2 Commits

Author SHA1 Message Date
root
189e8fb99b Add authentication + security hardening
- Session-based login with bcrypt password hashing
- First-time setup flow creates admin account
- @login_required on all page/API routes
- @admin_required on admin panel and lab routes
- Rate limiting: 60 req/min global, 5 login attempts/min
- Security headers: X-Frame-Options, XSS Protection, nosniff
- Login page with dark theme matching main UI
- Logout button in header
- users table in PostgreSQL

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-25 03:14:51 -05:00
root
1711d33337 LLM Team UI v1.0 — full-stack local AI orchestration platform
Features:
- 20 team modes (brainstorm, debate, consensus, red team, etc.)
- 3 autonomous pipelines (research, model eval, knowledge extraction)
- AutoResearch Lab with ratchet engine (Karpathy-inspired)
- Multi-provider support (Ollama, OpenRouter, OpenAI, Anthropic)
- Admin panel (providers, models, timeouts, OpenRouter browser)
- History panel with copy/iterate/re-pipe workflow
- Context budget system (smart truncation, safe_query, overflow recovery)
- PostgreSQL persistence (team_runs, pipeline_runs, lab_experiments, lab_trials)
- Pure Python + embedded HTML/CSS/JS, no external JS dependencies
- Inline SVG score charts in Lab monitor
- SSE streaming for real-time output
- Systemd service with auto-restart

Stack: Flask + Ollama + PostgreSQL + Bun-compatible
Hardware: RTX A4000 (16GB) + 128GB RAM

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-25 02:51:36 -05:00