AI-powered developer workflows with cost optimization and pattern learning.
Run code review, debugging, testing, and release workflows from your terminal or Claude Code. Smart tier routing saves 34-86% on LLM costs.
pip install empathy-framework[developer]$0 Workflows via Skills - Multi-agent workflows run through Claude Code's Task tool instead of API calls. No additional cost with your Claude subscription.
Socratic Workflows - Interactive discovery through guided questions. Workflows ask what you need rather than requiring upfront configuration.
Security Hardened - Fixed critical vulnerabilities (path traversal, JWT, SSRF).
Hub-Based Commands - Organized workflows into intuitive command hubs.
pip install empathy-framework[developer]# Auto-detect API keys
python -m empathy_os.models.cli provider
# Or set explicitly
python -m empathy_os.models.cli provider --set anthropicIn Claude Code:
/dev # Developer tools (debug, commit, PR, review)
/testing # Run tests, coverage, benchmarks
/docs # Documentation generation
/release # Release preparationCLI:
empathy workflow run security-audit --path ./src
empathy workflow run test-coverage --target 90
empathy telemetry show # View cost savingsPython:
from empathy_os import EmpathyOS
async with EmpathyOS() as empathy:
result = await empathy.level_2_guided(
"Review this code for security issues"
)
print(result["response"])Workflows are organized into hubs for easy discovery:
| Hub | Command | Description |
|---|---|---|
| Developer | /dev |
Debug, commit, PR, code review, quality |
| Testing | /testing |
Run tests, coverage analysis, benchmarks |
| Documentation | /docs |
Generate and manage documentation |
| Release | /release |
Release prep, security scan, publishing |
| Workflow | /workflow |
Planning, TDD, refactoring workflows |
| Utilities | /utilities |
Project init, dependencies, profiling |
| Learning | /learning |
Pattern learning and session evaluation |
| Context | /context |
State management and memory |
| Agent | /agent |
Create and manage custom agents |
Example usage:
/dev # Show interactive menu
/dev "debug auth error" # Jump directly to debugging
/testing "run coverage" # Run coverage analysis
/release # Start release preparationWorkflows guide you through discovery instead of requiring upfront configuration:
You: /dev
Claude: What development task do you need?
1. Debug issue
2. Create commit
3. PR workflow
4. Quality check
You: 1
Claude: What error or unexpected behavior are you seeing?
How it works:
- Discovery - Workflow asks targeted questions to understand your needs
- Context gathering - Collects relevant code, errors, and constraints
- Dynamic agent creation - Assembles the right team based on your answers
- Execution - Runs with appropriate tier selection
Create custom agents with Socratic guidance:
/agent create # Guided agent creation
/agent team # Build multi-agent teams interactivelyWhen using Claude Code, workflows run as skills through the Task tool - no API costs:
/dev # $0 - uses your Claude subscription
/testing # $0
/release # $0
/agent create # $0For programmatic use, smart tier routing saves 34-86%:
| Tier | Model | Use Case | Cost |
|---|---|---|---|
| CHEAP | Haiku / GPT-4o-mini | Formatting, simple tasks | ~$0.005 |
| CAPABLE | Sonnet / GPT-4o | Bug fixes, code review | ~$0.08 |
| PREMIUM | Opus / o1 | Architecture, complex design | ~$0.45 |
# Track API usage and savings
empathy telemetry savings --days 30# 4 parallel agents check release readiness
empathy orchestrate release-prep
# Sequential coverage improvement
empathy orchestrate test-coverage --target 90Up to 57% cache hit rate on similar prompts. Zero config needed.
from empathy_os.workflows import SecurityAuditWorkflow
workflow = SecurityAuditWorkflow(enable_cache=True)
result = await workflow.execute(target_path="./src")
print(f"Cache hit rate: {result.cost_report.cache_hit_rate:.1f}%")Workflows learn from outcomes and improve over time:
from empathy_os.orchestration.config_store import ConfigurationStore
store = ConfigurationStore()
best = store.get_best_for_task("release_prep")
print(f"Success rate: {best.success_rate:.1%}")from empathy_llm_toolkit.providers import (
AnthropicProvider, # Claude
OpenAIProvider, # GPT-4
GeminiProvider, # Gemini
LocalProvider, # Ollama, LM Studio
)# Provider configuration
python -m empathy_os.models.cli provider
python -m empathy_os.models.cli provider --set hybrid
# Workflows
empathy workflow list
empathy workflow run <workflow-name>
# Cost tracking
empathy telemetry show
empathy telemetry savings --days 30
empathy telemetry export --format csv
# Orchestration
empathy orchestrate release-prep
empathy orchestrate test-coverage --target 90
# Meta-workflows
empathy meta-workflow list
empathy meta-workflow run release-prep --real# Individual developers (recommended)
pip install empathy-framework[developer]
# All LLM providers
pip install empathy-framework[llm]
# With caching (semantic similarity)
pip install empathy-framework[cache]
# Enterprise (auth, rate limiting)
pip install empathy-framework[enterprise]
# Healthcare (HIPAA compliance)
pip install empathy-framework[healthcare]
# Development
git clone https://github.com/Smart-AI-Memory/empathy-framework.git
cd empathy-framework && pip install -e .[dev]# At least one provider required
export ANTHROPIC_API_KEY="sk-ant-..."
export OPENAI_API_KEY="sk-..."
export GOOGLE_API_KEY="..."
# Optional: Redis for memory
export REDIS_URL="redis://localhost:6379"Install the Empathy VSCode extension for:
- Dashboard - Health score, costs, patterns
- One-Click Workflows - Run from command palette
- Memory Panel - Manage Redis and patterns
- Cost Tracking - Real-time savings display
- Path traversal protection on all file operations
- JWT authentication with rate limiting
- PII scrubbing in telemetry
- HIPAA/GDPR compliance options
See SECURITY.md for details.
See CONTRIBUTING.md for guidelines.
Fair Source License 0.9 - Free for students, educators, and teams ≤5 employees. Commercial license for larger organizations. Details →
Built by Smart AI Memory · Docs · Examples · Issues