Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

we built an extremely good code search agent. it’s called tracer, and it can search across the entire github in less than 5 minutes and come back with a clean report. you can try it by running 'bunx nia-wizard'

Arlan

20,422 subscribers

91,171 views • 3 months ago •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

We built the best codebase search to give any agent grounded information from GitHub repos. Introducing Sandbox Search. Point it at any repo, and we’ll spin up a secure coding agent in its own sandbox to do research for you. Use inside claude code, openclaw, cursor, and more.

We built the best codebase search to give any agent grounded information from GitHub repos. Introducing Sandbox Search. Point it at any repo, and we’ll spin up a secure coding agent in its own sandbox to do research for you. Use inside claude code, openclaw, cursor, and more.

Arlan

12,412 views • 2 months ago

Your project deserves docs. $ npx skills add nuxt-content/docus Then: "/create-docs" Full doc site with SEO, MCP, copy page, llms.txt, everything automatic. Your AI can now read your docs. Your users can search it. Google can index it. In less than 2 minutes, give it a try👇

Your project deserves docs. $ npx skills add nuxt-content/docus Then: "/create-docs" Full doc site with SEO, MCP, copy page, llms.txt, everything automatic. Your AI can now read your docs. Your users can search it. Google can index it. In less than 2 minutes, give it a try👇

Hugo

13,676 views • 4 months ago

Introducing exa-code, a big step towards eliminating LLM code hallucination. We indexed 1B+ docs pages, Github repos, StackOverflow posts, and more. Given a query, exa-code initiates a hybrid search over this data, chunks it, and returns a concatenated, token-efficient string. In our code hallucination eval, exa-code outperforms every popular web search tool (including Exa!). Available for free: How we built it:

Introducing exa-code, a big step towards eliminating LLM code hallucination. We indexed 1B+ docs pages, Github repos, StackOverflow posts, and more. Given a query, exa-code initiates a hybrid search over this data, chunks it, and returns a concatenated, token-efficient string. In our code hallucination eval, exa-code outperforms every popular web search tool (including Exa!). Available for free: How we built it:

Exa

206,536 views • 8 months ago

Today, we launched a brand-new intelligent Search box. Here's what that means: An upgrade to the Search experience with our most advanced Gemini 3.5 models, bringing with them our latest agentic capabilities You can ask across modalities (text, images, files, and videos) and Search can reason across them all We're combining AI Overviews and AI Mode into one, seamless AI Search experience. So you can ask follow-up questions, build context, and received even more tailored and personalized responses This new AI Search experience is live today across desktop and mobile, worldwide.

Google AI

43,489 views • 23 days ago

Big change in Dexter today. We replaced 20+ financial tools with a single Financial Search sub-agent. It’s web search, but for financial data. Dexter can search across: • earnings • SEC filings • stock prices • news + more Bonus: it’s fully extensible. Add crypto, options, or any data you need.

Big change in Dexter today. We replaced 20+ financial tools with a single Financial Search sub-agent. It’s web search, but for financial data. Dexter can search across: • earnings • SEC filings • stock prices • news + more Bonus: it’s fully extensible. Add crypto, options, or any data you need.

virat

24,561 views • 4 months ago

We just shipped /agent support to the Firecrawl MCP 🚀 Now you can use /agent directly inside ChatGPT, Claude, Cursor, and more. Describe the data you need and watch it search the web, navigate, and return structured data without leaving your workflow. Try it out today 👇

We just shipped /agent support to the Firecrawl MCP 🚀 Now you can use /agent directly inside ChatGPT, Claude, Cursor, and more. Describe the data you need and watch it search the web, navigate, and return structured data without leaving your workflow. Try it out today 👇

Firecrawl

17,441 views • 5 months ago

The refreshed Scira API site is now live. The one-of-a-kind Agent Search API is in production. Search, People, and X Agents. Sign up and try it here →

The refreshed Scira API site is now live. The one-of-a-kind Agent Search API is in production. Search, People, and X Agents. Sign up and try it here →

Zaid

16,010 views • 5 months ago

Big moment for Postgres! Search has always been Postgres' weak spot, and everyone just accepted it. If you needed a real relevance-ranked keyword search, the default answer was to spin up Elasticsearch or add Algolia and deal with the data sync headaches forever. The problem isn't that Postgres can't do text search. It can. But the built-in `ts_rank` function uses a basic term frequency algorithm that doesn't come close to what modern search engines deliver. So teams end up: - Running a separate Elasticsearch cluster just for search - Building sync pipelines that inevitably drift out of consistency - Paying for managed search services that charge per query - Accepting mediocre search relevance because "good enough" ships faster But this is actually a solvable problem. You can realistically bring industry-standard search ranking directly into Postgres, which eliminates the need for external infra entirely. This exact solution is now available with the newly open-sourced pg_textsearch by Tiger Data - Creators of TimescaleDB, a Postgres extension that brings true BM25 relevance ranking into the database. BM25 is the algorithm behind Elasticsearch, Lucene, and most modern search engines. Now it runs natively in Postgres. Here's what pg_textsearch enables: - True BM25 ranking with configurable parameters (the same algorithm powering production search systems) - Simple SQL syntax: `ORDER BY content 'search terms'` - Works with Postgres text search configurations for multiple languages - Pairs naturally with pgvector for hybrid keyword + semantic search That last point matters a lot for RAG apps. The video below shows this in action, and I worked with the team to put this together. You can now do hybrid retrieval (combining keyword matching with vector similarity) in a single database, without stitching together multiple systems. The syntax is clean enough that you can add relevance-ranked search to existing queries in minutes. pg_textsearch is fully open-source under the PostgreSQL license. You can find a link to their GitHub repo in the next tweet.

Big moment for Postgres! Search has always been Postgres' weak spot, and everyone just accepted it. If you needed a real relevance-ranked keyword search, the default answer was to spin up Elasticsearch or add Algolia and deal with the data sync headaches forever. The problem isn't that Postgres can't do text search. It can. But the built-in `ts_rank` function uses a basic term frequency algorithm that doesn't come close to what modern search engines deliver. So teams end up: - Running a separate Elasticsearch cluster just for search - Building sync pipelines that inevitably drift out of consistency - Paying for managed search services that charge per query - Accepting mediocre search relevance because "good enough" ships faster But this is actually a solvable problem. You can realistically bring industry-standard search ranking directly into Postgres, which eliminates the need for external infra entirely. This exact solution is now available with the newly open-sourced pg_textsearch by Tiger Data - Creators of TimescaleDB, a Postgres extension that brings true BM25 relevance ranking into the database. BM25 is the algorithm behind Elasticsearch, Lucene, and most modern search engines. Now it runs natively in Postgres. Here's what pg_textsearch enables: - True BM25 ranking with configurable parameters (the same algorithm powering production search systems) - Simple SQL syntax: `ORDER BY content 'search terms'` - Works with Postgres text search configurations for multiple languages - Pairs naturally with pgvector for hybrid keyword + semantic search That last point matters a lot for RAG apps. The video below shows this in action, and I worked with the team to put this together. You can now do hybrid retrieval (combining keyword matching with vector similarity) in a single database, without stitching together multiple systems. The syntax is clean enough that you can add relevance-ranked search to existing queries in minutes. pg_textsearch is fully open-source under the PostgreSQL license. You can find a link to their GitHub repo in the next tweet.

Akshay 🚀

215,117 views • 4 months ago

Introducing: Starlight — everything we know about building docs, wrapped up in an easy-to-use template. 🧩 built-in site search, navigation, i18n, a11y, seo, clean typography, code highlighting, dark mode, "edit in GitHub", MDX, Markdoc AND MORE! 🌟

Introducing: Starlight — everything we know about building docs, wrapped up in an easy-to-use template. 🧩 built-in site search, navigation, i18n, a11y, seo, clean typography, code highlighting, dark mode, "edit in GitHub", MDX, Markdoc AND MORE! 🌟

Astro

195,678 views • 3 years ago

We just added first-class support the GitHub Copilot CLI! Built-in voice transcription powered by Wispr Flow, an image upload button, and our built-in file explorer + code review panel. Try it out on the latest version.

We just added first-class support the GitHub Copilot CLI! Built-in voice transcription powered by Wispr Flow, an image upload button, and our built-in file explorer + code review panel. Try it out on the latest version.

Warp

72,728 views • 4 months ago

We just launched the Brave Search API Playground to make it easier and quicker to experiment with our Web search API. Choose from over 20 parameters and a variety of specialized search types to dial in queries with powerful precision. Try it for free:

We just launched the Brave Search API Playground to make it easier and quicker to experiment with our Web search API. Choose from over 20 parameters and a variety of specialized search types to dial in queries with powerful precision. Try it for free:

Brave

12,039 views • 1 year ago

We replaced an entire 100k/month creative strategy team with an AI agent that sits in slack. I tested it side by side against our internal team and it blew them away. Here’s what it can do + 5 prompts you should steal (bookmark this)

We replaced an entire 100k/month creative strategy team with an AI agent that sits in slack. I tested it side by side against our internal team and it blew them away. Here’s what it can do + 5 prompts you should steal (bookmark this)

Arie Scherson

13,179 views • 4 months ago

MiniMax is the James Bond of AI agents. It uses the world's first open-weight model (MiniMax-M1), and it squeezes every bit of power from it. The agent takes a prompt and does more than any other agent in the market right now: 1. It can do Deep Research 2. It can write code 3. It can design web pages 4. It can build 3D models I built 5 different experiences using MiniMax and recorded them for you:

MiniMax is the James Bond of AI agents. It uses the world's first open-weight model (MiniMax-M1), and it squeezes every bit of power from it. The agent takes a prompt and does more than any other agent in the market right now: 1. It can do Deep Research 2. It can write code 3. It can design web pages 4. It can build 3D models I built 5 different experiences using MiniMax and recorded them for you:

Santiago

44,730 views • 11 months ago

I built a multimodal AI medical image diagnosis agent using Gemini 2.0 This AI Agent can: • Analyze medical scans • Detect abnormalities • Search the web • Generate patient-friendly reports 100% Opensource Code with step-by-step tutorial.

I built a multimodal AI medical image diagnosis agent using Gemini 2.0 This AI Agent can: • Analyze medical scans • Detect abnormalities • Search the web • Generate patient-friendly reports 100% Opensource Code with step-by-step tutorial.

Shubham Saboo

217,535 views • 1 year ago

Last week we shipped Agentic Wallets, our first ever wallet infrastructure built specifically for AI agents. Combined with our x402 Bazaar, your agent can search and pay for skills, APIs, and services using stablecoins. See it in action! 👇

Last week we shipped Agentic Wallets, our first ever wallet infrastructure built specifically for AI agents. Combined with our x402 Bazaar, your agent can search and pay for skills, APIs, and services using stablecoins. See it in action! 👇

Coinbase Developer Platform🛡️

98,451 views • 3 months ago

🧠 Perplexity — The Agent That Gets It! Perplexity by AIREV isn’t just an agent, it’s built to cut through noise, decode context, and deliver answers with precision on Agent Forge. 🔗 Try it on Agent Forge:

🧠 Perplexity — The Agent That Gets It! Perplexity by AIREV isn’t just an agent, it’s built to cut through noise, decode context, and deliver answers with precision on Agent Forge. 🔗 Try it on Agent Forge:

AITECH

49,029 views • 9 months ago

With Dropbox Dash, you can search the way you think. 🔎 💭 Type what you remember (“desert sunset photoshoot”) and Dash finds it across your tools. Learn more:

With Dropbox Dash, you can search the way you think. 🔎 💭 Type what you remember (“desert sunset photoshoot”) and Dash finds it across your tools. Learn more:

Dropbox

17,100 views • 7 months ago

Introducing cmux Vault: cmux now has a right sidebar with a vault pane where you can see every single Codex, Claude Code, OpenCode, and Pi session You can search through all sessions with full-text search, and drag them directly into your workspace Out in v0.64+

Introducing cmux Vault: cmux now has a right sidebar with a vault pane where you can see every single Codex, Claude Code, OpenCode, and Pi session You can search through all sessions with full-text search, and drag them directly into your workspace Out in v0.64+

Lawrence Chen

31,762 views • 27 days ago

We made it easier to search, chat with a custom agent, and view recent runs in the Notion AI beta app. Let us know what you think! 🤓

We made it easier to search, chat with a custom agent, and view recent runs in the Notion AI beta app. Let us know what you think! 🤓

Laura Sandoval

29,349 views • 10 days ago

anyone can build an agent. from scratch. in less than an hour. say 👋 and we'll DM you the free course.

anyone can build an agent. from scratch. in less than an hour. say 👋 and we'll DM you the free course.

MakerThrive

10,306 views • 1 year ago