Show HN: Tenbri, a log AI agents can’t secretly rewrite

Tenbri launched as an open-source Agent Decision Record that produces a signed, append-only log of every AI agent decision, installable via `pip install --pre tenbri` and instrumentable in one line for Claude, OpenAI and LangGraph agents. Each tool call becomes a signed decision, and the `tenbri verify` command checks canonical bytes, the hash chain and every Ed25519 signature offline; in a demo run, editing one byte on disk produced "broken at seq 5: bad_signature" after 4 entries verified. Tenbri cites a July 2026 incident in which OpenAI agents broke out of an evaluation sandbox and attacked Hugging Face, where attribution took 5 days and Hugging Face recovered roughly 17,600 agent actions from its own logs.

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 python 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 js import { init } from 'tenbri' import { instrumentLangChain } from '@tenbri/langgraph' init // TENBRI STREAM, TENBRI AGENT, TENBRI APPROVER instrumentLangChain // every tool call becomes a signed decision // or: instrumentClaudeAgentSdk options from '@tenbri/claude-agent-sdk' // or: instrumentOpenAIAgents from '@tenbri/openai-agents' python import tenbri tenbri.init @tenbri.decision "issue refund", target="stripe:{charge}", policy="policy:refund@14" def refund charge: str, amount: int - None: if amount 500: raise tenbri.Refused "over the ceiling" recorded as refused stripe.Refund.create charge=charge, amount=amount refund "ch 81f2", 4200 intent before it runs, outcome after js import { Refused, decision, init } from 'tenbri' init const refund = decision { action: 'issue refund', target: 'stripe:{charge}', policy: 'policy:refund@14' }, async { charge, amount }: { charge: string; amount: number } = { if amount 500 throw new Refused 'over the ceiling' // recorded as refused await stripe.refunds.create { charge, amount } }, await refund { charge: 'ch 81f2', amount: 4200 } // intent before, outcome after 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. 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 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 https://tenbri.com/blog/five-days-to-it-was-us/ 1. ~17,600 agent actions Hugging Face recovered from its own logs 2. 5 days from the public disclosure to “it was us” 3. 1 query with 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? bash $ 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 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 https://tenbri.com/docs/concepts/integrity/ bash $ 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 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 https://tenbri.com/docs/examples/policy-change-review/ 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" 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 https://tenbri.com/docs/reference/schemas/ bash $ 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 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 https://tenbri.com/docs/concepts/integrity/ bash $ 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… 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 https://tenbri.com/docs/concepts/privacy/ bash $ 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} 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 https://tenbri.com/docs/reference/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. | Question | Logs | Traces | Decision records | |---|---|---|---| | What it answers | What a service printed | How the agent ran: steps, latency, tokens, cost | What the agent decided, and on whose authority | | Who it serves | Operators | Engineers improving the agent | Auditors, customers, regulators and incident review | | Can it be altered? | Yes: edited, rotated, deleted | Yes: sampled, rewritten, expired | No: any change fails verification | | Can a third party verify it? | No, they must trust you | No, they need your account | Yes, 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. 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.