You juggle multiple AI CLIs (Claude Code, Codex, Gemini, Ollama) across multiple projects. Kronn brings shared memory, orchestration, and continuity. Local-first. 0 tokens on mechanical steps.
Four AI CLIs that ignore each other. Three diverging MCP configs. Fourteen copy-pasted prompts. Accepted state of the art. Kronn proposes a shared brain, local, plugged into everything.
Locally persisted discussions. Same context picked up by any CLI, OR N CLIs live in the same conversation.
Versioned Quick Prompts, measured, ✨ AI Improver.
Mechanical steps without an agent. AI cost = 0 tokens.
Here is what you do today, and what Kronn does for you.
{{vars}}, metrics per iteration.disc_join. Zero human messenger.Notify runs agentless: zero tokens.ApiCall (Resend, Mailjet, log webhook): zero tokens, the API directly, no LLM.docs/AGENTS.md generated by audit, auto-read by every agent.
You still write prompts by feel.
You copy-paste your context from one agent to another.
You pay the AI to send a Slack webhook.
You maintain three MCP configs that diverge the moment you blink.
Kronn ends this era.
No roadmap, no soon™. Everything is shipped, in the code, verifiable. Exhaustive list of what Kronn gives you today.
docs/AGENTS.md generated by audit~/.kronn/user-context/.kronn.json per project{{vars}} + conditional sections{{previous_qp.output}}You start with an MCP plugin, the agent learns how the vendor responds, tests, iterates. Once the sequence stabilizes, a dedicated AI Helper walks you through switching to an API plugin: the AI leaves the loop, execution becomes deterministic and token-free.
No promised numbers, just the building blocks that let regular usage lower cost and raise quality over time. Each one is in the code, reproducible, verifiable.
Full project scan: stack, conventions, tech debt. Generates tier-loaded docs/AGENTS.md. AutoPilot (opt-in) turns debts into Jira tickets via MCP and pre-configures the processing workflow in 1 click.
Locally persisted discussions + 10 MCP tools disc_* for bidirectional cross-CLI continuation. The next CLI reads AND enriches the thread, not just consults.
Your global preferences (commit style, conventions, anti-patterns) live in ~/.kronn/user-context/. All your projects benefit automatically. Each preference added → effect everywhere.
Reusable prompts with {{vars}}. Versioned and measured (tokens · duration · cost). You iterate, compare, pick the winner.
Step-based orchestration: Agent step + 5 mechanical steps (Exec, Gate, Notify, ApiCall) at 0 tokens by definition. CRON-schedulable. Feasibility-Gated pattern for big tickets: YAML triage → human Gate → constrained code.
Stating exclusions wins over skeptics. Here is what Kronn was not built to be.
Keep Cursor, VSCode, Vim, or Aider for CLI pair-prog. Kronn orchestrates above, doesn't replace your editor, though you can do quite a bit from Kronn: git worktree, diff access, direct exec, human gates ;)
You bring Anthropic, OpenAI, Google, or Ollama 100% local. Kronn locks you into none.
Local-first desktop app. Your data, prompts and discussions never leave your machine.
You drive via UI, you don't code. Multi-CLI orchestrated, not LangGraph in Python.
For non-AI integrations (Slack, ETL, CRM, lifecycle email), keep n8n or Zapier. Kronn targets AI agent orchestration specifically.
For build, deploy, lint on git, keep GitHub Actions. Kronn orchestrates local-first AI agent CLIs, not repo-bound cloud pipelines.
OK, convinced? Here is the local install. At the end you have an audited project, a measured Quick Prompt, and discussions that survive switching between 2 CLIs.
Two install paths:
Desktop app · download the binary (Mac, Windows, Linux) from releases.
Self-hosted · git clone -b <tag> then kronn start (CLI / headless, ideal for teams).
Local-first in both cases. Agent metrics stay local (QPs, runs, tokens, cost) · never cloud telemetry.
Open Kronn, add your project, launch audit with Briefing (≈ 2 min of guided Q&A). Kronn then scans your stack, detects conventions, identifies tech debt and generates tier-loaded docs/AGENTS.md.
Launch: 2 min. Background scan: 20-30 min on an average project, more on a monorepo. AutoPilot ready afterward to turn debts into tickets.
Automation tab, create a Quick Prompt. Drop a {{ticket}} variable in the template. Run it on an agent: Kronn records tokens, duration, cost.
You can run the same Quick Prompt on N agents in parallel to compare outputs.
Automation → Workflows tab, click New and pick a preset (Ticket-to-PR, Feasibility-Autopilot, Feature Planner…). Kronn pre-fills the steps Brief → Architecture → Code → Tests → Review with their human Gates. All you do is approve at each Gate.
The Quick Prompts from STAGE 03 work as building blocks inside your custom workflows.
Eight terms that show up everywhere in Kronn. Quick glossary to decode the rest: what it is, what it does.
Reusable prompt template with variables {{ticket}}, {{context}}. Versioned. Metrics recorded per version (tokens, duration, cost). ✨ Improver button to iterate with AI.
A sequence of Quick Prompts. Each QP can reference {{previous_qp.output}} to chain the previous output. Drag & drop reorderable.
Model Context Protocol · open standard (by Anthropic) letting AI agents access external tools. Kronn relies on MCP to bridge the CLIs and expose its own tools via kronn-internal.
The 7 step types in a workflow: 2 AI (Agent, BatchQuickPrompt) and 5 mechanical (ApiCall, BatchApiCall, Notify, Exec, Gate) at 0 tokens.
Opt-in loop after audit: Kronn detects tech debt, creates Jira tickets via MCP, pre-configures a workflow to handle them. One click, done.
Implementation pattern for big tickets: Kronn generates a feasibility YAML manifest, then a human Gate (you approve or reject), then the agent codes following the manifest. Zero surprise.
The canonical doc source for a Kronn project. Generated by the audit. Tier-loaded (light always-on, sections on-demand). Auto-read by every CLI that opens the project.
4 flavors: MCP (vendor exposes a server, e.g. Atlassian), API (API-only vendor packaged, e.g. Resend), Hybrid (both), Custom API (declare your own endpoints).
Local-first by default. No telemetry, no cookies, no Kronn server. Here is what is protected, and what we don't have yet: honesty before the certification seal.
~/.kronn/.env and vendor prefixes filtered before docs/AGENTS.mdExec gated by workflow exec_allowlist (literal argv, no sh -c)Gate human-in-the-loop: the agent waits for your explicit approval