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

博客园 - Franky
有赞技术团队
有赞技术团队
宝玉的分享
宝玉的分享
雷峰网
雷峰网
Hugging Face - Blog
Hugging Face - Blog
V
V2EX
大猫的无限游戏
大猫的无限游戏
博客园 - 司徒正美
D
Docker
T
The Blog of Author Tim Ferriss
罗磊的独立博客
博客园 - 叶小钗
酷 壳 – CoolShell
酷 壳 – CoolShell
Blog — PlanetScale
Blog — PlanetScale
月光博客
月光博客
J
Java Code Geeks
Jina AI
Jina AI
博客园 - 【当耐特】
C
Check Point Blog
OSCHINA 社区最新新闻
OSCHINA 社区最新新闻
腾讯CDC
Last Week in AI
Last Week in AI
freeCodeCamp Programming Tutorials: Python, JavaScript, Git & More
V
Visual Studio Blog

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 - ActiveMemory/ctx: ctx: do you remember? — a sing...
parlakisik · 2026-05-05 · via Hacker News - Newest: "AI"

ctx

ctx (Context)

ctx is a system, not a prompt.

A lightweight, file-based system that enables AI coding assistants to persist, structure, and rehydrate project context across sessions.

ctx works with any AI tool that can read files; no model or vendor lock-in.

Full documentation: ctx.ist

The ctx Manifesto

Creation, not code. Context, not prompts. Verification, not vibes.

ctx is infrastructure for preserving intent under scale. Without durable context, intelligence resets. With ctx, creation compounds.

Read the full Manifesto | ctx.ist/manifesto

The Thesis

Context as State: A Persistence Layer for Human-AI Cognition

AI-assisted development systems assemble context at prompt time using heuristic retrieval from mutable sources. These approaches optimize relevance at the moment of generation but provide no mechanism for persistence, verification, or accumulated learning across sessions. ctx treats context as deterministic state.

Read the full Thesis

Core Documents

Document Context
Manifesto Philosophy: creation, context, verification
The Thesis Whitepaper: context as deterministic state
Design Invariants System properties that must always hold
Tool Comparison How ctx differs from .cursorrules, Aider, Copilot
ctx Blog Deep dives, architecture notes, learnings

The Problem

Most LLM-driven development fails not because models are weak: They fail because context is ephemeral. Every new session starts near zero:

  • You re-explain architecture
  • The AI repeats past mistakes
  • Decisions get rediscovered instead of remembered

The Solution

ctx treats context as infrastructure:

  • Persist: Tasks, decisions, learnings survive session boundaries
  • Reuse: Decisions don't get rediscovered; lessons stay learned
  • Align: Context structure mirrors how engineers actually think
  • Integrate: Works with any AI tool that can read files

Here's what that looks like in practice:

❯ "Do you remember?"

● Yes. The PreToolUse hook runs ctx agent, and CLAUDE.md tells me to
  read the context files. I have context.

❯ "What have we been working on recently?"

● Yes. I can run ctx journal source and review recent activity:
    - 2025-01-20: The meta-experiment that started it all
    - 2025-01-21: The ctx rename + Claude hooks session

That's the whole point: Temporal continuity across sessions.

Installation

Download pre-built binaries from the releases page, or build from source:

git clone https://github.com/ActiveMemory/ctx.git
cd ctx
CGO_ENABLED=0 go build -o ctx ./cmd/ctx
sudo mv ctx /usr/local/bin/

See installation docs for platform-specific instructions.

Quick Start

# Initialize context directory in your project
ctx init

# Activate it for the current shell (binds CTX_DIR). Required
# before every other command: ctx no longer walks up the
# filesystem looking for .context/.
eval "$(ctx activate)"

# Check context status
ctx status

# Get an AI-ready context packet
ctx agent --budget 4000

# Add tasks, decisions, learnings
ctx task add "Implement user authentication"
ctx decision add "Use PostgreSQL for primary database" \
  --context "Need a reliable database for production workloads" \
  --rationale "PostgreSQL offers ACID compliance, JSON support, and team familiarity" \
  --consequence "Team needs PostgreSQL training; must set up replication"
ctx learning add "Mock functions must be hoisted in Jest"

ctx activate emits export CTX_DIR=... for your shell; one-shot callers can prefix the binding inline as CTX_DIR=<abs-path> ctx .... The value must be an absolute path with .context as its basename; relative paths and other names are rejected on first use. A small allowlist (init, activate, deactivate, version, help, system bootstrap, doctor, guide, why, config switch/status, hub *) runs without CTX_DIR declared; every other command exits with a next-step hint when it is unset.

Documentation

This README is a map, not the territory. The full documentation lives at ctx.ist and carries the recipes, runbooks, threat model, and design rationale that this file intentionally doesn't try to fit. If you're past install and wondering "how do I actually use this in a real session," the recipes are the right next stop.

Guide Description
Getting Started Installation, quick start, first steps
Recipes Practical workflow guides
CLI Reference All commands and options
Context Files File formats and structure
Integrations Claude Code, Cursor, Aider setup
Operations Runbooks, day-to-day, hub deployment
Security Trust model, audit trail, permissions

Contributing

Contributions welcome. See CONTRIBUTING.md for guidelines.

All commits must be signed off (git commit -s) to certify the DCO.

Community

Open source is better together.

Join the community to ask questions, share feedback, and connect with other users:

Join the ctx Discord

License

Apache 2.0