π― The only AI memory system that solves the context-switching problem
Never lose context when jumping between projects. AgentCortex creates isolated, persistent memory banks for each codebase, so your AI assistant remembers everythingβexactly where it belongs.
The Problem: AI assistants forget everything between conversations. Worse, when you work on multiple projects, context bleeds between codebasesβyour React patterns from Project A contaminate your Vue.js work on Project B.
The Solution: Project-isolated persistent memory. Each project gets its own intelligent memory bank that grows smarter over time, never interfering with your other work.
- Isolated memory banks per project/codebase
- Zero context bleeding between different repos
- Automatic project detection and context switching
- Clean slate for each new project, full memory for existing ones
- Never lose context again across all conversations
- Cumulative learning that builds on every interaction
- Semantic search finds relevant memories instantly
- Intelligent importance ranking and auto-cleanup
- Break down complex PRDs into actionable tasks
- Smart task suggestions based on project context
- Progress tracking with dependency management
- Context-aware subtask generation
- Sub-200ms response times with optimized queries
- Vector search with 1536-dimensional embeddings
- 99.9% uptime SLA with enterprise security
- Scales infinitely with your growing codebase
# Sign up at agentcortex.dev and grab your API key
curl -X POST https://api.agentcortex.dev/auth/signup \
-H "Content-Type: application/json" \
-d '{"email":"you@company.com"}'
# Install globally
npm install -g agentcortex
# Or run directly
npx agentcortex
Add to your claude_desktop_config.json
file:
{
"mcpServers": {
"agentcortex": {
"command": "npx",
"args": ["agentcortex"],
"env": {
"AGENTCORTEX_API_KEY": "your_api_key_here"
}
}
}
}
Add to Cursor Settings β MCP or your cursor_settings.json
:
{
"mcp.servers": {
"agentcortex": {
"command": "npx",
"args": ["agentcortex"],
"env": {
"AGENTCORTEX_API_KEY": "your_api_key_here"
}
}
}
}
Add to your Windsurf configuration file:
{
"mcp": {
"servers": {
"agentcortex": {
"command": "npx",
"args": ["agentcortex"],
"env": {
"AGENTCORTEX_API_KEY": "your_api_key_here"
}
}
}
}
}
Add to your VS Code User Settings (JSON) or .vscode/mcp.json
:
{
"mcp": {
"servers": {
"agentcortex": {
"command": "npx",
"args": ["agentcortex"],
"env": {
"AGENTCORTEX_API_KEY": "your_api_key_here"
}
}
}
}
}
# Working on your React e-commerce app
Human: We're using React 18 with TypeScript and Zustand for state management
AI: β
Stored in TaskMem β Project: "ecommerce-frontend"
# Switch to your Python API project
Human: Switch to my Python API project
AI: π Switched to "payment-api" project context
# Now working in Python context - React knowledge doesn't interfere
Human: What framework should I use for the API?
AI: π Based on your "payment-api" project: FastAPI with Pydantic for validation
(No mention of React/TypeScript - clean context separation!)
# Back to React project later
Human: Switch back to ecommerce frontend
AI: π Switched to "ecommerce-frontend"
π Remembers: React 18, TypeScript, Zustand state management
Human: What did we decide about error handling?
AI: π Found 3 relevant memories:
1. [94% match] "Use React Error Boundaries for component failures"
2. [89% match] "Log errors to Sentry in production"
3. [85% match] "Show user-friendly messages, never expose stack traces"
All from your current project context.
Human: Break down the user authentication system implementation
AI: π Task broken down into 6 subtasks:
β
Research authentication patterns for React 18
π Set up Supabase Auth integration
β³ Implement login/signup forms
β³ Add protected route middleware
β³ Create user profile management
β³ Add session persistence logic
Estimated: 2-3 days based on your project complexity
Tool | What It Does | When To Use |
---|---|---|
Project Management | ||
create_project |
Create new isolated project context | Starting work on a new codebase |
set_current_project |
Switch between project contexts | Moving between different repos |
get_current_project |
Show active project info | Confirm which project you're in |
list_projects |
List all your project contexts | See all your codebases |
get_project_context |
Full project overview & summary | Get up to speed on a project |
Memory Operations | ||
store_memory |
Save important project information | Record decisions, patterns, configs |
search_memory |
Find memories with semantic search | "What did we decide about...?" |
get_memories |
List memories with filtering | Browse project knowledge base |
update_memory_importance |
Adjust memory priority (1-10) | Boost critical information |
Task Management | ||
create_task |
Add new task to project | Track feature work, bugs, tech debt |
list_tasks |
View tasks with status filtering | See what's pending/in progress |
update_task_status |
Change task progress | Mark tasks complete |
suggest_next_task |
AI-powered task recommendations | "What should I work on next?" |
break_down_task |
Split complex work into subtasks | Turn PRDs into actionable steps |
# Share project context with team members
Human: Export this project's memory for onboarding
AI: π¦ Generated onboarding package for "ecommerce-frontend"
β Includes: Architecture decisions, coding standards, setup guides
β Share with: new team members for instant context
# Import team knowledge
Human: Import the backend team's API documentation memories
AI: β
Imported 47 memories from "payment-api" project
β Now available when working on frontend integrations
# Learn from patterns across projects
Human: What authentication patterns have I used before?
AI: π Across your projects:
- ecommerce-frontend: Supabase Auth + React Context
- admin-dashboard: Auth0 + JWT tokens
- mobile-app: Firebase Auth + AsyncStorage
Recommendation: Supabase for consistency with your React patterns
Variable | Description | Required | Default |
---|---|---|---|
AGENTCORTEX_API_KEY |
Your API key from agentcortex.dev | β | - |
AGENTCORTEX_API_URL |
API endpoint override | β | https://api.agentcortex.dev |
AGENTCORTEX_PROJECT_AUTO_DETECT |
Auto-detect project from git repo | β | true |
AGENTCORTEX_DEFAULT_IMPORTANCE |
Default memory importance level | β | 5 |
Claude Desktop:
{
"mcpServers": {
"agentcortex": {
"command": "npx",
"args": ["agentcortex"],
"env": {
"AGENTCORTEX_API_KEY": "your_api_key",
"AGENTCORTEX_PROJECT_AUTO_DETECT": "true",
"AGENTCORTEX_DEFAULT_IMPORTANCE": "7"
}
}
}
}
Cursor/Windsurf/Claude Code:
{
"mcp": {
"servers": {
"agentcortex": {
"command": "npx",
"args": ["agentcortex"],
"env": {
"AGENTCORTEX_API_KEY": "your_api_key",
"AGENTCORTEX_PROJECT_AUTO_DETECT": "true",
"AGENTCORTEX_DEFAULT_IMPORTANCE": "7"
}
}
}
}
}
Plan | Price | Projects | Memories/Month | Task Management | Support |
---|---|---|---|---|---|
Developer | Free | 1 project | 1,000 memories | Basic | Community |
Pro | $29/mo | Unlimited | Unlimited | Advanced | Priority |
Team | $99/mo | Unlimited | Unlimited | Collaboration | Dedicated |
All plans include:
- β Project context separation
- β Semantic search
- β 99.9% uptime SLA
- β Enterprise security
- β MCP protocol support
# Clone and setup
git clone https://github.com/sage-hq/agentcortex
7B3F
.git
cd agentcortex/apps/mcp
npm install
# Development with hot reload
npm run dev
# Build for production
npm run build
# Run tests
npm test
# Publish to npm
npm run publish
- Fork the repository
- Create a feature branch:
git checkout -b feature/amazing-feature
- Add tests for new functionality
- Ensure TypeScript types are correct
- Test with multiple MCP clients
- Submit a Pull Request
- π Documentation: docs.agentcortex.dev
- π¬ Discussions: GitHub Discussions
- π Bug Reports: GitHub Issues
- π Feature Requests: Feature Board
- π§ Email Support: support@agentcortex.dev
"Finally, an AI that doesn't forget my React patterns when I switch to my Python API project. Game changer."
β Sarah Chen, Senior Engineer @ Stripe
"AgentCortex solved our biggest pain point: onboarding new developers. Now they get instant context on our 20+ microservices."
β Marcus Rodriguez, Tech Lead @ DataDog
"The project isolation is incredible. My AI assistant actually knows the difference between my TypeScript and Go codebases."
β Alex Kim, Principal Engineer @ Vercel
- π Auto-sync with Git: Automatic project detection from repositories
- π€ Code Analysis: AI-powered codebase understanding and suggestions
- π Advanced Search: Full-text search across code, docs, and conversations
- π― Smart Suggestions: Proactive memory and task recommendations
- π VS Code Extension: Direct integration with popular editors
- π₯ Team Collaboration: Shared project contexts and knowledge bases
MIT License - see LICENSE file for details.
π Ready to give your AI perfect memory?
npx agentcortex
Never lose context again. Start free today.