sarkar-ai-taken/riva
Local-first observability and control plane for AI agents.
Provides real-time resource tracking (CPU, memory, token usage), multi-framework agent discovery (15+ frameworks from Claude Code to CrewAI), and forensic session analysis with compliance audit logging via HMAC-chained JSONL. Exports metrics and traces to OpenTelemetry backends (Datadog, Grafana, Jaeger) while maintaining local-first architecture with no cloud dependencies. Includes boundary policy monitoring for file access and network connections, accessible via CLI, TUI, web dashboard, or native macOS system tray.
3 stars and 1,099 monthly downloads. Available on PyPI.
Stars
3
Forks
1
Language
Python
License
MIT
Category
Last pushed
Mar 08, 2026
Monthly downloads
1,099
Commits (30d)
0
Dependencies
7
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/agents/sarkar-ai-taken/riva"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related agents
petterjuan/agentic-reliability-framework
ARF is an agentic reliability intelligence platform that separates decision intelligence (OSS)...
Nubaeon/empirica
Make AI agents and AI workflows measurably reliable. Epistemic measurement, Noetic RAG,...
relai-ai/relai-sdk
A platform for building reliable AI agents
soumendrak/ragwatch
An SDK for Python AI Agents. Under heavy development.
imtt-dev/steer
The Active Reliability Layer for AI Agents. Catch failures, teach fixes, and automate reliability