惯性聚合 高效追踪和阅读你感兴趣的博客、新闻、科技资讯
阅读原文 在惯性聚合中打开

推荐订阅源

云风的 BLOG
云风的 BLOG
The GitHub Blog
The GitHub Blog
Y
Y Combinator Blog
博客园 - 三生石上(FineUI控件)
T
The Blog of Author Tim Ferriss
宝玉的分享
宝玉的分享
Hugging Face - Blog
Hugging Face - Blog
WordPress大学
WordPress大学
V
Visual Studio Blog
小众软件
小众软件
Cyber Security Advisories - MS-ISAC
Cyber Security Advisories - MS-ISAC
MongoDB | Blog
MongoDB | Blog
V
V2EX
钛媒体:引领未来商业与生活新知
钛媒体:引领未来商业与生活新知
博客园 - 【当耐特】
Microsoft Azure Blog
Microsoft Azure Blog
The Cloudflare Blog
H
Hackread – Cybersecurity News, Data Breaches, AI and More
freeCodeCamp Programming Tutorials: Python, JavaScript, Git & More
Engineering at Meta
Engineering at Meta
L
LangChain Blog
Martin Fowler
Martin Fowler
GbyAI
GbyAI
博客园 - 司徒正美

Hacker News - Newest: "AI"

AI can't read an investor deck AI as an attorney? Student uses ChatGPT, Gemini to sue UW over alleged racial discrimination Hacking MCP Servers in AI Systems – The Rug Pull: Tool Changes After Approval GitHub - MeepCastana/KubeezCut: Free Web based video editor Can AI judge journalism? A Thiel-backed startup says yes, even if it risks chilling whistleblowers Coming soon: 10 Things That Matter in AI Right Now DARPA built an AI to fact-check enemy weapons claims What explains heterogeneity in AI adoption? When AI Meets Muscle: Context-Aware Electrical Stimulation Promises a New Way to Guide Human Movements - Department of Computer Science AI Changed How We Build. It Did Not Change What Matters. Linux rules on using AI-generated code - Copilot is OK, but humans must take 'full responsibility for the… Meta spins up AI version of Mark Zuckerberg to engage with employees Code Mode: Let Your AI Write Programs, Not Just Call Tools | TanStack Blog GitHub - Delavalom/graft: Go framework for building AI agents. Type-safe tools, multi-provider (OpenAI, Anthropic, Gemini, Bedrock), zero vendor SDKs. India's TCS tops estimates, says new AI models did not dent services demand Gen Z's fading AI hype Strong feeling: we are in a folded AI reality GitHub - machinarii/total-recall-catalog: A reference catalog of latest knowledge retrieval, memory & RAG systems GitHub - mensfeld/code-on-incus: Give each AI agent its own isolated machine with root, Docker, and systemd. Active defense detects and stops threats automatically.. Quantization, LoRA, and the 8% Problem: Benchmarking Local LLMs for Production AI Iran war: We spoke to the man making Lego-style AI videos that experts say are powerful propaganda Powell, Bessent discussed Anthropic's Mythos AI cyber threat with major U.S. banks GitHub - immartian/bellamem: Persistent belief-graph memory for AI agents. Retrieves decisive context by importance — not recency, not RAG, not /compact. recursive-mode: The Repo-Native Operating System for AI Engineering After the attack on Sam Altman's home, will AI CEO's go on the offensive? The biggest advance in AI since the LLM Opus 4.6 vs GPT 5.4 One Prompt Unity World Generation Test “AI polls” are fake polls Client Challenge Can AI be a 'child of God'? Inside Anthropic's meeting with Christian leaders
GitHub - gmarland/Agent-Context: Attach external codebase...
gamerdrome · 2026-04-27 · via Hacker News - Newest: "AI"

Give your AI coding tools access to your best reference code — without copying anything into your repo.


Why this exists

Modern AI tools like GitHub Copilot, Cursor, and ChatGPT are only as good as the context they can see.

But your most valuable code usually lives somewhere else:

  • previous services
  • internal starter projects
  • architecture patterns
  • experimental repos

Agent Context lets you attach those projects directly to your workspace — so both you and your AI tools can use them immediately.


What it does

  • Attach external folders as live references
  • Expose them inside your workspace via symlinks
  • Keep your repo clean (no copying, no vendoring)
  • Maintain a shared instructions file for humans and AI
  • Provide a sidebar to manage all attached context

Built for AI-assisted development

Agent Context turns your past work into usable AI context.

When you attach folders, it can generate a shared instructions block that:

  • Lists available reference projects
  • Describes what each one is useful for
  • Helps AI tools generate better, more consistent code

Example

You’re working on:

/projects/current-app

You attach:

/projects/reference-apps/nest-auth-example

Agent Context creates:

/projects/current-app/.examples/nest-auth-example

Now:

  • Browse it directly in VS Code
  • Reference it in prompts
  • Let AI tools use it as context

Example prompt:

"Implement authentication similar to the nest-auth-example in .examples"


Features

  • Activity Bar icon + sidebar view
  • Add folders from anywhere on disk
  • Remove folders safely (no impact on originals)
  • Store descriptions for each reference
  • Auto-managed .gitignore block
  • Generated instructions file for team + AI awareness
  • Fast, lightweight, zero-copy workflow

How it works

When you attach a folder, the extension:

  1. Creates a symlink inside a workspace folder (default: .examples/)
  2. Stores metadata in .symlinks.json
  3. Updates .gitignore with a managed block
  4. Optionally updates an instructions file

The generated instructions section is safely wrapped:

...


Sidebar workflow

Open Agent Context from the Activity Bar.

Available actions:

  • Add Context Folder
  • Refresh
  • Open Agent Context Directory
  • Remove Context Folder
  • Edit Description
  • Reveal Original Folder

Configuration

agentContext.targetFolder

  • Default: .examples

agentContext.updateAgentInstructions

  • Default: true

agentContext.instructionsFile

  • Default: AgentContext.AGENTS.md

Intended use

Agent Context is ideal when:

  • You reuse patterns across projects
  • You want AI tools to follow real examples
  • You want to avoid copying code into repos
  • You want teams aligned on reference implementations

Installation

  1. Open VS Code
  2. Go to Extensions
  3. Search for Agent Context
  4. Click Install

Or install via .vsix:

code --install-extension agent-context.vsix


Development

Requirements

  • Node.js
  • npm
  • VS Code 1.85+

Install dependencies

npm install

Build

npm run compile

Watch mode

npm run watch

Lint

npm run lint

Run extension

Open the project in VS Code and launch the Extension Host via debugger.


License

MIT