Kronn
Active·★ 18·AGPL-3.0·Updated 2026-10-22
Kronn is a self-hosted control plane that unifies multiple AI coding agents like Claude Code, Codex, and Ollama into a single dashboard, offering shared context, secrets, and repeatable workflows. It emphasizes decomposing complex AI tasks into smaller, deterministic code steps and focused AI prompts, reducing token costs and improving reliability.
#AI Agents#Workflow Automation#Self-Hosted#LLM Orchestration#Prompt Engineering#Dev Tooling#Local LLMs#Code Audit
01
Features
01Unifies multiple AI coding CLIs (Claude Code, Codex, Gemini, Ollama, etc.) into a single, self-hosted dashboard.
02Enables batch processing of Quick Prompts over multiple items (e.g., 30 PR drafts from Jira tickets) with human approval gates.
03Allows validation of AI prompts by comparing results across multiple agents, ensuring prompt solidity before batch execution.
04Supports 100% local operation with Ollama, enabling zero token cost and enhanced data privacy.
05Provides a comprehensive code audit system that generates structured documentation, detects drift, and integrates with workflows.
02
Compatibility
Rust
Backend
Verified via docs
React
Frontend
Verified via docs
MacOS
OS
Verified via docs
Windows
OS
Verified via docs
Linux
OS
Verified via docs
Docker
Container
Verified via docs
03
Quick start
1
$ git clone https://github.com/DocRoms/Kronn.git
2
$ cd Kronn
3
$ ./kronn start
04
Use cases
↳Consolidating management of disparate AI coding assistants from different vendors into one unified interface.
↳Automating repetitive code-related tasks, such as generating release notes, refactoring code, or drafting multiple PRs from a list of tickets.
↳Implementing an eco-friendly and cost-effective AI workflow by using deterministic code steps where possible and focused AI prompts only for reasoning.
↳Performing in-depth, persistent code audits for security, quality, and architecture, with drift detection and automatic ticket generation.
↳Creating end-to-end Auto-Dev workflows from issue creation to PR merge, incorporating human checkpoints for approval.
05
Alternatives
oto-dock★ 193
The self-hosted platform for your company's AI agents. Your team builds them on Claude Code, Codex or local models, and they work in chats, on schedules, on the phone and on your own machines.
nimblebrain★ 25
Self-hosted platform for MCP Apps and agent automations — tools, interactive UIs, scheduled runs, multi-agent delegation.
OctoForge★ 22
Self-hosted multi-tenant agent platform for teams: skills, knowledge, API contracts and MCP servers live in the database and grow at runtime; big API responses are queried with SQL, not stuffed into context. Typed Python core (Protocol ports) you can embed in your own stack.
marvis★ 14
The Company Brain your agents install — use your coding agent to run projects and coordinate agents, not just code. Cross-project knowledge graph + immutable audit, self-hosted & EU-resident. BSL 1.1 → Apache 2.0.
loomcycle★ 15
The runtime substrate for agentic systems — one Go binary, six LLM providers, MCP-native, configurable as a managed sandbox or full agentic dev environment. Where agents live, talk, and learn.
Comments
Log in to leave a comment
No comments yet. Be the first!