash prizes & credits
⚡ 6 hours to ship
apply now:
judges and speakers including @yanivm13 @vivmarquez and more
Show more
Building finance agents? Give them deeper access to the web to get more complete and relevant context.
3 @LangChain examples for regulatory monitoring, due diligence, and deal sourcing, using Nimble’s Search API or Agent API.
Code + walkthroughs:
Show more
Enable Databricks Genie One to search the web, retrieve granular web data, structure it into fields, and stream it into you tables. In seconds.
Learn more about Nimble's integration with Genie One ⬇️
Show more
Agents that need live web data can now add nimble_research and nimble_extract to an agent spec by name, instead of wiring up your own scraping and search code. 👇
nimble_research hands a task to a @nimble_search Web Search Agent and returns per-claim citations with a confidence signal. It needs pip install 'omnigent[nimble]'. nimble_extract runs one of your Nimble extract templates against the live web and returns structured JSON. Both resolve inside the Omnigent runner.
For a quick lookup, set search_provider: nimble on web_search. That path needs no extra.
🔗 Read the full post:
#Omnigent# #AIAgents#
Show more
Give your @LangChain agents richer, deeper, and more cost efficient web context.
Nimble integrates with LangChain so you agents can:
1) run blazing-fast web searches, or...
2) execute complex research workflows with self-learning agents that adapt web search/crawling to your use case
Specialized web search ➡️ more accuracte and complete web context for your agents, using less tokens
Read the announcement:
Cookbook for company research:
Show more
Same prompt to Claude Code...with and without Nimble for deep research.
Nimble gives your agent access to web data it didn't have previously.
Try it free!
Web search can quietly become one of the biggest drivers of AI costs.
With Nimble, your AI can search the web for 8x less.
New: Nimble integrates with LiteLLM, giving every model a consistent web search tool to retrieve high-quality web context, more efficiently.
Cookbook: We built a Claim Verifier that shows how LiteLLM and Nimble work together to equip any model with the right context , for the right job.
Read the blog:
Show more
Nimble now runs natively inside Omnigent, Databricks' open-source agent meta-harness.
See en example of what that looks like with our new cookbook: an agent that decides which API to use, then ships the integration.
A Nimble Web Search Agent researches each candidate against one shared schema, returning per-field citations and confidence. A Claude head and a GPT head debate the evidence. A coding agent implements the winner on a reviewed branch.
Cookbook:
Docs:
Show more
Omnigent v0.9.0 is now available! 🎉
🧭 Smart routing (@databricks AI Gateway + OSS)
🎨 Refreshed web UI
🧰 More sandbox and deployment control
🤖 Grok Build harness + example agents
🌐 nimble_extract and nimble_research builtins
🔗 Full details, bug fixes, and upgrade notes:
#Omnigent# #AIAgents#
Show more
Web search can quietly become one of the biggest drivers of AI costs.
With Nimble, your AI can search the web for 8x less.
Same prompt to Claude Code...with and without Nimble for deep research.
Nimble gives your agent access to web data it didn't have previously.
Try it free!
Give your @LangChain agents richer, deeper, and more cost efficient web context.
Nimble integrates with LangChain so you agents can:
1) run blazing-fast web searches, or...
2) execute complex research workflows with self-learning agents that adapt web search/crawling to your use case
Specialized web search ➡️ more accuracte and complete web context for your agents, using less tokens
Read the announcement:
Cookbook for company research:
Show more
