Bookmarks

Bookmarks

49953 bookmarks
Custom sorting
AI Readyな開発環境の整え方
AI Readyな開発環境の整え方
Orchestration Guildメンバーの迫川です。普段はAgent platformの開発をしています。この記事は、社内ワークショップOrchestration Development Wor...
·techblog.lycorp.co.jp·
AI Readyな開発環境の整え方
The Monorepo Advantage for AI Agents | Nx Blog
The Monorepo Advantage for AI Agents | Nx Blog
AI agents underperform not because of the models but because of the architecture around them. Repo boundaries limit what agents can read, what they can write, and what they can remember.
·nx.dev·
The Monorepo Advantage for AI Agents | Nx Blog
Prompt Caching In Agents | EARENDIL
Prompt Caching In Agents | EARENDIL
How prompt caching shapes the cost, latency, tools, and architecture of coding agents, and what Pi does to keep cache behavior visible.
·earendil.com·
Prompt Caching In Agents | EARENDIL
GitHub - forloopcodes/contextplus: Semantic Intelligence for Large-Scale Engineering. Context+ is an MCP server designed for developers who demand 99% accuracy. By combining RAG, Tree-sitter AST, Spectral Clustering, and Obsidian-style linking, Context+ turns a massive codebase into a searchable, hierarchical feature graph. · GitHub
GitHub - forloopcodes/contextplus: Semantic Intelligence for Large-Scale Engineering. Context+ is an MCP server designed for developers who demand 99% accuracy. By combining RAG, Tree-sitter AST, Spectral Clustering, and Obsidian-style linking, Context+ turns a massive codebase into a searchable, hierarchical feature graph. · GitHub
Semantic Intelligence for Large-Scale Engineering. Context+ is an MCP server designed for developers who demand 99% accuracy. By combining RAG, Tree-sitter AST, Spectral Clustering, and Obsidian-st...
·github.com·
GitHub - forloopcodes/contextplus: Semantic Intelligence for Large-Scale Engineering. Context+ is an MCP server designed for developers who demand 99% accuracy. By combining RAG, Tree-sitter AST, Spectral Clustering, and Obsidian-style linking, Context+ turns a massive codebase into a searchable, hierarchical feature graph. · GitHub
Matt Pocock on X: "Here's a decision tree for when you get to the end of a piece of work, and you're not sure how to continue: - Continue in the current session - /clear - /handoff - Use a subagent - /compact Posting for feedback. Which parts are confusing? What questions does it raise? https://t.co/4OSexT09u4" / X
Matt Pocock on X: "Here's a decision tree for when you get to the end of a piece of work, and you're not sure how to continue: - Continue in the current session - /clear - /handoff - Use a subagent - /compact Posting for feedback. Which parts are confusing? What questions does it raise? https://t.co/4OSexT09u4" / X
- Continue in the current session - /clear - /handoff - Use a subagent - /compact Posting for feedback. Which parts are confusing? What questions does it raise?
·x.com·
Matt Pocock on X: "Here's a decision tree for when you get to the end of a piece of work, and you're not sure how to continue: - Continue in the current session - /clear - /handoff - Use a subagent - /compact Posting for feedback. Which parts are confusing? What questions does it raise? https://t.co/4OSexT09u4" / X
mikeyobrien/pi-tidy-tools: Tidy, reason-first tool output for pi. Every tool call in two lines: why it ran, and what it returned. Diffs and output on demand.
mikeyobrien/pi-tidy-tools: Tidy, reason-first tool output for pi. Every tool call in two lines: why it ran, and what it returned. Diffs and output on demand.
Tidy, reason-first tool output for pi. Every tool call in two lines: why it ran, and what it returned. Diffs and output on demand. - mikeyobrien/pi-tidy-tools
·github.com·
mikeyobrien/pi-tidy-tools: Tidy, reason-first tool output for pi. Every tool call in two lines: why it ran, and what it returned. Diffs and output on demand.
termcn
termcn
A collection of beautifully designed, accessible, and customizable terminal UI components. Built on Ink and OpenTUI. Works with shadcn/ui.
·termcn.dev·
termcn
Boris Cherny on X: "I talk to engineers at other companies every day and hear the same thing: one person is 10x'ing their output with Claude but the rest of the org hasn't caught up. Watching teams adopt AI, I keep seeing the same 4 steps. I mapped them out here: Steps of AI Adoption" / X
Boris Cherny on X: "I talk to engineers at other companies every day and hear the same thing: one person is 10x'ing their output with Claude but the rest of the org hasn't caught up. Watching teams adopt AI, I keep seeing the same 4 steps. I mapped them out here: Steps of AI Adoption" / X
Watching teams adopt AI, I keep seeing the same 4 steps. I mapped them out here: Steps of AI Adoption
·x.com·
Boris Cherny on X: "I talk to engineers at other companies every day and hear the same thing: one person is 10x'ing their output with Claude but the rest of the org hasn't caught up. Watching teams adopt AI, I keep seeing the same 4 steps. I mapped them out here: Steps of AI Adoption" / X
Agentic Testing: Where Agents Fit in the E2E Testing Stack
Agentic Testing: Where Agents Fit in the E2E Testing Stack
Abstract Agent-driven end-to-end (E2E) tests add a new exploratory layer to testing, but should they replace traditional deterministic tests? We ran more than 200 agentic E2E workflows using the Playwright MCP, Playwright CLI, and agent-generated Playwright tests in test workspaces using non-production data to find out how agentic testing could fit into both our and…
·slack.engineering·
Agentic Testing: Where Agents Fit in the E2E Testing Stack
rivet-dev/agentos: Give agents an operating system as a library. Runs in your existing backend – no sandboxes, VMs, or SaaS. Powered by WebAssembly & V8 isolates.
rivet-dev/agentos: Give agents an operating system as a library. Runs in your existing backend – no sandboxes, VMs, or SaaS. Powered by WebAssembly & V8 isolates.
Give agents an operating system as a library. Runs in your existing backend – no sandboxes, VMs, or SaaS. Powered by WebAssembly & V8 isolates. - rivet-dev/agentos
·github.com·
rivet-dev/agentos: Give agents an operating system as a library. Runs in your existing backend – no sandboxes, VMs, or SaaS. Powered by WebAssembly & V8 isolates.
Peter Steinberger 🦞 on X: "5.6 Terra high is underrated. Switched @clawsweeper (GitHub review bot) to it and it's ~40% faster overall with negligible quality loss. Better than 5.5 on all counts. Massively cheaper. (Tried xhigh but that negates perf wins, didn't make a noticable difference in review evals)" / Twitter
Peter Steinberger 🦞 on X: "5.6 Terra high is underrated. Switched @clawsweeper (GitHub review bot) to it and it's ~40% faster overall with negligible quality loss. Better than 5.5 on all counts. Massively cheaper. (Tried xhigh but that negates perf wins, didn't make a noticable difference in review evals)" / Twitter
(Tried xhigh but that negates perf wins, didn't make a noticable difference in review evals)
·x.com·
Peter Steinberger 🦞 on X: "5.6 Terra high is underrated. Switched @clawsweeper (GitHub review bot) to it and it's ~40% faster overall with negligible quality loss. Better than 5.5 on all counts. Massively cheaper. (Tried xhigh but that negates perf wins, didn't make a noticable difference in review evals)" / Twitter
「第二の脳」とやらについて
「第二の脳」とやらについて
ClaudeとObsidianを使って「第二の脳」を作る、という話を読んだ。 (これ↓) https://x.com/chizevsm5/status/2079513704870142428 ふーん。 まず最初にいっておくと、便利なんだろうとは思う。 自分が読んだ文章だの、仕事で調べたことだの、…
·anond.hatelabo.jp·
「第二の脳」とやらについて
PieX — Pi Extensions
PieX — Pi Extensions
Core capabilities from top coding agents, packaged as npm packages for on-demand install into Pi.
·piex.dev·
PieX — Pi Extensions