AgentIndex icon
AgentIndex
ToolsMCP ServersHOTCategoriesTrendingNewBest ListsCompareGuides
Submit Tool
ToolsMCP ServersHOTCategoriesTrendingNewBest ListsCompare
Home/
Security & Safety/
ctrlrun
ctrlrun logo

ctrlrun

Active·★ 27·Apache-2.0·Updated 2026-10-22

CTRLRun ensures execution safety for AI agents by acting as a critical check between an agent's decision and the actual call. It enforces strict policies to prevent unintended actions, duplicate effects, and ambiguous outcomes, providing auditable receipts for every interaction.

#AI Agents#Execution Safety#Policy Enforcement#Auditing#Transactional Guarantees#Human-in-the-Loop#Python Library
© 2026 AgentIndex.app|Built by a 10-year iOS Developer.
Best by use caseAboutContactAdvertisePrivacy PolicyTerms of UseQYSGitHubBuy me a coffee ☕

Browse by Category

MCP ServersCode AssistantWorkflow AutomationRAG / Knowledge BaseMulti-AgentBrowser AutomationLLM InfraDev ToolingObservability

Not affiliated with Anthropic, OpenAI or Microsoft.

Guides
$ Install
$ pip install ctrlrun
↗ Visit site★ GitHub
01

Features

01Approval binding to exact actions, refusing mutated or replayed ones.
02Ensures one logical effect happens at most once, across threads, processes, and hosts.
03Distinguishes unknown outcomes (AMBIGUOUS) from failures, blocking blind retries.
04Generates portable JSON receipts for every executed action, recording who, what, and outcome.
05Applies a fail-closed policy, denying unknown actions, missing policies, or principals by default.
02

Compatibility

Python
Runtime
Verified via docs
SQLite
Database
Verified via docs
PostgreSQL
Database
Verified via docs
Multi-host
Deployment
Verified via docs
Microservice Control Plane (MCP)
Integration
Verified via docs
03

Quick start

1
$ pip install ctrlrun
04

Use cases

↳Managing infrastructure deployments and operations in DevOps, ensuring changes are approved and auditable.
↳Enforcing security policies like firewall rules or disabling protection, with strict human oversight for critical actions.
↳Handling financial transactions such as refunds, ensuring amounts are within policy and preventing double refunds.
↳Controlling Identity and Access Management (IAM) operations like granting roles, preventing unauthorized privilege escalation.
05

Alternatives

⚡Top VS:
VSDashClaw★313→VSagents-shipgate★90→VSwirken★192→VS

Comments

Log in to leave a comment

No comments yet. Be the first!

On this page
01Features02Compatibility03Quick start04Use cases05Alternatives
kru
★129
→
DashClaw logo
DashClaw★ 313
🛡️The governance runtime for AI agents. Intercept actions, enforce guard policies, require approvals, and produce audit-ready decision trails.
VSCompare→
agents-shipgate logo
agents-shipgate★ 90
The deterministic merge gate for AI-generated agent capability changes — a local-first, static Tool-Use Readiness review for MCP, OpenAPI, and SDK tool surfaces. Open-source CLI + GitHub Action.
VSCompare→
wirken logo
wirken★ 192
The enterprise gateway for autonomous agents. Identity management, per-channel isolation, credential vault, per-session tamper-evident audit log.
VSCompare→
kru logo
kru★ 129
Local-first MCP password and credential manager for AI agents. Use passwords, API keys, SSH identities, and TOTP without exposing hidden plaintext to the model.
VSCompare→
AegisFlow logo
AegisFlow★ 36
Local-first policy gateway for coding agents. Allow, review, or block MCP, shell, SQL, GitHub, and HTTP actions with scoped credentials and signed evidence.
VSCompare→
mcp-hangar logo
mcp-hangar★ 18
MCP policy enforcement plane — deterministic policy on every Model Context Protocol call: identity, RFC 8707 audience binding, tool schema digest pinning, full audit trail. Python, self-hosted, MIT.
VSCompare→
sourcerykit logo
sourcerykit★ 21
SourceryKit — counterspell for hallucinating agents. Python SDK that breaks the illusion on every tool call, API response, and MCP handoff before bad outputs propagate.
VSCompare→
shellgate logo
shellgate★ 15
Self hosted secure gateway for AI agents. One token. Full control. Complete audit trail.
VSCompare→
See all alternatives →
CTRLRun /
ctrlrun
↗

The execution safety layer for AI agents.

27Apache-2.0
Last commit1d ago
StatusActive
CategorySecurity & Safety
Links
Documentation↗Discussion↗Issues↗Releases↗
Cloud Infrastructure
Ad

Deploy on DigitalOcean

Host your MCP servers, Docker containers, and AI agents with $200 free credit over 60 days.

Claim $200 Free Credit