Agent Incident Forensics
Portable, redactable, hash-chained evidence for agent runs.
Seal it. Ship it. Re-verify it — without trusting the producer’s UI.
Traces show you a story in a dashboard.
SAGE gives you an artifact another team can fail-closed verify offline.
Observability products already exist. The gap is a backend-neutral forensic pack: redacted before hash, content-addressed blobs, custody MAC, optional pinned Ed25519, third-party sage verify.
SAGE is a security tool, not a chat UI, not an RCA leaderboard, and not “AI observability SaaS.”
pip install -e ".[dev]"
export SAGE_PACK_KEY="replace-me"
python examples/security_verify_loop.py
sage verify evidence.sage.tar.gz \
--policy policies/strict.json \
--witness \
--hmac-key "$SAGE_PACK_KEY" \
--receipt verify.receipt.jsonAuditor posture (pinned signature):
python examples/auditor_kit.py
# docs: docs/AUDITOR_KIT.md · docs/VERIFY_RUNBOOK.mdfrom sage import SageRecorder
with SageRecorder(trace_id="incident-42") as rec:
agent.run(task)
rec.export("incident.sage.json")| Capability | Detail |
|---|---|
| Recorder | Sanitize-on-close, redact-before-hash, CAS offload |
| Journal | Crash-safe live WAL → sealed manifest + merkle |
| Pack v2 | Portable .sage.tar.gz with custody-bound HMAC |
| Verify | Policies, blob inventory, witness, receipts |
| Signatures | Optional Ed25519 — pinned key required (TOFU refused) |
| Handoff | Offline auditor kit (sage handoff) |
| Adapters | LangChain callback, CrewAI/AutoGen wrappers, OTel tap |
Formats are frozen under the 2.x compatibility covenant.
- Does not prove the agent / LLM / tools told the truth
- Research (
sage research *) is not forensic custody - Software HMAC/Ed25519 ≠ HSM identity — see THREAT_MODEL.md
pip install -e ".[dev]" # core + tests + cryptography
pip install -e ".[sign]" # Ed25519 only
pip install -e ".[tui]" # optional inspect TUICore recorder / CAS / verify / CLI remain stdlib-only.
python scripts/release_check.py
pytest -q
python examples/auditor_kit.py
sage doctorCI: Ubuntu · Windows · macOS × Python 3.10 / 3.12.
| Doc | Purpose |
|---|---|
| VERIFY_RUNBOOK.md | Record → ship → auditor re-verify |
| AUDITOR_KIT.md | Pinned-signature verify posture |
| THREAT_MODEL.md | Assets, adversaries, non-goals |
| SECURITY.md | Supported versions / reporting |
| RELEASE.md | Tag / publish checklist |
| CONTRIBUTING.md | PR bar for a security tool |
If you run agents in production and want sealed incident packs on one real path — open an issue or reach out. We want brutal feedback, not vanity stars.
FSL-1.1-ALv2 — Functional Source License (Fair Source).
- ✅ Internal use, education, research, self-host for your company
- ❌ Competing commercial product/SaaS without a commercial license
- ⏱ Converts to Apache-2.0 2 years after each version’s availability
Commercial terms: COMMERCIAL.md · License FAQ: fsl.software
