For teams whose agents keep repeating the same mistake
The open-source AI Operating System
Harness engineering is the practice of designing the environment an AI agent operates within: the rules it follows, the checks it must pass, and the feedback loops that prevent the same mistake from recurring. Reliability is decided in that harness. Kortix is the open-source AI Operating System, and it keeps the harness in files you own.
Open source · Any model provider with your own keys · Approval gates you set
const cfg = loadConfig() // reads KORTIX_HARNESS, then the selected adapter's env
const selected = resolveHarness(cfg)
const runtime = selected.createService(cfg, projectEnv)
await runtime.lifecycle.start()/kortix-ai/suna/blob/dev/apps/kortix-sandbox-agent-server/src/harness/README.md
Each one is a file a reviewer can open, diff and roll back.
Guides and sensors
A linter steers the change on the way in, a test reports on what came out, and the same failure cannot pass twice.
src/orders/total.ts- return items.reduce(sum) + tax+ return items.reduce(sum, withTax)lint · typecheck · test: pass
Permissions
The agent edits its own branch without a prompt and stops on the one call that reaches production.
policy in the manifest
Swappable harness
A preflight answers what a switch would cost before anyone makes it, and the log records the switch when it happens.
2 adapters registered
What matters is where the rules live, who can change them, and what runs the agent.
Open source here means the adapter, the manifest and the rules around them are yours to read, fork and audit.
It moves reliability into the environment around the model, the part LangChain calls the harness. On public benchmarks, the same model can place significantly higher or lower depending entirely on how that harness is built. Databricks paired GPT-5.5 with its OfficeQA Pro Agent Harness and scored 52.63%, up from 36.10% with GPT-5.4.
With the mistake that just happened. Fix it in the environment rather than in the prompt: a lint rule, a test, a hook, or one line the agent reads every session. Then commit those files and review them like any other code.
Yes. Guides steer any agent before it acts and sensors check what it produced after, so a research agent gets a source check on the way in and a citation check on the way out. The checks change with the job; the structure does not.
Agents, skills, company memory and connectors in one git repo.