Tenbri

Tenbri is an open-source audit trail tool that creates signed and hash-chained decision records for AI agents.

Tenbri provides an audit trail for AI agents by generating signed, append-only decision records on storage you control. It records who acted, the rules and inputs used, approvals, and outcomes, with verification performed offline through canonical bytes, hash chains, and Ed25519 signatures. The platform supports Python, TypeScript, and Rust, with framework adapters for Claude, OpenAI, and LangGraph. It is designed for developers, auditors, and organizations needing proof of agent decisions for compliance, incident analysis, and disputes. Tenbri sets itself apart by keeping storage under user control, maintaining privacy through encrypted bodies and subject erasure, and linking decisions to OpenTelemetry traces.

Tenbri at a glance

Best for: Software engineer
Runs on: Web, macOS, Windows, Linux, API, CLI, self-hosted, open source
Pricing: Free
Released: October 2026
Category: AI agent tool
Website: tenbri.com

Key features

Hash-chained and Ed25519 signed decision records
Offline verification by anyone using a fingerprint
SDKs for Python, TypeScript, and Rust
Framework adapters for Claude, OpenAI, and LangGraph
Plain file storage on local disk, S3, R2, or MinIO
Encrypted bodies and subject erasure
Action declarations via tenbri.toml

Use it for

Investigate AI agent incidents and security breaches
Verify agent decisions offline for auditors and regulators
Track policy changes and decisions made under previous rules
Generate cryptographic receipts for specific agent actions

Alternatives to Tenbri

iFixAi — Audits agent behavior independently without building manual eval harnesses.
TencentDB Agent Memory — It unifies cross-agent memory assets, skill libraries, wikis, and code graphs.
Toli — Connects different AI systems to collaborate on tasks locally and across networks.
BrowserOS — Runs entirely locally and lets AI agents use real user logins to complete tasks.
Caura — Governed memory providing persistent knowledge sharing for AI agent fleets.
Beeuni — Agents retain context and improve skills over time through a controlled review process.
Melra — Governs AI agent tool calls with local policies, approval gates, and verified receipts.
Agent Beacon — Retains coding agent knowledge across tools so errors do not repeat.
Sandbase Harness — It keeps agent infrastructure local, secure, and fully auditable.
Agent Referee Client — Provides signed receipts for agent decisions and independent reviews.
Trigora — It uses Transparent Continuation Checkpointing instead of replaying prior history.
Hybro — Orchestrates local and remote agents using the open Agent2Agent protocol.

All Tenbri alternatives