AgentIndex icon
AgentIndex
ToolsMCP ServersHOTCategoriesTrendingNewBest ListsCompareGuides
Submit Tool
ToolsMCP ServersHOTCategoriesTrendingNewBest ListsCompare
Home/
Multi-Agent/
dos-kernel
dos-kernel logo

dos-kernel

Active·★ 20·MIT·Updated 2026-09-27

An AI agent will tell you it finished. DOS checks the real world instead of taking its word — and the nearest piece of the real world is your git history. It verifies agent claims against artifacts, providing an objective verdict to prevent false 'done' reports and ensure reliable multi-agent operations.

#AI Agent Verification#Multi-Agent Systems#GitOps#Workflow Orchestration#Developer Tools#Code Integrity
© 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
#Autonomous Agents
$ Install
$ pip install dos-kernel && dos init --hooks auto
↗ Visit site★ GitHub
01

Features

01Verifies agent claims against real-world artifacts like git history, file tree, and clock, rather than agent narration.
02Prevents agents from falsely reporting 'done' and detects silent failures or agents stuck in loops ('spinning').
03Coordinates multiple agents working on the same repository, arbitrating collisions and enforcing file-scope boundaries.
04Integrates with diverse agent runtimes, CI/CD pipelines, and fleet frameworks through hooks, CLI exit codes, or a Python API.
02

Compatibility

Python
Runtime
Verified via docs
Git
Version Control
Verified via docs
Linux
Operating System
Verified via docs
Windows
Operating System
Verified via docs
AI Agent Frameworks
Integrations
Verified via docs
03

Quick start

1
$ pip install dos-kernel
2
$ dos init --hooks auto
04

Use cases

↳Ensuring the reliability and trustworthiness of AI agent-generated code in software development workflows.
↳Automatically gating or approving code changes made by autonomous agents within CI/CD pipelines based on verified claims.
↳Orchestrating and monitoring multi-agent fleets to prevent silent conflicts, identify stalled runs, and improve overall efficiency.
↳Streamlining code review processes by pre-validating agent-claimed commits, allowing human reviewers to focus on unverified or complex changes.
05

Alternatives

⚡Top VS:
VSHexis★118→VSagent-framework★14.3k→VSspring-ai-alibaba★11.1k→

Comments

Log in to leave a comment

No comments yet. Be the first!

On this page
01Features02Compatibility03Quick start04Use cases05Alternatives
VS
agents-aea
★242
→
Hexis logo
Hexis★ 118
Centrally manage AI-agent skills, tools, context, permissions, and identity across your entire org. Self-hosted, Git-backed and MCP-native.
VSCompare→
agent-framework logo
agent-framework★ 14.3k
A framework for building, orchestrating and deploying AI agents and multi-agent workflows with support for Python and .NET.
VSCompare→
spring-ai-alibaba logo
spring-ai-alibaba★ 11.1k
Agentic AI Framework for Java Developers
VSCompare→
agents-aea logo
agents-aea★ 242
A framework for autonomous economic agent (AEA) development
VSCompare→
piyaz logo
piyaz★ 196
The agentic workspace where people and AI coding agents work together on every project.
VSCompare→
agent-symphony logo
agent-symphony★ 123
Multi-Agent AI Task Orchestrator 2026
VSCompare→
paneflow logo
paneflow★ 87
Local-first Rust/GPUI workspace for running coding agents side by side: real terminal panes, live status, worktree review, read-only MCP, and local orchestration.
VSCompare→
dwarf_fortress_mcp logo
dwarf_fortress_mcp★ 24
A semantic, transactional, replayable MCP control plane that lets autonomous AI agents operate Dwarf Fortress as a long-lived civilization. Safe-Rust phase-0B scaffold: MVCC world state, witnessed semantic plans, evidence-backed effects, deterministic replay.
VSCompare→
See all alternatives →
anthony-chaudhary /
dos-kernel
↗

Catch your AI agents when they lie about what they shipped — verifies claims against git instead of believing the agent.

20MIT
Last commit3w ago
StatusActive
CategoryMulti-Agent
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