Kerno
Also known as: Kerno.io, KIT (Kerno Intelligence Tools)
AI backend QA engineer that coding agents drive over MCP to test every code change against the running app and dependencies, with baseline diffs, security checks, MCP server testing and plan approval gates.
Kerno is an AI backend QA engineer that runs inside a coding agent's loop. The customer's coding agent, such as Claude Code, Codex or Cursor, drives Kerno over MCP, and Kerno reviews what the agent just wrote against the running app and its real dependencies, so the agent can read the results and fix what broke in the same session.
Kerno builds a deterministic index of the codebase, connects to the running app locally or remotely, and generates tests covering each endpoint's functional behavior, edge cases and security, which it runs to capture a baseline.
When code changes, it maps the blast radius, re-runs the affected tests and shows each difference from the baseline so the team can tell an intended change from a bug, then updates the suite for intended changes. It also tests MCP servers' tools against the running server and background jobs through the customer's own broker.
Its agent pauses for approval of the environment and scenario plans, keeps reviewable memory of what it learns about the codebase, and replays committed tests on every pull request through a GitHub Action.
Kerno runs locally and keeps code on the customer's machine, sending excerpts to Anthropic and OpenAI through its proxy on zero-data-retention terms. The Community plan is free for 30 test runs a month, Pro is $50 per developer per month, and Enterprise adds SSO and SAML, self-hosting and audit logs; a SOC 2 Type 2 audit is in progress.
Vendor details
Canonical URL
https://www.kerno.io/
Category
Agent infrastructure
Funding status
Seed stage (last funding recorded December 2023); amount not disclosed this session.
Company status
independent
Use cases & customers
Primary use cases
Target customers
Deployment options
Integrations
Runs inside the IDE and orchestrates the app plus its dependencies locally, mocking external dependencies so tests run against the real stack. Works alongside AI code generation tools including Cursor and Claude Code, validating each change before a pull request. Distributed as KIT (Kerno Intelligence Tools) with a 60 second install.
Sources & related URLs
Agentic Index coverage score
8.0 / 14 capabilities · 57%
| Integrations & Tool Calling | Partial |
|---|---|
|
Kerno's agent calls the customer's running endpoints, triggers background tasks through the customer's own message broker, introspects MCP servers and runs against real dependencies such as databases and caches, and integrates with coding agents over MCP, GitHub and CI. These actions reach the customer's own app under test. No connector, OAuth-authorized action or custom tool that lets an agent act on other business systems is described. SourceKerno, kerno.gitbook.io/docs security testing, environment setup and integrations, and kerno.io/llms.txtread 2026-09-21 |
|
| Workflow Orchestration | Partial |
|
A fixed pipeline drives Kerno's agent, mixing deterministic steps with the agent's own planning: it indexes code, builds a Docker Compose environment, plans and writes scenarios, runs each one repeatedly with critique and repair until it passes, and updates the suite, as async jobs that can be polled or canceled. Customers do not define or reuse their own workflows. SourceKerno, kerno.gitbook.io/docs how Kerno works, testing modes and Kerno MCPread 2026-09-21 |
|
| Knowledge Grounding & RAG | Full |
|
Underneath the agent sits a deterministic index of the customer's codebase that resolves every function, class, model, endpoint, import and reference to a precise location. Kerno keeps it up to date as the code changes by re-deriving only what a change affects, and queries it to find each change's blast radius and the endpoints to test; custom rules add the team's own testing guidance. New code enters the index without retraining, and the agent reads it to decide what to test and to show which code a change touches. SourceKerno, kerno.gitbook.io/docs codebase indexing, how Kerno works and custom rulesread 2026-09-21 |
|
| Human Oversight & Guardrails | Full |
|
Before Kerno's agent acts, it pauses for approval: it shows the full environment build plan and cannot start the environment until the plan is explicitly approved, it shows the scenario plan before writing any test and lets the person approve it, reject individual scenarios or give feedback, and it opens feedback requests for plan approvals, planner questions or missing credentials that are answered with an approval or a rejection with a reason. Generate runs always pause for approval, update runs pause only in interactive mode, and a plan-approval setting chooses between gated and automatic runs. SourceKerno, kerno.gitbook.io/docs testing modes, Kerno MCP feedback gate and changelogread 2026-09-21 |
|
| Security, Identity & Governance | Partial |
|
On the Enterprise plan, Kerno offers SSO and SAML, audit logs and data controls and a custom data processing agreement, its portal gives organizations owner, admin and member roles, and API keys can be revoked or expire; the homepage states a SOC 2 Type 2 audit is in progress. SourceKerno, kerno.io pricing and homepage, and kerno.gitbook.io/docs organizations and teamsread 2026-09-21 |
|
| Observability & Auditability | Partial |
|
An IDE extension shows what Kerno's agent is doing, run reports are uploaded to a portal that rolls up coverage, issues and runs across repositories, and job status and results are readable over MCP and HTTP. A step-by-step record of the agent's own prompts, tool calls and reasoning is not described. SourceKerno, kerno.gitbook.io/docs portal overview, reports and dashboards, IDE extension and Kerno MCPread 2026-09-21 |
|
| Memory & State Persistence | Full |
|
What Kerno's agent learns from the code, from running tests and from the team's feedback, such as how an endpoint authenticates or what must be seeded before a request succeeds, goes into long-term memory, and the agent reuses those lessons when planning later tests. People can review each lesson and agree, amend its wording or disagree so Kerno stops using it, unchecked lessons are labeled as such, and each entry is stored as a git commit stamped with the code revision it was learned at so stale analysis is re-derived when code changes. SourceKerno, kerno.gitbook.io/docs memory and learningread 2026-09-21 |
|
| Deployment & Data Residency | Full |
|
The Kerno agent runs on the customer's machine, with the repository, code index, test environment, scenarios and baselines kept on the local filesystem and in local Docker containers and no code stored on Kerno's servers, and the Enterprise plan adds self-hosting in the customer's own infrastructure. SourceKerno, kerno.gitbook.io/docs security and privacy, and kerno.io/pricingread 2026-09-21 |
|
| Prebuilt Agents / Templates / Packs | Not documented |
|
The offering is a single testing agent with built-in validation categories. No catalog of ready-made agents, templates or packaged workflows a buyer adopts for its own work is offered. SourceKerno, kerno.io homepage and kerno.io/llms.txtread 2026-09-21 |
|
| Triggers & Channel Coverage | Partial |
|
A customer's coding agent starts Kerno's agent by calling it over MCP inside a coding session, and a GitHub Action replays the committed tests on every pull request without an account or agent. No event or schedule that starts the agent on its own, without someone's session asking for it, is documented. SourceKerno, kerno.gitbook.io/docs Kerno MCP and running tests in CIread 2026-09-21 |
|
| Model Flexibility & Routing | Not documented |
|
To plan and reason about tests, Kerno sends code excerpts to Anthropic and OpenAI through its own proxy. No customer choice of model or provider, bring-your-own keys, routing policy or fallback is documented. SourceKerno, kerno.gitbook.io/docs security and privacyread 2026-09-21 |
|
| APIs / SDKs / MCP Extensibility | Partial |
|
Kerno is driven through an MCP server with an enumerated set of tools for workspaces, environments, endpoint tests, jobs and feedback, a documented CLI installed from npm, an HTTP jobs endpoint and an API key for non-interactive sign-in in CI. The local agent also serves a REST API on localhost for the IDE extension and CLI, but no reference for it and no SDK is published. SourceKerno, kerno.gitbook.io/docs Kerno MCP, Kerno CLI and integrations and API keysread 2026-09-21 |
|
| Testing, Debugging & Optimization | Full |
|
Kerno generates functional, edge-case and security tests for each endpoint, runs them against the customer's running app to capture a baseline, re-runs the affected tests whenever the customer's coding agent changes code and reports each difference from the baseline, updates the suite when a change is intended, tests MCP servers' tools against the running server, and replays the committed tests on every pull request as a CI check. SourceKerno, kerno.gitbook.io/docs how Kerno works, change validation and running tests in CI, and kerno.io/llms.txtread 2026-09-21 |
|
| Browser / Computer-use | Not documented |
|
Kerno tests backends, APIs, MCP servers and background workers over HTTP and message brokers, and no browser, desktop or computer control by an agent is documented. SourceKerno, kerno.gitbook.io/docs overview and kerno.io/llms.txtread 2026-09-21 |
|
The Agentic Index coverage score grades every vendor Full, Partial or Not documented against the same 14 buyer facing capabilities, from public evidence only. Each capability links to how all vendors in the index score on it. How this evidence is graded
Recent platform changes
Kerno introduced automated runtime testing for Model Context Protocol (MCP) servers. The platform now introspects running servers to generate test scenarios directly from the actual tool surface, executing them in a local sandbox. This catches critical defects like authentication gaps, leaked configurations, and boundary enforcement failures before they reach production.
Bears on: Security / enterprise
View sourcePricing
Free · Pro $50 per developer per month
Per developer per month, with test runs metered on the free plan (each scenario run against the app counts as one run)
Cost watchouts
Every scenario run counts as a test run, so a single endpoint with five scenarios uses five runs and the free plan's 30 go quickly; SSO, self-hosting and audit logs need Enterprise.
Variable cost rationale
Paid cost scales with the number of developers; the free plan caps test runs, and Pro removes the cap, so usage does not add cost once on Pro.
Sales call required
Mixed (some tiers require a call)
Free / trial
Community plan free with 30 test runs a month, no credit card
Lowest paid plan
Pro, $50 per developer per month
Commercial notes
Self-serve per-developer pricing from a free Community plan to Pro at $50 a developer a month, with Enterprise through sales for SSO, self-hosting and audit logs, plus free open-source and discounted startup programs.
Key ambiguities
Enterprise pricing is not published. The KIT code-intelligence graph is free and unlimited on all plans.
Related vendors
- AgentOps — Agent observability and debugging platform: open source SDKs trace…
- Agno — Python agent framework and AgentOS runtime (formerly Phidata) for…
- AIsa — Resource and payment gateway for AI agents: one key to 110+ models…
- AlphaBitCore — AI control plane for regulated financial firms: one gateway enforces…
- Anchor Browser — Cloud hosted browser infrastructure that lets AI agents operate real…
- Apify — Cloud platform and marketplace of more than 73,000 ready-to-run…
Alternatives to Kerno
The closest documented capability profiles to Kerno among agent infrastructure platforms tracked by Agentic Index, ordered by similarity on the same 14 point evidence the rankings use. No vendor pays for placement.
- LangChain11.5 / 14Adds documented Prebuilt Agents, Templates & Packs and Model Flexibility & Routing
- Personal AI9.5 / 14Adds documented Prebuilt Agents, Templates & Packs and Model Flexibility & Routing
- Cognee7.0 / 14Adds documented Model Flexibility & Routing
- Extend9.0 / 14Adds documented Model Flexibility & Routing
- Lemony7.0 / 14Adds documented Prebuilt Agents, Templates & Packs and Model Flexibility & Routing
- LlamaIndex12.0 / 14Adds documented Prebuilt Agents, Templates & Packs and Model Flexibility & Routing
Similarity is computed from each vendor's Agentic Index coverage score evidence, axis by axis, not from the totals. How this evidence is graded