Tenbri 0.1.0-beta.5: Tenbri UI, a read-only web UI served by tenbrid

The Agent Decision Record

Tenbri: the open-source Agent Decision Record

Proof of what your agents decided

An Agent Decision Record is a signed, append-only record of every decision an AI agent makes: who acted, under which rule and inputs, who approved, and what happened, verifiable offline by anyone. Tenbri is the open-source one. One line for Claude, OpenAI and LangGraph agents; plain files on storage you control.

$ pip install --pre tenbri
import tenbri

tenbri.init()                        # TENBRI_STREAM, TENBRI_AGENT, TENBRI_APPROVER
tenbri.instrument_claude_agent_sdk() # every tool call becomes a signed decision

# or: tenbri.instrument_openai_agents()
# or: tenbri.instrument_langchain()

Tenbri UI

See what your agents decided

tenbrid serves a read-only UI over your streams: dashboards, every decision with its outcome, traces as timelines, and a verification check. Open it with a bearer token; it cannot write.

127.0.0.1:7070

Overview, then the errors, one decision's timeline and signed chain, its whole trace, and the integrity check.

See it run

Record, verify, tamper, get caught

A refund function decorated with @tenbri.decision, called three times. Then someone edits one byte on disk. Real output from a run, with hashes and paths shortened.

  1. 1Record
  2. 2Read
  3. 3Verify
  4. 4Tamper
  5. 5Caught
tenbri quickstart
OpenAIHugging Face

From the blog · Incident analysis

Five days to “it was us”

In July 2026, OpenAI agents broke out of an evaluation sandbox and attacked Hugging Face. Attribution took five days. What a signed record of every agent decision would have changed, and what it would not.

Read the analysis
  1. ~17,600agent actions Hugging Face recovered from its own logs
  2. 5 daysfrom the public disclosure to “it was us”
  3. 1 querywith a Tenbri record: tenbri query --target-domain, on the roadmap

What you get

Built for the day something goes wrong

Disputes, incidents, policy changes and audits all ask the same question: what did the agent decide, and on whose authority?

$ tenbri verify
verified 8 entries, stream tnb1:986d8e32…3588, pinned to sha256:986d8e32… (the pin recorded in ~/demo/keys/pins)

$ tenbri verify    # after someone edits one batch on disk
broken at seq 5: bad_signature: the signature does not verify
4 entries verified before it, stream tnb1:986d8e32…3588

$ tenbri verify audit/support --key sha256:986d8e32…   # an auditor on another machine pins it
Verify

Anyone can check it, offline

Hand an auditor the stream and one fingerprint. Verification checks canonical bytes, the hash chain, every Ed25519 signature and every key, with no access to your systems. A checkpoint they kept catches truncation and forks.

How integrity works
$ tenbri query --rule policy:refund@14
3  2026-10-20T16:49:42.442Z  decision intent  agent:support  issue_refund stripe:ch_3PqX  -  verified
5  2026-10-20T16:49:42.485Z  decision intent  agent:support  issue_refund stripe:ch_9ZzY  -  verified
7  2026-10-20T16:49:42.525Z  decision intent  agent:support  issue_refund stripe:ch_0     -  verified

$ tenbri query --rule policy:refund@14 --json | jq .entry.action   # JSON when piped
Query

Every decision made under the old rule

Inputs are pinned by reference, version and keyed digest. When a policy changes, list what was decided under the previous version and review it. Each answer is re-checked against storage before it is returned.

Review a policy change
unknown_actions = "reject"

[actions.issue_refund]
target   = "stripe:{charge}"     # filled from the tool call's arguments
policy   = "policy:refund@14"    # the rule that allowed it
approval = true                  # a person must approve first
inputs   = ["policy:refund"]

[actions.issue_refund.fields."ext.refund.amount"]
required = true
type = "integer"
Schemas

Say what each action must record

Declare actions once in tenbri.toml. The SDKs read it to map tool calls to actions, targets and policies, tenbrid enforces it at write time, and CI checks whole streams against it.

Action schemas
$ tenbri receipt create ./audit/support --entry 3 --out refund-3.receipt
$ tenbri receipt verify refund-3.receipt --key sha256:9c1e…
proves seq 3 (decision intent), id 01M4XBH0Y6…, ts 2026-10-14T14:02:13Z (claimed by the writer)
in stream tnb1:1702…b7d8, checkpoint at size 8, pinned to sha256:9c1e…; key history: 2 key entries
Receipts

Proof you can hand over

A receipt proves specific entries with their inclusion proofs, the key history and an optional RFC 3161 timestamp. A customer, a regulator or the police verify it alone, without seeing the rest of the stream.

Receipts and timestamps
$ tenbri erase ./audit/support --subject subj_7f3c91d2 --reason dsr:2026-1042 --yes
erased subject subj_7f3c91d2: 2 data key epochs deleted; erasure recorded at seq 7

$ tenbri verify ./audit/support --key sha256:9c1e…
verified 8 entries, stream tnb1:1702…b7d8, pinned to sha256:9c1e…
Privacy

Erase a person without breaking the chain

Only hashes go in the chain. Bodies are encrypted and input digests are keyed per subject, so deleting a subject's keys makes their data unreadable while every chain, checkpoint and receipt still verifies.

Privacy and erasure
$ export TENBRI_STREAM=r2://audit/agents/support CLOUDFLARE_ACCOUNT_ID=…

$ curl -X POST https://tenbrid.internal:7070/v1/streams/support/intents \
    -H "Authorization: Bearer $TOKEN" -H "Idempotency-Key: $(ulid)" \
    -d '{"action":{"type":"issue_refund","target":"stripe:ch_81f2"}}'
{"entry":{"kind":"decision","phase":"intent","seq":3,…},"replayed":false}
Anywhere

Your storage, any language

A stream is plain files in a directory, S3, R2 or MinIO, with the keys kept apart. Write from Python, TypeScript or Rust, or run tenbrid and use REST or gRPC from anything else.

tenbrid API

A new kind of record

Logs, traces, decision records

Observability tools such as Langfuse and MLflow answer how an agent ran. A decision record proves what it decided and on whose authority. Keep both: Tenbri links each decision to its OpenTelemetry trace.

QuestionLogsTracesDecision records
What it answersWhat a service printedHow the agent ran: steps, latency, tokens, costWhat the agent decided, and on whose authority
Who it servesOperatorsEngineers improving the agentAuditors, customers, regulators and incident review
Can it be altered?Yes: edited, rotated, deletedYes: sampled, rewritten, expiredNo: any change fails verification
Can a third party verify it?No, they must trust youNo, they need your accountYes, offline, with one fingerprint

Architecture

Write, sign and chain, store, prove

One Rust core behind every SDK, the CLI and tenbrid. Turn on the optional parts when you need them; the rest is on the roadmap.

  1. WriteYour agents and services

    Available

    Optional

    Coming soon

    • Proxy-observed entries
    • Ingest and Kafka
  2. Sign and chainTenbri core, in Rust

    Available

    Optional

    Coming soon

    • PKCS#11, cloud KMS
    • Passkey attestations
  3. StoreStorage you control

    Available

    Optional

    Coming soon

    • GCS, Azure Blob, Postgres
    • Iceberg index, --as-of
  4. ProveAnyone with the fingerprint

    Available

    Optional

    Coming soon

    • Witnesses, Rekor
    • Silent-stream alerts
    • Viewer, MCP, exports

One Rust core behind every SDK, the CLI and tenbrid. Entries are signed and chained before they reach storage; signing keys never live with the stream.

Status as of 0.1.0-beta.5. Source: the Tenbri roadmap.

Records these frameworks ask for

Evidence, not screenshots

Tenbri gives you the records. It does not make a system compliant on its own.

  • EU AI Act Art. 12, 14, 19, 26
  • GDPR Art. 22
  • DORA
  • NIS2
  • SOC 2
  • ISO/IEC 27001
  • ISO/IEC 42001
  • NIST AI RMF

Start recording decisions in five minutes

Open source, Apache-2.0, written in Rust. Plain files on storage you control, and no telemetry.