Thenvoi launches platform to assist developers orchestrate multiple AI coding agents

Thenovi AI Ltd., an organization developing an interaction infrastructure for artificial intelligence agents, today announced the launch of its developer platform that connects coding agents for shared conversations.

As more coders adopt AI agents, they’ve begun to specialize them into different roles: planning, review, integration and testing. It is because, in lots of cases, developers discovered certain models have different quirks that make them more efficient at particular tasks.

For instance, a developer might use Claude Code to orchestrate a workflow and supply high-level planning and architecture, Codex for code implementation, and a fleet of other agents for testing and review.

“Coding is becoming agent-based, however the agents themselves can’t actually work together,” said co-founder and Chief Executive Arick Goomanovsky.

Goomanovsky identified that after each iteration, it comes all the way down to the developer to take the output from one agent after which feed it into the following one. This becomes a tedious dance of copy/paste or document shuffling between tools.

Thenovi seeks to resolve this by becoming a chat-hookup backend that may spin up agents, providing them with a shared space where the developer can communicate with them as in the event that they were a team of employees.

The software engineer can then provide the plan document to the planner, which then crunches on the schema to get the architecture of the project polished. Once that’s ready, it may well be passed off for the reviewer to fill in any gaps before implementation, which might request the planner to repair up the plan document. Next, the finalized project requirements get handed off to a coding implementation agent, which might break it down into subtasks and coding agents get to work. Finally, testing and security agents get the ending touches squared away, which could iterate back to implementation for code fixes.

“As a substitute of wiring agents together through files or local shared state, developers can connect agents to a standard environment where coordination happens routinely,” explained Chief Technology Officer Vlad Luzin.

In line with Thenovi, context, files and workflow remain coherent your complete time as every agent retains persistent knowledge of its role and last motion inside the project. Under the hood, orchestration incorporates specialized logic to forestall rationale loops, dead-end pathways and overthinking.

The launch also arrives as personal AI agents, equivalent to OpenClaw, have begun to emerge within the open-source community and repair providers. These agents act as colleagues that may reason, plan and take motion for his or her users. Nevertheless, like many current enterprise-level agents, they operate in isolation.

In addition they lack a secure technique to discover and connect with other agents without additional plugins.

Thenovi said its platform can extend beyond development work through what it calls Agentic Mesh, a connectivity layer for independent agents to securely discover one another. Using the mesh, agents can securely connect, communicate and delegate tasks inside user-set boundaries.

With the platform, a private agent could coordinate directly with one other agent or interact with a vendor’s service agent to barter tasks, coordinate logistics or execute transactions while maintaining identity controls.

Image: SiliconANGLE/Microsoft Designer