Plano

Active
GitHub Rust Apache-2.0

Description

An AI-native proxy and data plane for agentic apps with built-in orchestration, safety, observability, and smart LLM routing so developers can focus on agent core logic.

Key Features

  • AI-native proxy and data plane with built-in orchestration and safety
  • YAML-based agent descriptions for intelligent routing without hand-written logic
  • Agentic Signals for zero-code full-chain observability capture
  • Filter Chains for jailbreak protection and content moderation
  • Smart LLM routing with model aliases and automatic preference selection
  • Built on Envoy, supports any language or AI framework

Use Cases

💡 Unified orchestration and intelligent routing for multi-agent applications
💡 Production-grade safety and content moderation for LLM applications
💡 Unified API gateway and load balancing across model providers
💡 Full-chain observability monitoring for AI agent applications

Strengths & Limitations

Strengths

  • Actively maintained, recent updates
  • High community interest (7.0k stars)
  • Permissive open-source license (Apache-2.0)
  • Established track record (2 years in production)

Quick Start

1. Install Plano following the prerequisites guide
2. Write `config.yaml` defining agent URLs and descriptions
3. Start Plano: `planoai up config.yaml`
4. Send requests via `localhost:8001`
5. View full-chain observability in the tracing dashboard

Related Projects

TensorZero

11.7k · Rust
Normal B

TensorZero is an open-source LLMOps platform that unifies an LLM gateway, observability, evaluation, optimization, and A/B testing, designed for production agents.

observabilityllmllm-gateway +2
  • · Unified LLM gateway - one API for Anthropic, OpenAI, Bedrock, Gemini, vLLM, and 20+ providers
  • · Sub-1ms p99 overhead at 10k+ QPS - Rust core built for production-grade throughput
  • · Inference and feedback storage - own your data in your own database

AxonHub

5.1k · Go
Active A

Open-source AI gateway that lets any SDK call 100+ LLMs. Built-in failover, load balancing, cost controls, and end-to-end tracing for production AI agent workloads.

agent-toolsllm-gatewayobservability +2
  • · Unified LLM gateway - call 100+ models through OpenAI and Anthropic compatible protocols
  • · Automatic failover - switch to backup providers when the primary one is down
  • · Smart load balancing - distribute requests across model instances to avoid overload