mem8
Context management toolkit for AI-assisted development. Manage memory, templates, and workflows with Claude Code and other AI tools.
Quick Start
# Install
uv tool install mem8
# Initialize workspace
cd your-project
mem8 init
# Check status
mem8 status
Core Features
🧠 Context Window Management
Persistent memory system for Claude Code with structured documentation. Keep AI context focused and relevant across long development sessions.
# Search your memory
mem8 search "authentication"
# Use Claude Code commands
/mem8:research "payment system"
/mem8:plan "add OAuth support"
/mem8:implement memory/shared/plans/oauth.md
/mem8:commit
🔧 Toolbelt Integration
Verify and manage CLI tools required for AI workflows.
# Check for missing tools
mem8 doctor
# Auto-install missing tools
mem8 doctor --fix
# List all tools and versions
mem8 tools
Verified tools include: ripgrep, fd, jq, gh, git, bat, delta, ast-grep, and more.
🚢 Port Management
Global port leasing system prevents conflicts across projects.
# Lease port range for project
mem8 ports --lease
# View assigned ports
mem8 ports
# Kill process on port (safe mode)
mem8 ports --kill 20000
🎨 External Templates
Share standardized configurations across teams using GitHub templates.
# Use official templates
mem8 init --template-source killerapp/mem8-plugin
# Use team templates
mem8 init --template-source your-org/templates
# Set default for all projects
mem8 templates set-default your-org/templates
🤖 Claude Code Integration
Custom commands and agents for enhanced AI workflows.
Commands installed by default:
/mem8:research- Parallel codebase exploration/mem8:plan- Structured implementation planning/mem8:implement- Execute plans with progress tracking/mem8:validate- Verify implementation completeness/mem8:commit- Create semantic commits/mem8:describe-pr- Generate PR descriptions
Documentation
📚 Full documentation at codebasecontext.org
Development Workflow
mem8 provides a structured development cycle:
- Research (
/mem8:research) - Understand existing patterns - Plan (
/mem8:plan) - Design with concrete steps - Implement (
/mem8:implement) - Execute with progress tracking - Validate (
/mem8:validate) - Verify completeness - Commit (
/mem8:commit) - Create semantic commits
Project Structure
After running mem8 init --template full:
your-project/
├── .claude/
│ ├── commands/ # Custom slash commands
│ └── agents/ # Custom agent definitions
├── memory/
│ └── shared/
│ ├── research/ # Research documents
│ ├── plans/ # Implementation plans
│ ├── prs/ # PR descriptions
│ └── decisions/ # Technical decisions
└── .mem8/
├── config.yaml # Configuration
├── ports.md # Port assignments
└── tools.md # Tool inventory
Requirements
- Python 3.11+
- uv (recommended) or pip
Optional:
- Docker (for backend API features)
- Node.js 18+ (for web interface)
Support
License
MIT License - see LICENSE file for details.
Metadata
Release files for mem8 6.0.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | |
|---|---|---|---|---|
| mem8-6.0.0.tar.gz | 1.5 MB | Without provenance | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| mem8-6.0.0-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 1.6 MB
Release files / mem8-6.0.0.tar.gz
| Download URL | mem8-6.0.0.tar.gz |
|---|---|
| Size | 1.5 MB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
daf23cb110b16aea5434b18b3ed1da76e422a1a3db657733e01cd504aa5380b8
|
|
BLAKE2b-256 checksum How to use checksums |
c31aecf06d4b6fb4b637c67ea3a82ea121ab394673c22829fbf73189fa25718c
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
uv/0.9.3
|
Release files / mem8-6.0.0-py3-none-any.whl
| Download URL | mem8-6.0.0-py3-none-any.whl |
|---|---|
| Size | 108.8 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
155be401edc52dbda6058ac3ab9385aae949b19ee3dc14a04146b2efb9929084
|
|
BLAKE2b-256 checksum How to use checksums |
22b0f3b04f9e8147a697d4a5a8982c6301914ec34c6db2f5327532f2072eef32
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
uv/0.9.3
|
Security for mem8 6.0.0
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.