Skip to content
Back to the index

revathi

PyPIInfrastructure

No liveness check has reached it yet; it is registered on PyPI and has been in the index since 11 Oct 2026. How this is checked

Revathi is an open-source Python package that adds safety controls for AI agents, including action guards, proof-before-completion checks, undo support, tamper-evident records, and approved memory. It is intended for developers using Claude Code, Antigravity, and similar agent workflows.

Inferred · not functionally tested

Open SourceMITCLISelf-hosted
Visit PyPI

Overview

6 features

Purpose: Preventing AI agents from taking unsafe or unverifiable actions without an auditable way to undo them.

Inferred · not functionally tested

Audience: developers building or operating AI coding agents

Inferred · not functionally tested

Functions: agents, monitoring

Inferred · not functionally tested

Interfaces: API: unknown · MCP: unknown · CLI: indicated (inferred, not tested) · Self-hosting: indicated (inferred, not tested)

Recorded constraints: pricing: open_source · license: MIT · platforms: CLI · deployment: cli, self_hosted

Constraint provenance is unknown; confirm requirements with the publisher.

Record sources: pypi.org. These links do not verify the individual claims.

revathi is an AI security & guardrails project. Inferred · not functionally tested: It focuses on preventing AI agents from taking unsafe or unverifiable actions without an auditable way to undo them. Inferred · not functionally tested: revathi is an open-source project aimed at developers building or operating AI coding agents. Basis unknown · not verified: The project is open source (MIT). Basis unknown · not verified: It runs on the command line, and it can be self-hosted.

revathi first shipped in 2026. Inferred · not functionally tested: Among its 6 catalogued features are action guards, proof checks, and undo support.

Summary written by a language model from the project’s public pages.

Tasks: Inferred · not functionally tested

  • Action guards
  • Proof checks
  • Undo support
  • Tamper-evident records
  • Approved memory
  • Agent hooks

Topics: Inferred · not functionally tested

Tags
ai-agent-guardrailstamper-evident-auditagent-undoapproved-memory
AI capabilities
TextCode
Inference: Local

JSON profile · Text profile · Access guide

Built with & integrations

AI providers
anthropic
Runs on
CLISelf-hosted

Trust & compliance

License
MIT
Public signals
HTTPSOpen Source

Indexing history

2

What PulseGate has recorded for this listing

  1. Indexed11 Oct · 14:52 UTC
    revathi seen via PyPI Fresh Feed
    Source: PyPI Fresh Feed · Open
  2. Indexed11 Oct · 13:45 UTC
    revathi seen via PyPI Bulk Enumerator
    Source: PyPI Bulk Enumerator · Open

Frequently asked questions about revathi

What is revathi?
Inferred · not functionally tested: Revathi focuses on preventing AI agents from taking unsafe or unverifiable actions without an auditable way to undo them. It is catalogued under AI security & guardrails on PulseGate.
Who is revathi for?
Inferred · not functionally tested: revathi is an open-source project built for developers building or operating AI coding agents.
Is revathi free?
Basis unknown · not verified: Yes — revathi is open source under the MIT license and free to use.
What platforms does revathi run on?
Basis unknown · not verified: revathi runs on the command line. It can also be self-hosted.
Is revathi still maintained?
Unverified. revathi has not been re-checked since it entered the index, so there is no finding either way — and only a positive finding would say otherwise.
What projects are similar to revathi?
Similar projects tracked by PulseGate include VITNA, cloakroom, and Privacy Policy.VITNAcloakroomPrivacy Policy
When did revathi launch?
revathi first shipped in 2026.
Is revathi open source?
Basis unknown · not verified: Yes — revathi is open source under the MIT license.

Also in AI security & guardrails

Same category — not a similarity match