Finally, an OpenRouter for agent harnesses! (including System One by Jev) Devs just open-sourced a plug-and-play infrastructure layer that lets you run any harness under a single interface, like: - Codex - Hermes - Claude code - DeepSeek Harness - System One, powered by Jev - And 9 more... agent harnesses This means you can bring Jev into the same product that already uses Codex, Claude Code, or another supported harness, without writing another implementation for sessions, streaming, files, cancellation, and failure handling. Here's the repo: (don't forget to star it ⭐ ) The harnesses run locally, and the Unified Harness Protocol (UHP) defines the common task interface with an OpenAI Responses-compatible API. If you want to dive deeper, my recent article explains why model routing is not the same as harness routing, and what it takes to support multiple harnesses. It also covers UHP, the full local setup, a working API call, and how sessions and files work. Read it below.show more

OpenRouter works because all the models behind it take the same shape — text in, text out. Agent harnesses have different state, tool signatures, and session models. How does a unified interface handle that?

I only run one harness for my own build, Claude Code, so I've never hit the switching-cost pain this solves directly. for someone already committed to one harness, is the real win here A/B testing models across harnesses, or something else?

Useful layer. Separate itch on my side: once Codex / Claude Code / etc are installed they still rubber-stamp themselves. I built consilium so the hub agent can `consult` a different-provider CLI for a second opinion, or run a council that verifies every file:line finding.

The hard part seems to be semantic parity: session resume, streamed tool events, and cancellation need identical guarantees across harnesses. A conformance suite covering those cases would make UHP much more useful than an adapter layer.

This could make building with multiple AI agents much simpler. One interface, multiple harnesses.

What would be really cool is if the router automatically chooses the correct harness for a given task.

Interesting! I’ll try it out for mobile development and then share my hands-on experience on my page

standardizing the harness layer is the missing piece. in our autonomous pipeline targeting brazil, we don't bind models to tasks directly. the harness runs deterministic python stages and invokes external harnesses only when schema gates fail. harness routing > model routing

@akshay_pachaar that's a game-changer for devs dealing with multiple harnesses! simplifies the workflow like crazy. really makes you think about how much time we waste on integrations.

Yoooo lemme finish up TaskWraith so it qualifies 🥲

OM >

The unified interface is the strongest part, but harness routing is not quite equivalent to model routing: harnesses carry different state, tool semantics, and failure modes. UHP can normalize the plumbing, not erase those behavioral differences.

routing models is easy. routing harnesses is the part people pay for twice.

one harness already needs a babysitter. now i can route between five lol

the idea of running multiple harnesses like Codex and Claude under one interface is really cool, should save a lot of time

A shared harness interface is useful only if it standardizes the ugly parts too, especially cancellation, state handoff, and failure recovery across sessions.

model routing works because the contract is thin -- messages in, tokens out. harness routing means normalizing side effects: how each one sandboxes shell access, what a cancellation leaves mid-file-write, when a permission prompt blocks vs auto-approves. that's where it leaks first.

Having a clean abstraction layer to benchmark different harnesses against the exact same task suite is huge.

Unified interface sounds useful, but wondering how you handle the different prompt/response formats across Codex, Claude Code, and DeepSeek? Does the abstraction leak when one tool expects JSON while another wants raw text?

Curious how you measured harness-to-harness overhead — same task, same model, what’s the extra latency and tokens just from the unified protocol versus talking to Claude Code or Codex directly?

专为代理框架设计，UHP统一会话流式取消这类脏活实现

Unifying the harness interface is useful, but did anyone run the same task set across Codex / Claude Code / Jev and report tokens per solved task plus idle turns?

We already have @omnigent_ai, you’re overlooking this…

harness switcher is nice. finding one that barely drains is better

the agent wars are just starting and standardizing the harness layer is already table stakes, whoever owns that interface wins.

Standardizing permissions and sessions sounds clean until two runtimes disagree on the schema. Still babysitting, just one level higher up.

A common protocol gets you portability. State and tool behavior decide whether the switch is actually painless. Are you using more than one coding harness today?

One interface across harnesses is useful mostly for comparison. The part worth normalising along with the calls is failure: each harness reports a failed tool step differently, and some report it as a normal answer. Does the layer unify errors, or pass them through?

One interface for the harness, not just the model.

not sure the OpenRouter analogy holds. OpenRouter works because models share a shape. harness behavior is the opinionated part, and a wrapper flattens exactly that. does it preserve Jev's context-carry or does that disappear?

Under one harness interface, what breaks first when you swap Codex for Claude Code: permissions, tools, or memory?

Unified Harness Protocol can list Codex. Sessions and cancellation still have to work across every harness.

I honestly start to be fed up about these hype driven, AI written tools and articles that add complexity instead of value.

this is actually massive for agent infra