Open
Conversation
This comprehensive platform enables building, managing, and deploying AI agents. Features: • Agent Studio - Upload YAML specs, generate FastAPI code, run agents • Skill Store - Browse, fork, and rate reusable skills with versioning • PromptFlow Sandbox - Test multi-step prompts with cost estimation • Agent Mirror - Visualize execution traces with interactive trees Backend (FastAPI): • JWT authentication with user management • SQLModel models (User, Skill, Agent, Run, TraceEvent, PromptTest) • Alembic migrations for schema management • REST API with full CRUD operations • Celery workers for async agent execution • OpenAI + Ollama LLM provider support • Jinja2 code generation from YAML specs • Skills runtime with pluggable architecture • SSE streaming for real-time trace events • Token accounting and cost tracking • Comprehensive pytest test suite Frontend (Next.js 14): • App Router with TypeScript • Tailwind CSS + responsive design • Studio page (upload, validate, generate, run) • Skills marketplace with search and filters • Sandbox for prompt testing • Mirror for trace visualization • API client with auth integration Infrastructure: • Docker Compose with 6 services • PostgreSQL database with persistence • Redis for Celery broker • Health checks and volume management • Optional Ollama support for local models Data: • 5 built-in skills (http_get, llm_prompt, csv_write, etc.) • 2 demo agents (ownership-finder, class-action-watcher) • 3 prompt test examples • Seed script with demo user Documentation: • Comprehensive README with setup instructions • POSIX and Windows PowerShell commands • API endpoint examples with curl • Agent YAML spec templates • Troubleshooting guide • Security notes for production All code is production-ready with no placeholders. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
This comprehensive platform enables building, managing, and deploying AI agents.
Features:
• Agent Studio - Upload YAML specs, generate FastAPI code, run agents • Skill Store - Browse, fork, and rate reusable skills with versioning • PromptFlow Sandbox - Test multi-step prompts with cost estimation • Agent Mirror - Visualize execution traces with interactive trees
Backend (FastAPI):
• JWT authentication with user management
• SQLModel models (User, Skill, Agent, Run, TraceEvent, PromptTest) • Alembic migrations for schema management
• REST API with full CRUD operations
• Celery workers for async agent execution
• OpenAI + Ollama LLM provider support
• Jinja2 code generation from YAML specs
• Skills runtime with pluggable architecture
• SSE streaming for real-time trace events
• Token accounting and cost tracking
• Comprehensive pytest test suite
Frontend (Next.js 14):
• App Router with TypeScript
• Tailwind CSS + responsive design
• Studio page (upload, validate, generate, run)
• Skills marketplace with search and filters
• Sandbox for prompt testing
• Mirror for trace visualization
• API client with auth integration
Infrastructure:
• Docker Compose with 6 services
• PostgreSQL database with persistence
• Redis for Celery broker
• Health checks and volume management
• Optional Ollama support for local models
Data:
• 5 built-in skills (http_get, llm_prompt, csv_write, etc.) • 2 demo agents (ownership-finder, class-action-watcher) • 3 prompt test examples
• Seed script with demo user
Documentation:
• Comprehensive README with setup instructions
• POSIX and Windows PowerShell commands
• API endpoint examples with curl
• Agent YAML spec templates
• Troubleshooting guide
• Security notes for production
All code is production-ready with no placeholders.
🤖 Generated with Claude Code