Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

ast-grep outline is released! It gives you a fast local map of code structure, between grep and a full language server. Syntax aware, no index to maintain, and extensible through declarative extraction rules.

hd_nvim's profile picture

Herrington Darkholme

8,376 subscribers

76,474 Aufrufe • vor 13 Tagen •via X (Twitter)

BildungWissenschaft & Technologie
LIVE

Anya Rossi• Live Now

Private livecam show

0 Kommentare

Keine Kommentare verfügbar

Kommentare vom Original-Post werden hier angezeigt

Ähnliche Videos

how about using ast-grep lint messages like Cursor rules so your coding agent has the context it needs to auto-fix issues your way? example: detect hard-coded strings and replace them with translation keys. lemme know if you like this specific pro linter or if you need other custom linters for enforcing best practices or incremental migrations. 🫡 ast-grep + AI → ❤️
0:37

how about using ast-grep lint messages like Cursor rules so your coding agent has the context it needs to auto-fix issues your way? example: detect hard-coded strings and replace them with translation keys. lemme know if you like this specific pro linter or if you need other custom linters for enforcing best practices or incremental migrations. 🫡 ast-grep + AI → ❤️

Alex Bit

40,248 Aufrufe • vor 9 Monaten

grep is multimodal now. performs better then apple photos and gives you and your agent perfect search. just run npm install -g @mixedbread/mgrep
0:35

grep is multimodal now. performs better then apple photos and gives you and your agent perfect search. just run npm install -g @mixedbread/mgrep

Aamir

49,631 Aufrufe • vor 7 Monaten

I gave my coding agent a map across 3 of my repos: - Reduce ~50% token - a grep hook so every grep call has much richer info - trace any function's call chain + blast radius Really can feel my agent is getting A LOT smarter; I added to my codebase setup skill + 8-min deep dive: Copy it. Adapt it to your codebase.
8:30

I gave my coding agent a map across 3 of my repos: - Reduce ~50% token - a grep hook so every grep call has much richer info - trace any function's call chain + blast radius Really can feel my agent is getting A LOT smarter; I added to my codebase setup skill + 8-min deep dive: Copy it. Adapt it to your codebase.

Jason Zhou

80,115 Aufrufe • vor 6 Tagen

Introducing SWE-grep and SWE-grep-mini: Cognition’s model family for fast agentic search at >2,800 TPS. Surface the right files to your coding agent 20x faster. Now rolling out gradually to Windsurf users via the Fast Context subagent – or try it in our new playground!
0:28

Introducing SWE-grep and SWE-grep-mini: Cognition’s model family for fast agentic search at >2,800 TPS. Surface the right files to your coding agent 20x faster. Now rolling out gradually to Windsurf users via the Fast Context subagent – or try it in our new playground!

Cognition

663,379 Aufrufe • vor 8 Monaten

Try out our Fast Context playground that allows you to compare SWE-grep against Claude Code!: It's back up after temporary capacity issues yesterday night.
1:07

Try out our Fast Context playground that allows you to compare SWE-grep against Claude Code!: It's back up after temporary capacity issues yesterday night.

Silas Alberti

11,782 Aufrufe • vor 8 Monaten

Give Claude Code a semantic filesystem 🗃️🛠️ Giving Claude Code access to the right CLI tools over your filesystem turns it into a general agent capable of automating far more knowledge work beyond code - it can do dynamic financial/legal/medical/technical/backoffice analysis over any subset of documents. With our latest release of semtools 💫, you can now manually or *agentically* create a persistent workspace over any subset of files. This gives Claude Code the ability to get blazing-fast, local semantic search over any data, while still allowing it to chain with commands like grep/cat/etc. so that it can load in dynamic context instead of naive top-k vector search. The coding agent can dynamically index data and use those indexes, instead of having to rebuild it every time. So you get the benefits of fast search along with agentic reasoning over CLI tools mentioned above. Come check it out!
0:38

Give Claude Code a semantic filesystem 🗃️🛠️ Giving Claude Code access to the right CLI tools over your filesystem turns it into a general agent capable of automating far more knowledge work beyond code - it can do dynamic financial/legal/medical/technical/backoffice analysis over any subset of documents. With our latest release of semtools 💫, you can now manually or *agentically* create a persistent workspace over any subset of files. This gives Claude Code the ability to get blazing-fast, local semantic search over any data, while still allowing it to chain with commands like grep/cat/etc. so that it can load in dynamic context instead of naive top-k vector search. The coding agent can dynamically index data and use those indexes, instead of having to rebuild it every time. So you get the benefits of fast search along with agentic reasoning over CLI tools mentioned above. Come check it out!

Jerry Liu

77,373 Aufrufe • vor 9 Monaten

There's a built-in agent inside Claude Code you can invoke just by telling Claude to use the claude-code-guide agent Save this... you'll need it It's not a local file in your project. It's a built-in subagent defined in Claude Code's system itself. It answers questions about Claude Code CLI, the Agent SDK, and the Claude API. It uses Glob, Grep, Read, WebFetch, and WebSearch, but can't edit or write files. Its only job is to answer questions.
0:22

There's a built-in agent inside Claude Code you can invoke just by telling Claude to use the claude-code-guide agent Save this... you'll need it It's not a local file in your project. It's a built-in subagent defined in Claude Code's system itself. It answers questions about Claude Code CLI, the Agent SDK, and the Claude API. It uses Glob, Grep, Read, WebFetch, and WebSearch, but can't edit or write files. Its only job is to answer questions.

Daniel San

57,240 Aufrufe • vor 4 Monaten

🚨 AI coding agents hallucinate because they can't actually read your codebase. This MCP server fixes that. It's called Context+ and it gives AI 99% accuracy on large-scale engineering projects by building a real semantic map of your code before touching a single line. Here's what makes it different from every other MCP tool: → Tree-sitter AST parsing across 43 file extensions. Not grep. Not regex. Actual syntax trees. → Spectral Clustering that groups semantically related files into labeled clusters. Your AI finally understands what belongs together. → Obsidian-style wikilinks that map features to code files. Navigate entire codebases like a knowledge graph. → Blast radius tracing. Before any change, it shows every file and line where a symbol is imported or used. No more orphaned references. → Shadow restore points. Every AI-proposed commit creates a restore snapshot. One command to undo any change without touching git history. → Semantic search by meaning. Ask what something does. Not what it's called. The `propose_commit` tool is the wild part. It validates changes against strict rules, creates a shadow restore point, and only then writes to disk. AI can't just freestyle your production code. Works with Claude Code, Cursor, VS Code, and Windsurf. One line to install with bunx or npx. This is what responsible AI coding infrastructure actually looks like. 100% Opensource. Link in comments.
0:46

🚨 AI coding agents hallucinate because they can't actually read your codebase. This MCP server fixes that. It's called Context+ and it gives AI 99% accuracy on large-scale engineering projects by building a real semantic map of your code before touching a single line. Here's what makes it different from every other MCP tool: → Tree-sitter AST parsing across 43 file extensions. Not grep. Not regex. Actual syntax trees. → Spectral Clustering that groups semantically related files into labeled clusters. Your AI finally understands what belongs together. → Obsidian-style wikilinks that map features to code files. Navigate entire codebases like a knowledge graph. → Blast radius tracing. Before any change, it shows every file and line where a symbol is imported or used. No more orphaned references. → Shadow restore points. Every AI-proposed commit creates a restore snapshot. One command to undo any change without touching git history. → Semantic search by meaning. Ask what something does. Not what it's called. The `propose_commit` tool is the wild part. It validates changes against strict rules, creates a shadow restore point, and only then writes to disk. AI can't just freestyle your production code. Works with Claude Code, Cursor, VS Code, and Windsurf. One line to install with bunx or npx. This is what responsible AI coding infrastructure actually looks like. 100% Opensource. Link in comments.

Ihtesham Ali

29,781 Aufrufe • vor 3 Monaten

i built a very fast, virtualized filesystem for ai agents built with Redis, Vercel AI SDK and just-bash agents can search and grep files really fast because it's all in redis memory
1:31

i built a very fast, virtualized filesystem for ai agents built with Redis, Vercel AI SDK and just-bash agents can search and grep files really fast because it's all in redis memory

Josh tried coding

72,964 Aufrufe • vor 3 Monaten

Forums Ask an LLM questions about any GitHub repo, and let it grep and list and explore the source code directly. Now available via: → Web → CLI (and Skill) 🆕 → MCP 🆕
2:08

Forums Ask an LLM questions about any GitHub repo, and let it grep and list and explore the source code directly. Now available via: → Web → CLI (and Skill) 🆕 → MCP 🆕

JB

16,373 Aufrufe • vor 5 Monaten

A big announcement! Finally fff.nvim got live grep search that is actually revamping the way grepping works making it a much better search for the code *AND* solves all the QOL problems with the existing ripgrep based pickers
6:26

A big announcement! Finally fff.nvim got live grep search that is actually revamping the way grepping works making it a much better search for the code *AND* solves all the QOL problems with the existing ripgrep based pickers

Dmitriy Kovalenko

45,477 Aufrufe • vor 4 Monaten

Analyze code and scan for vulnerabilities using natural language in your terminal 🔎 → Endor Labs built a Gemini CLI Extension that acts as an MCP server to help you maintain secure dependencies.
0:35

Analyze code and scan for vulnerabilities using natural language in your terminal 🔎 → Endor Labs built a Gemini CLI Extension that acts as an MCP server to help you maintain secure dependencies.

Google for Developers

40,408 Aufrufe • vor 5 Monaten

Introducing Codex to Figma: Roundtrip between code and canvas through the Figma MCP server
0:36

Introducing Codex to Figma: Roundtrip between code and canvas through the Figma MCP server

Figma

179,484 Aufrufe • vor 4 Monaten

introducing Nozomio Labs index API. our mission is to index your entire life and put it into a single file, starting with technical sources. index repos, docs, datasets, papers, slack, and local folders. built for agents. works with cursor, claude code, openclaw, and more.
1:10

introducing Nozomio Labs index API. our mission is to index your entire life and put it into a single file, starting with technical sources. index repos, docs, datasets, papers, slack, and local folders. built for agents. works with cursor, claude code, openclaw, and more.

Arlan

34,959 Aufrufe • vor 4 Monaten

My dear software developers (and anyone who’s interested in the future of code search): I have crawled through depths of hell to bring you, one of the more important foundational piece of programming: fast, the most accurate, index free, and correct code search Here is a real time code search on leaked claude code sources, linux kernel 100k files, and chromium repo 500k files
1:06

My dear software developers (and anyone who’s interested in the future of code search): I have crawled through depths of hell to bring you, one of the more important foundational piece of programming: fast, the most accurate, index free, and correct code search Here is a real time code search on leaked claude code sources, linux kernel 100k files, and chromium repo 500k files

Dmitriy Kovalenko

190,044 Aufrufe • vor 3 Monaten

Huge DX update! We shipped a big improvement to wrangler, which means you can view and modify the state of your local KV, D!, R2 bindings through a nice local dashboard No code change required. Local explorer is available in wrangler 4.81.2 and up
3:28

Huge DX update! We shipped a big improvement to wrangler, which means you can view and modify the state of your local KV, D!, R2 bindings through a nice local dashboard No code change required. Local explorer is available in wrangler 4.81.2 and up

Confidence

11,623 Aufrufe • vor 2 Monaten

Claude Code is insane. And yes… there’s a free version. Here’s how it works: → install the free Claude Code repo → connect Nvidia NIM free API → map Opus to GLM-4.7 → run local proxy server → launch Claude Code normally → start building apps for $0 Same workflow. No monthly API bill. Save this video, you’ll stop paying for Claude Code.
7:22

Claude Code is insane. And yes… there’s a free version. Here’s how it works: → install the free Claude Code repo → connect Nvidia NIM free API → map Opus to GLM-4.7 → run local proxy server → launch Claude Code normally → start building apps for $0 Same workflow. No monthly API bill. Save this video, you’ll stop paying for Claude Code.

Julian Goldie SEO

16,651 Aufrufe • vor 2 Monaten

someone just made a tool that indexes code by meaning, not string matching this project is the first time i have seen someone treat code like a knowledge graph. sometimes i feel they are the only ones actually pushing cs most rag pipelines for agents are embarrassing and we should be chunking by semantic scope, imagine your agent's accuracy if this was used instead of simple grep google spent millions on kythe to index code and devs just did it better as a weekend hobby project. never bet against a functional programmer with a strict type system.
0:38

someone just made a tool that indexes code by meaning, not string matching this project is the first time i have seen someone treat code like a knowledge graph. sometimes i feel they are the only ones actually pushing cs most rag pipelines for agents are embarrassing and we should be chunking by semantic scope, imagine your agent's accuracy if this was used instead of simple grep google spent millions on kythe to index code and devs just did it better as a weekend hobby project. never bet against a functional programmer with a strict type system.

𝕱𝖔𝖗𝕷𝖔𝖔𝖕

25,587 Aufrufe • vor 4 Monaten

The best *code embedding* model in the market right now was just released: Qodo-Embed-1 — There are two flavors: A lite model with 1.5B parameters and a medium model with 7B parameters (Hugging Face links below). If you want to index a large codebase (supports 10M+ lines of code), this is the model you want. 1. Index your repositories 2. Ask anything (including test and code generation) The models are optimized to answer natural language questions or code-to-code questions. The video here shows the model indexing 90 repositories (!!!!!) and letting the user ask questions about them. The simplest way to use the model is through the Qodo Gen AI extension in Visual Studio Code, Cursor, or JetBrains (see link below).
4:18

The best *code embedding* model in the market right now was just released: Qodo-Embed-1 — There are two flavors: A lite model with 1.5B parameters and a medium model with 7B parameters (Hugging Face links below). If you want to index a large codebase (supports 10M+ lines of code), this is the model you want. 1. Index your repositories 2. Ask anything (including test and code generation) The models are optimized to answer natural language questions or code-to-code questions. The video here shows the model indexing 90 repositories (!!!!!) and letting the user ask questions about them. The simplest way to use the model is through the Qodo Gen AI extension in Visual Studio Code, Cursor, or JetBrains (see link below).

Santiago

56,584 Aufrufe • vor 1 Jahr