Getting Started

ctx¶
ctx (Context) is a file-based system that enables AI coding assistants to
persist project knowledge across sessions. Instead of re-explaining your
codebase every time, context files let AI tools remember decisions,
conventions, and learnings:
- A session is interactive.
ctxenables cognitive continuity.- Cognitive continuity enables durable, symbiotic-like human–AI workflows.
Community¶
Open source is better together.
Help ctx Change How AI Remembers
If the idea behind ctx resonates, a star helps it reach engineers
who run into context drift every day.
→ https://github.com/ActiveMemory/ctx
ctx is free and open source software, and contributions are always
welcome and appreciated.
Join the community to ask questions, share feedback, and connect with other users:
Why?¶
Most AI-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
ctx solves this by treating context as infrastructure:
files that version with your code and persist across sessions.
Installation¶
Binary Downloads (Recommended)¶
Download pre-built binaries from the releases page.
Download ctx-0.2.0-windows-amd64.exe from the releases page and add it to your PATH.
Verifying Checksums¶
Each binary has a corresponding .sha256 checksum file. To verify your download:
# Download the checksum file
curl -LO https://github.com/ActiveMemory/ctx/releases/download/v0.2.0/ctx-0.2.0-linux-amd64.sha256
# Verify the binary
sha256sum -c ctx-0.2.0-linux-amd64.sha256
On macOS, use shasum -a 256 -c instead of sha256sum -c.
Build from Source¶
Building from the source gives you the latest features and bug fixes; however,
it also means you will be using an unreleased version of ctx that has not
been fully tested.
Want to help test the latest features?
If you like living on the edge and want to test the latest features before they are released, then building from source is the way to go.
Requires Go 1.25+:
git clone https://github.com/ActiveMemory/ctx.git
cd ctx
make build
sudo make install
# or:
# sudo mv ctx /usr/local/bin/
Verify installation:
Quick Start¶
1. Initialize Context¶
This creates a .context/ directory with template files and configures
AI tool hooks (for Claude Code).
2. Check Status¶
Shows context summary: files present, token estimate, and recent activity.
3. Start Using with AI¶
With Claude Code, context loads automatically via hooks. For other tools, paste the output of:
4. Verify It Works¶
Ask your AI: "Do you remember?"
It should cite specific context: current tasks, recent decisions, or previous session topics.
What Gets Created¶
.context/
├── CONSTITUTION.md # Hard rules — NEVER violate these
├── TASKS.md # Current and planned work
├── CONVENTIONS.md # Project patterns and standards
├── ARCHITECTURE.md # System overview
├── DECISIONS.md # Architectural decisions with rationale
├── LEARNINGS.md # Lessons learned, gotchas, tips
├── GLOSSARY.md # Domain terms and abbreviations
├── DRIFT.md # Staleness signals
├── AGENT_PLAYBOOK.md # How AI tools should use this
└── sessions/ # Session snapshots
.claude/ # Claude Code integration (if detected)
├── hooks/ # Auto-save and enforcement scripts
├── commands/ # ctx slash command definitions
└── settings.local.json # Hook configuration
See Context Files for detailed documentation of each file.
Common Workflows¶
Add a Task¶
Record a Decision¶
ctx add decision "Use PostgreSQL for primary database" \
--context "Need a reliable database for production" \
--rationale "PostgreSQL offers ACID compliance and JSON support" \
--consequences "Team needs PostgreSQL training"
Note a Learning¶
ctx add learning "Mock functions must be hoisted in Jest" \
--context "Tests failed with undefined mock errors" \
--lesson "Jest hoists mock calls to top of file" \
--application "Place jest.mock() before imports"
Mark Task Complete¶
Check for Stale Context¶
Next Steps¶
- Prompting Guide — Effective prompts for AI sessions
- CLI Reference — All commands and options
- Context Files — File formats and structure
- Autonomous Loops — Iterative AI development workflows
- Integrations — Setup for Claude Code, Cursor, Aider