SkillsMay 14, 2026·1 min read

beava — Live Features for Agent Guardrails

beava turns live product events into guardrail-ready agent features; verified 130 stars, Rust core, and a 60-second quickstart for teams skipping Kafka.

Agent Toolkit
Agent Toolkit · Community
Agent ready

Ready-to-run agent install

This asset can be installed after the agent chooses its runtime, checks the plan, and runs the matching command.

Native · 98/100Policy: allow
Agent surface
Any MCP/CLI agent
Kind
Skill
Install
Single
Trust
Trust: Established
Entrypoint
Asset
Direct install command
npx -y tokrepo@latest install 0d930b9e-2125-5c06-a06a-071c06041ec4 --target codex

Run after dry-run confirms the install plan.

Intro

beava turns live product events into guardrail-ready agent features; verified 130 stars, Rust core, and a 60-second quickstart for teams skipping Kafka.

Best for: Agent teams needing live risk, support, or recommendation signals without streaming infrastructure

Works with: Python apps, Rust services, Docker, and event-driven product telemetry

Setup time: 5-10 minutes

Main

  • The README treats beava as a small live-decision layer rather than a full streaming platform, which is exactly why it is useful for agent guardrails.
  • Install paths converge on the same beava quickstart, so TokRepo readers get one stable entrypoint across pip, brew, and Docker.
  • Quantitative hooks are explicit: 130 stars, Rust implementation, and exposed ports 8080 and 8081 for local validation.

FAQ

  • Is it a Kafka replacement?: No. The value is a compact live feature layer for immediate reads and writes.
  • What should I test first?: Run beava quickstart and confirm the service comes up before modeling more signals.
  • Why TokRepo?: It is a practical runtime building block with clear commands and current maintenance.
🙏

Source & Thanks

Source: https://github.com/beava-dev/beava > License: Apache-2.0 > GitHub stars: 130 · forks: 8

Discussion

Sign in to join the discussion.
No comments yet. Be the first to share your thoughts.

Related Assets

CAMEL — Multi-Agent and Tooling Library

CAMEL is an open-source library for multi-agent systems and tools. Install `camel-ai`, then compose agents, tools, and optional web helpers in Python.

Skills
Agent Toolkit

AgentPrism — Visualize AI Agent Traces

AgentPrism is an open-source set of React components for visualizing AI agent traces, turning OpenTelemetry spans into debuggable diagrams and timelines.

Skills
Agent Toolkit

Owncast — Self-Hosted Live Streaming Server

An open source, self-hosted, decentralized live video streaming and chat server that gives you full control over your broadcasts.

Skills
AI Open Source

Air — Live Reload for Go Applications

Air provides live reload for Go development. It watches your source files, automatically rebuilds on changes, and restarts the binary — giving you a hot-reload experience similar to nodemon for Node.js or Flask debug mode for Python.

Skills
Script Depot
◈Home🔍Search👤Me