Agentmetry
Free · Open source
SOC and DevSecOps teams
Rootsign
FreeOpen SourceSelf-Hosted
When an AI agent fires a wrong refund, overwrites a record, or leaks PII, the first question from compliance is: what exactly did it do, in what order, and who authorized it — and the default answer from every major agent framework is silence. RootSign exists to change that answer.
Similar tools
AgentmetryFreeAgentmetry is an open-source, local-only session recorder for AI coding agents — Cursor, Claude…
Comet AIFreemiumOpik connects the full loop: trace every step an agent takes, surface recurring silent errors…
Selfship.aiFreemiumThe observe-diagnose-fix-verify cycle runs on live traffic without you assigning tasks or…
TokenDamFreemiumThe tool runs entirely in the browser — nothing you paste leaves your machine — which means no…
Get This Tool
License: Apache-2.0 Any use incl. commercial
Local-run terms: Users may install via pip, run with local PostgreSQL/TimescaleDB, and use the Python SDK and CLI under the Apache-2.0 license.
Screenshots 3
Pricing
- Model
- Free
Summary
RootSign is an open-source Python library that attaches tamper-evident provenance logging to AI agent actions — tool calls, API hits, database writes — capturing a verifiable record of what happened, in what order, and under whose authorization. The vendor describes it as the agent capture layer of a broader Agent Accountability Platform. It installs via pip and ships a Docker Compose quickstart for self-hosting, so the audit trail stays inside your infrastructure. The library integrates with LangGraph and CrewAI by wrapping agent actions at the point of execution. At low log volume the architecture holds; teams with high-throughput agents running thousands of tool calls per hour will hit questions the current documentation does not answer about storage scaling and query performance.
Bottom line: Pick RootSign when you need a verifiable, self-hosted audit trail for a LangGraph or CrewAI agent in a regulated environment — and plan for additional infrastructure work when that agent's call volume outgrows what a single Docker Compose deployment can absorb.
Find your fit
Before you choose Rootsign
More options in LLM Observability. Compare pricing, platforms, and features side by side.
Comet AI
Freemium
Developers building GenAI apps and agents
Pros
- Tamper-evident log entries, so the audit trail you hand to a compliance reviewer cannot be silently altered after the fact — which is the difference between a debug log and a defensible compliance artifact.
- Self-hosted by design with a Docker Compose quickstart, so the provenance data never leaves your infrastructure — which matters when the records contain PII or financially sensitive agent decisions.
- Apache-2.0 licensed with no paid tier, so there is no vendor gate between your team and the full functionality — you are not discovering that audit export is a paid-only feature six weeks before an audit.
- Native fit for LangGraph and CrewAI, so teams already on those frameworks instrument their agents without rewriting the execution layer.
- Captures action sequence and authorization context alongside the action itself, so when something goes wrong you can reconstruct not just what the agent did but what authorized it to do so.
Cons
- There is no hosted backend, no SaaS option, and no managed storage — standing up and maintaining the infrastructure is entirely on your team. A team without DevOps capacity to run and scale a Dockerized Postgres-backed service will hit this wall before the first production deployment.
- The repository shows 2 stars and 32 commits, with one open issue. Community-sourced answers to edge cases — storage tuning, high-volume write patterns, schema migration in production — do not yet exist. Teams that hit an undocumented failure mode are debugging against source code, not a knowledge base.
- There is no REST API or webhook surface, meaning any external system that needs to read or react to the audit log must connect directly to the storage backend. Teams that need to feed provenance data into a SIEM or compliance platform will build that integration themselves.
- When agent call volume scales and the single Docker Compose deployment becomes a bottleneck, the documentation provides no guidance on horizontal scaling, write throughput limits, or storage partitioning. Teams at that scale will either architect a solution from scratch or switch to a purpose-built observability platform with a managed backend.
About
- Platforms
- Python 3.11+
- API Available
- No
- Self-Hosted
- Yes
- Last Updated
- June 20, 2026
Best For
Who it's for
- Teams needing verifiable provenance for agent actions
- Regulated environments requiring audit trails
- LangGraph and CrewAI users
What it does well
- Audit trails for production AI agent tool calls and API actions
- Compliance-grade logging with tamper detection
- Human-in-the-loop decision verification
Integrations
Compare Rootsign
Frequently Asked Questions
- Is Rootsign free?
- Rootsign offers a free option. Hosting, model usage, or optional services may have separate costs; check the pricing details and official terms.
- Is Rootsign open source?
- Yes. Rootsign is open source.
- Can I self-host Rootsign?
- Yes. Rootsign supports self-hosting on your own infrastructure.
- What platforms does Rootsign support?
- Rootsign is available on: Python 3.11+.
People also compared
Curated lists that include this category
RootSign wraps AI agent tool calls and API actions at execution time, writing tamper-evident log entries that record what action fired, when, in what sequence, and under what authorization context. The core workflow is: install the Python package, configure your storage backend via the provided Docker Compose setup or your own target, then instrument your agent’s action handlers with RootSign decorators or wrappers. Each captured event is stored with cryptographic properties designed to detect after-the-fact modification — so the log you show an auditor is the log that reflects what actually ran.
The differentiating property here is tamper detection, not just logging. Standard application logs can be edited. RootSign’s architecture, as described in the repository, is designed so that any modification to a stored entry is detectable — which is what moves a log from ‘useful for debugging’ to ‘acceptable as a compliance artifact.’ That distinction matters in financial services, healthcare, and any environment where an external auditor will ask you to prove what the agent did.
RootSign fits teams who need to answer regulatory questions about agent behavior without building a custom provenance layer from scratch. It fits tightly with LangGraph and CrewAI. It does not fit teams who need a turnkey SaaS dashboard, a hosted backend, or a no-code setup — the library requires Python instrumentation and your own hosting. The GitHub repository shows 32 commits and 2 stars at the time of this listing, which signals early-stage maturity: the core functionality is present, but edge-case documentation, storage scaling guidance, and community-sourced workarounds are sparse.
The repository ships with a Docker Compose file, an Alembic migration setup indicating a relational storage backend, an examples directory, and a tests directory. The Apache-2.0 license permits commercial use and modification. There is no API surface — RootSign is a library you embed, not a service you call.
Contribute
- Work on Rootsign? Claim this listing.
- Embed a badge for your README or site.
Sign in to rate this tool or suggest an edit.