assurance
PulseGate's liveness check found it on 24 Sep 2026; it is registered on GitHub and PyPI and has been in the index since 24 Sep 2026. How this is checked
Assurance is an open-source Python package that provides tools for examining AI agent runs, including coverage, spending, permissions, and upcoming installations. It is designed for developers operating agent systems who need guardrails and supply-chain visibility.
Inferred · not functionally tested
Overview
6 featuresPurpose: Auditing AI agent activity, permissions, spending, and installation risks in one toolkit.
Inferred · not functionally tested
Audience: AI agent developers and platform engineers
Inferred · not functionally tested
Functions: agents, monitoring
Inferred · not functionally tested
Interfaces: API: indicated (inferred, not tested) · MCP: indicated (inferred, not tested) · CLI: indicated (inferred, not tested) · Self-hosting: indicated (inferred, not tested)
Recorded constraints: pricing: open_source · license: Apache-2.0 · platforms: CLI · deployment: cli, api_only, self_hosted
Constraint provenance is unknown; confirm requirements with the publisher.
Record sources: pypi.org · github.com. These links do not verify the individual claims.
In the AI security & guardrails space, assurance takes a focused approach. Inferred · not functionally tested: It focuses on auditing AI agent activity, permissions, spending, and installation risks in one toolkit. Inferred · not functionally tested: assurance is an open-source project aimed at AI agent developers and platform engineers. Basis unknown · not verified: assurance is open source under the Apache-2.0 license. Basis unknown · not verified: assurance is available on the command line and API, and it can be self-hosted.
Behind assurance is i-ops-hq, and it first shipped in 2026. The project is developed in the open on GitHub with 130 commits in the last 90 days. Inferred · not functionally tested: Among its 6 catalogued features are agent run coverage, spend tracking, and permission checks. Inferred · not functionally tested: Catalogued interfaces include an MCP server.
Summary written by a language model from the project’s public pages.
Tasks: Inferred · not functionally tested
- Agent run coverage
- Spend tracking
- Permission checks
- Install previews
- Supply-chain checks
- Guardrails
Topics: Inferred · not functionally tested
Built with & integrations
- Claude Code
- commit d302d0551950 · since Sep 2026
- Cursor
- commit 5363f1edfec1 · since Sep 2026
Trust & compliance
Indexing history
22What PulseGate has recorded for this listing
Frequently asked questions about assurance
- What does assurance do?
- Inferred · not functionally tested: Assurance focuses on auditing AI agent activity, permissions, spending, and installation risks in one toolkit. It is catalogued under AI security & guardrails on PulseGate.
- Who is assurance for?
- Inferred · not functionally tested: assurance is an open-source project built for AI agent developers and platform engineers.
- Is assurance free?
- Basis unknown · not verified: Yes — assurance is open source under the Apache-2.0 license and free to use.
- What platforms does assurance run on?
- Basis unknown · not verified: assurance runs on the command line and API. It can also be self-hosted.
- Is assurance still active?
- PulseGate's liveness check found it on 24 Sep 2026. Its GitHub repository shows 130 commits in the last 90 days.
- What are alternatives to assurance?
- Similar projects tracked by PulseGate include agent-assurance, agent-assure, and assurance-budget.agent-assuranceagent-assureassurance-budget
- Who develops assurance?
- assurance is developed by i-ops-hq.
- How long has assurance been around?
- assurance first shipped in 2026.
Similar projects
Closest matches by what these projects do