Heron: Wireshark for AI Agents — Passive eBPF Observability
Heron is a passive network analyzer that reconstructs what AI agents are doing by capturing TLS-encrypted LLM calls via eBPF, with zero SDKs or proxies. It's open-source, Rust-based, and latest v0.7.0 aligns with OpenTelemetry, adds eBPF capture discovery, auto-filters hidden sidecars, and enables one-click SFT trajectory export for fine-tuning.
Heron : Wireshark for AI Agents: passive eBPF observability | Product Hunt
Heron
Launching today
Wireshark for AI Agents: passive eBPF observability
42 followers
Wireshark for AI Agents: passive eBPF observability
42 followers
Visit website
Observability tools
Heron is a passive network analyzer that reconstructs what your AI agents are actually doing. Zero SDKs. Zero proxy. Hook eBPF to see TLS-encrypted LLM calls and identify which agent process made them.
Overview
Reviews
Alternatives
Team
More
Launch tags:Open Source•Developer Tools•Artificial Intelligence
Launch Team
Subscribe
Promoted
Maker
📌
Hey PH! 👋 I'm sharing Heron today on behalf of the engineering team at Netis.
We built Heron because our team got tired of our AI agent loops looking like 200 OK in the logs while the actual agent was stuck replaying the same tool call for 47 seconds straight.
What Heron does: Heron is a passive analyzer that reconstructs what your AI agents are actually doing — from the network traffic itself. No SDK, no proxy, nothing in the request path. It captures LLM traffic (OpenAI, Anthropic, Gemini, vLLM, SGLang, Ollama…), parses the wire protocol, and stitches multi-call interactions into agent turns you can actually debug.
What's new in v0.7.0 (just shipped): 🌌 OpenTelemetry Native — We completely aligned our architecture with OTel standards. Agent turns are now traces, and LLM calls are now spans.
🔥 eBPF capture discoverability — hook SSL_read/SSL_write to see TLS-encrypted agent traffic as plaintext, with process attribution (which agent process made which call). No proxy, no TLS terminator.
📊 We discovered that ~73% of Claude Code's Opus turns in our production capture were hidden security-monitor sidecars — Heron now filters them automatically so you see real agent work, not housekeeping noise.
🧬 One-click SFT trajectory export — turn your production agent traffic into fine-tuning training data without re-running anything.
Built in Rust, ships as a single binary with the React console embedded. Apache-2.0. Would love your feedback!
🦩 Try it: curl -fsSL https://raw.githubusercontent.com/Netis/heron/main/install.sh | sh ⭐ GitHub: https://github.com/Netis/heron
Report
24h ago
What's the performance impact of running Heron alongside a live agent in production?
Report
1h ago
Maker
@pradyumna6 Great question. Heron is designed to avoid request-path impact: it does not sit between your agent and the model provider, and it does not proxy or mutate requests. It passively observes traffic, so it should not add latency to the live agent path.
That said, it is still a real observer process, so the impact depends on traffic volume, body sizes, capture mode, retention settings, and storage backend. In production we recommend starting with a passive/shadow deployment, tuning retention and body caps, and watching CPU, memory, and disk I/O before expanding coverage.
The main design goal is: if Heron is slow or fails, your agent traffic should keep flowing. Heron may lose observability data under resource pressure, but it should not block the agent itself.
Report
36m ago
Seeing TLS encrypted LLM calls without proxies sounds impressive I'd to understand the technical boundaries and what information remains inaccessible due to encryption or process isolation.
Report
9m ago
If I've got a swarm of agent processes all calling out to the same LLM endpoint from one box, how do you disambiguate which process initiated which call at the eBPF layer, is it PID tracking through the syscall, or are you also correlating with something at the process tree level?
Report
10m ago