zolva

# Zolva

> Open-source, self-hosted agent platform for banks and fintechs. Agents are
> declared in YAML + Markdown config; tools are the bank's own APIs registered
> as typed Python functions; guardrails (incl. per-customer contact caps),
> PII redaction before provider calls, evals, feedback loop, hash-chained
> audit with pluggable storage (SQLite or Postgres), human handover with a
> resume path, and synthetics attach to every step via a middleware bus.
> An EU AI Act compliance evidence pack maps the audit chain, config hashes,
> handover and eval gates to named articles; OpenTelemetry export drops every
> step into the bank's existing observability stack. Ships a read-only team
> dashboard and a reference HTTP entrypoint (`zolva serve`).
> pip-installable, runs entirely inside the bank's infrastructure.
> Apache-2.0. https://zolva.ai

Install: `pip install zolva` (dev: `pip install -e ".[dev]"`). Python >=3.11.
Entry points: `zolva.AgentApp.from_config("agents/")`, `@zolva.tool`, CLI `zolva validate <dir>`, `zolva compliance <audit.db>`, `zolva serve`, `zolva dashboard`.

## Docs

- [AGENTS.md](AGENTS.md): exact setup, verify, and convention instructions for AI coding agents
- [README.md](README.md): quickstart and public API
- [Playbooks](https://zolva.ai/playbooks/): thirteen production playbooks. Channels: WhatsApp, Twilio+Razorpay SMS, RCS fraud alerts, Telegram+Zendesk, ElevenLabs voice. Platform: CI gating, Slack handover desk, red-team synthetics, feedback-to-fix loop, regulator-ready audit+dashboard, self-hosted LLM gateway, cross-channel contact caps, PII redaction. Every provider call verified against and linked to official docs
- [Use cases](https://zolva.ai/use-cases/): seven industry use cases with the controls each one needs. Banking customer support, loan collections, fraud and disputes, KYC and onboarding, insurance claims, healthcare patient support, telecom operations
- [Blog](https://zolva.ai/blog/): RBI FREE-AI framework as an engineering spec, prompt injection and the 2026 OWASP agentic risks, MCP tool access inside a bank, AI voice disclosure in collections, EU AI Act obligations for financial services, DORA and LLM vendor concentration risk, guardrails as config rather than prompts, what a defensible audit trail contains, choosing an agent framework for regulated industries
- [docs/specs/2026-07-12-zolva-design.md](docs/specs/2026-07-12-zolva-design.md): full architecture, security model, competitive positioning
- [examples/mockbank/](examples/mockbank/): runnable end-to-end example (config + tools + orchestrator)
- [examples/dashboard_demo/](examples/dashboard_demo/): seeded demo for `zolva dashboard` (600 sessions, verifiable audit chain)

## Optional

- [docs/plans/2026-07-12-core-runtime.md](docs/plans/2026-07-12-core-runtime.md): core implementation plan with every interface signature