SpecMem
Unified Agent Experience & Pragmatic Memory for Every Coding Agent
The first-ever Agent Experience (AgentEx) platform: a unified, embeddable memory layer for AI coding agents.
The Problems We Solve
AI coding agents are powerful, but they face critical challenges that limit their effectiveness.
Markdown Madness & Verbosity
Developers drowning in CLAUDE.md, AGENTS.md, .cursorrules, requirements.md... What happens to all these specs after features are built?
Vendor Lock-In & Format Fragmentation
Every coding agent uses its own proprietary format. Switching agents means rewriting all your specs. Your project knowledge is trapped.
Agents Have Amnesia
Sessions reset, context is lost, previous decisions vanish. Agents write code without knowing your specs or earlier decisions.
Wasted Compute & Slow CI
Without understanding what changed, agents trigger full test runs for every tiny change, wasting compute and slowing pipelines.
No Agent Experience (AgentEx) Layer
We have DevEx for humans. But where is AgentEx for AI coding agents? No unified memory, no context optimization, no impact analysis.
How SpecMem Solves Them
Core Features
Everything you need to give your AI coding agents persistent, intelligent memory.
Multi-Framework Adapters
Parse specs from Kiro, SpecKit, Tessl, Claude Code, Cursor, Codex, Factory, Warp, Gemini CLI
Intelligent Memory
Vector-based semantic search with LanceDB, ChromaDB, Qdrant, or AgentVectorDB
SpecImpact Graph
Bidirectional relationships between specs, code, and tests
SpecDiff Timeline
Track spec evolution, detect drift, find contradictions
SpecValidator
Quality assurance with 6 validation rules for structure, timeline, duplicates, and more
Spec Coverage
Analyze gaps between acceptance criteria and tests with suggestions
Test Mapping Engine
Map tests to specs across pytest, jest, vitest, and more
Health Score
Project health grades (A-F) with improvement suggestions
Web UI
Interactive dashboard with live sync, filtering, and WebSocket updates
See SpecMem in Action
Watch how SpecMem transforms your AI coding workflow with persistent memory and intelligent context.
Quick Start
Get started with SpecMem in minutes.
Try the Demo (30 seconds)
See SpecMem in action with its own specifications - browse, search, and see relationships between specs and code.
# Install with VectorDB support (uses LanceDB by default)
pip install specmem[local]
# Run the demo
specmem demo💡 What you'll see: A dashboard showing SpecMem's own specs with all indexed specifications, relationships between specs and code, project health score, and spec coverage metrics.
Set Up Your Project (2 minutes)
Step 1: Install
# Install SpecMem with VectorDB support
pip install specmem[local]
# Or install from source
git clone https://github.com/SuperagenticAI/specmem.git
cd specmem
pip install -e .Step 2: Initialize
cd your-project
specmem initThis creates a .specmem.toml config file.
Step 3: Scan Your Specs
specmem scanSpecMem automatically detects and indexes specs from: .kiro/specs/ (Kiro), CLAUDE.md (Claude Code), .cursorrules (Cursor), and more.
What You'll See
📊 Spec Overview
All your specifications in one place, searchable and organized.
💚 Health Score
A grade (A-F) showing your project's spec health with actionable insights.
📈 Coverage Report
See which acceptance criteria have tests and which don't.
🔗 Impact Analysis
Before changing code, see which specs are affected.
Python API
from specmem import SpecMemClient
# Initialize SpecMem
sm = SpecMemClient()
# Index specifications
sm.index_specs()
# Search for specs
results = sm.search("authentication")
# Get spec coverage
coverage = sm.get_coverage()
# Analyze impact
impact = sm.analyze_impact("src/auth.py")Want to Learn More?
Explore the complete getting started guide with detailed examples, Kiro integration, value guide, and advanced features.
View Getting Started DocsKiro Integration
First-class support for Kiro IDE with native adapters and MCP server.
Kiro Powers
Install SpecMem as a Kiro Power for seamless IDE integration. Query specs, analyze impact, and get context-aware suggestions.
MCP Server
Full Model Context Protocol support. Kiro's agent can query your specs, analyze impact, and get optimized context automatically.
Native Kiro Adapter
First-class support for .kiro/specs/ structure: requirements.md, design.md, tasks.md parsed into searchable memory.
Visualize Your Specs
Build the SpecMem dashboard to visualize your specifications, validate them against tests, and detect drift.
Integrate with CI/CD
Add SpecMem to your GitHub pipelines to validate specs and get coverage data.
Enhance Pull Requests
Add SpecMem to your PR workflow to get insights on specification impact and coverage gaps.
Index Specs as Memory
Use your favorite vector database to index your specs as searchable memory for coding agents.
Run Selective Tests
Use SpecMem to identify only the tests that need to run, saving CI time and compute costs.
How Can Kiro Users Use SpecMem Right Now?
SpecMem is published on PyPI and available on GitHub. Kiro users can start using it today.
Visualize Your Specs
Build the SpecMem dashboard to visualize your specifications, validate them against tests, and detect drift. Host it as GitHub Pages for team collaboration. Show this dashboard to your Product Owner or Business Analyst and watch their face light up.
Integrate with CI/CD
Add SpecMem to your GitHub pipelines to validate specs and get coverage data, just like you do for test coverage. Catch spec issues before they reach production.
Enhance Pull Requests
Add SpecMem to your PR workflow to get insights on specification impact, coverage gaps, and potential drift with every code change.
Index Specs as Memory
Use your favorite vector database (LanceDB, ChromaDB, Qdrant) and embedding models to index your specs as searchable memory for coding agents.
Run Selective Tests
Use SpecMem against your code changes to identify only the tests that need to run, saving CI time and compute costs.
Supported Frameworks & Agents
SpecMem works with all major spec frameworks and AI coding agents.
Spec Frameworks
| Framework | Adapter | Patterns |
|---|---|---|
| Kiro | kiro | .kiro/specs/**/*.md |
| SpecKit | speckit | .speckit/**/*.yaml |
| Tessl | tessl | .tessl/**/*.md |
Commercial Agents
| Agent | Adapter | Patterns |
|---|---|---|
| Claude Code | claude | Claude.md, CLAUDE.md |
| Cursor | cursor | cursor.json, .cursorrules |
| Codex | codex | .codex/**/*.md |
| Factory | factory | .factory/**/*.yaml |
| Warp | warp | .warp/**/*.md |
| Gemini CLI | gemini | GEMINI.md, .gemini/**/*.md |
Vector Databases
Choose the vector database that fits your needs.
LanceDB
Local development
pip install specmem[local]ChromaDB
Embedded persistence
pip install specmem[chroma]Qdrant
Production scale
pip install specmem[qdrant]AgentVectorDB
Lightweight
Built-inEmbedding Providers
Use cloud embeddings for enhanced semantic search.
OpenAI
Model: text-embedding-3-small
pip install specmem[openai]Model: embedding-001
pip install specmem[google]Together AI
Model: togethercomputer/m2-bert
pip install specmem[together]Advanced Features
Power features for enterprise and advanced use cases.
Cloud Embeddings
Support for OpenAI, Google, Together AI embedding providers
Coding Guidelines
Aggregate guidelines from Kiro steering, CLAUDE.md, .cursorrules
Spec Lifecycle
Prune stale specs, generate specs from code, compress verbose specs
Kiro Session Search
Index and search Kiro chat sessions for context
Static Dashboard
Export specs to static HTML dashboard for GitHub Pages
GitHub Action
CI integration with coverage thresholds and PR comments
MCP Server
Model Context Protocol server for AI agent integration
Streaming Context API
Token-aware context optimization with streaming support
Ready to Give Your Agents Memory?
Start using SpecMem today and transform how your AI coding agents understand and work with your codebase.