heron
Heron is a passive analyzer that watches LLM traffic on the wire and reconstructs what your agents are doing — tool calls, multi-step plans, where time goes. No SDK, no proxy, off the request path.
heron at a Glance
- Pricing
- Free
- How you use it
- CLI with a local web console
- Who it's for
- Operations and development teams observing agents and LLM traffic
- Works with
- Claude Code OpenAI Codex Hermes OpenClaw OpenAI Anthropic Azure OpenAI Gemini vLLM Ollama
heron Key Features
- Agent turn reconstruction
- LLM traffic analysis
- Latency and token metrics
- Session observability
- Trajectory export
Can't Find What You're Looking For?
We build custom AI agents tailored to your specific business needs. From ideation to deployment, TinyAI.Tools is your partner in AI innovation.
No commitment required. Let's discuss your ideas.
heron Alternatives
OpenLore
Deterministic, local-first memory and guardrails for AI coding agents with no LLM in the hot path. - clay-good/OpenLore
claude-tap
Intercept and inspect Coding Agent API traffic from Claude Code, Codex CLI, Gemini CLI, Cursor CLI, OpenCode, Kimi/Kimi Code, Pi, and Hermes in a local trace viewer. - liaohch3/claude-tap
PI-Desktop
A modular desktop workspace for AI agents
SuiGPT
SuiGPT - AI-powered Move code decompiler and analyzer
Deuz-SDK
A pure, web-first, multi-provider TypeScript AI SDK with zero runtime dependencies and one canonical streaming wire.
OpenGuider
An AI companion that lives on your desktop - OpenGuider watches your screen, listens to your voice, and guides every step with clear actions. - mo-tunn/OpenGuider