Show HN: Link firewall log entries to the AI agent step behind them Mnestiq released an open-source Python package, installable via `pip install mnestiq`, that records AI agent runs as hash-chained, Ed25519-signed Merkle checkpoints so a firewall or flow-log connection can be traced back to the specific agent run, step, input and approval behind it. The recorder instruments agents built on Anthropic, OpenAI, Azure OpenAI and OpenAI-compatible models in a few lines of code, tags every model input by source (user, web, tool output, retrieved document, another agent), and joins that evidence with VPC flow logs, Zeek and proxy logs with a confidence score. Mnestiq says the tool is built to fail safely — if recording fails, the agent keeps running — and that prompts and customer data can be redacted before sharing while the proof still holds. Open source · forensic evidence for AI agents Trace a network connection back to the AI agent step that made it. Mnestiq records what your agents saw, decided and did as signed, tamper-evident evidence. When something goes wrong, you can name the run, the step, the input that drove it and who approved it, and prove the record wasn't altered afterwards. pip install mnestiq 1. Firewall10.0.4.17:53120 → 198.51.100.9:25 · 48 KB · no agent identity 2. Mnestiqagent support-bot · run f48cccfa · step 6 · sandbox container:a91f02 · operator acme-helpdesk 3. Causeuntrusted input at step 4 web, via fetch page → model requested send email → approved by policy:email-auto-approve 4. Evidencesealed by checkpoint · signer ed25519:6bec5262… pinned · corroborated by vpc-flow.log, conn.log The gap Your logs see connections. Your traces see prompts. Nothing connects them. A firewall alert: a host that runs AI agents sent 48 KB to an outside mail server on port 25. The responder now has three questions, and today's tools answer none of them. links them Which agent did this? Firewall and flow logs show an IP and a port. They don't know about agents, runs or steps. Why did it do it? Was the instruction from the user, or from a web page, a document or another agent? That has to be captured when it happens, not reconstructed later. Can we prove it? Ordinary logs can be edited by anyone with write access. Evidence for a post-mortem, an insurer or a regulator needs to show it wasn't. How it works Record, verify, investigate. A flight recorder in the agent Records agents built on Anthropic, OpenAI, Azure OpenAI and OpenAI-compatible models in a few lines. Built to fail safely: if recording fails, the agent keeps running. - Every piece of model input tagged by source: user, web, tool output, retrieved document, another agent - Tool calls, approvals and effective permissions - Every outbound connection, with run identity headers and the local address and port Marked sources are treated as untrusted by the detection rules. bash $ pip install "mnestiq anthropic " $ mnestiq keygen --out keys Instrument an existing agent. Your agent code doesn't change. import anthropic from mnestiq import FileSink, Recorder from mnestiq.egress import instrument egress from mnestiq.integrations.anthropic import instrument anthropic from mnestiq.keys import load private key recorder = Recorder FileSink "evidence.jsonl" , agent id="support-bot", signing key=load private key "keys/signing.key" client = instrument anthropic anthropic.Anthropic , recorder instrument egress stamp and record outbound connections during runs with recorder.run : ... your agent, as it is today recorder.close signs the last checkpoint: verify needs it Later: $ mnestiq verify evidence.jsonl --trusted-key keys/signing.pub Tamper-evident by construction Records are hash-chained and sealed by Ed25519-signed Merkle checkpoints. - Edits, deletions, insertions and reordering fail verification - Pin the recorder's key, and a re-signed forgery is rejected - Redact prompts and customer data before sharing, and the proof still holds record hash of the record before record hash of the record before record hash of the record before Signed checkpoint Merkle root of the records it covers · Ed25519 signature Change, remove, add or reorder a record and the hashes stop matching what was signed. From a log line to a cause Join agent evidence with the infrastructure logs you already collect. - VPC flow logs, Zeek and proxy logs linked to the exact agent step, with a confidence score - The untrusted input that preceded an action, and who approved it - Traffic from agent hosts that no recorded step explains When someone edits the record Built for the person holding the incident. What the responder gets The run, the step, the input and the approval. The same evidence file answers the three questions: which agent, why, and whether the record can be shown to be unaltered. Anyone can check it with the open-source verifier, without Mnestiq. Two products Open evidence. Professional detection and investigation. Mnestiq recorder The evidence format, recorder, verifier and a local dashboard. Free and open source, so you can audit it yourself. - An open spec and JSON Schema, aligned with OpenTelemetry GenAI conventions - Python SDK for Anthropic, OpenAI, Azure OpenAI and OpenAI-compatible models - Signing keys held outside the agent, in Azure Key Vault or a dedicated signing service - Independent RFC 3161 timestamps and signed heartbeats - Crash-safe, size-capped, fails open by default - Dashboard runs on your machine only Mnestiq Workbench For security teams that need to see what their agents do as they run, and to investigate and prove what happened when something goes wrong. - Live detection: alerts in Microsoft Sentinel within minutes, every agent's activity, and a dashboard in the tools your SOC already uses - Agent evidence joined with flow, DNS, proxy, firewall and cloud logs, with a stated reason for every link - Microsoft Sentinel both ways: logs come into the case, triage decisions go back onto the incident - An independent Evidence Vault that catches evidence cut back or rewritten - Signed reports, and a claim pack written for insurers that anyone can check Security model What it proves, and what it doesn't. Evidence is only useful if its limits are known. We state them plainly in the open spec https://github.com/mnestiq/mnestiq/blob/main/spec/SPEC.md and in a published threat model https://github.com/mnestiq/mnestiq/blob/main/docs/threat-model.md , where every attack considered is backed by an automated test. Evidence Vault https://mnestiq.com/workbench vault does this for you. Verify, don't trust. You should not have to take a security vendor's word for it. The recorder and its verifier are open source, every claim in the threat model is backed by an automated test, and any evidence file can be verified independently, without Mnestiq. Prompts and data stay on your own systems: only signed checkpoint fingerprints leave, and only to destinations you configure. Independent review is welcome. The break-it challenge https://github.com/mnestiq/mnestiq/blob/main/examples/break-it/README.md provides a signed, timestamped incident record: alter it without the verifier noticing, and tell us how. Design partners Running agents with real permissions in production? Let's talk. We're looking for a small number of security and platform teams to shape the workbench around real incidents.