Agentic AI Platform Change Log

Agent capability

Prime Intellect rewrote Prime Agent, its open source coding agent, in Rust, adding native Windows support in beta and installation through Homebrew. Each session now runs in its own worker process so one crash leaves the others running, and sessions persist on disk so clients can reattach after a restart.

Windows developers can run the agent natively, and lower memory and startup cost matter when running many sessions or subagents at once. The speed figures in the post are the vendor's own.

MCP / tool calling / API

Prime Intellect publicly released Prime Inference, a serving platform for open models on its own GPU fleet, with serverless endpoints, reserved capacity and failover between data centers, starting with GLM-5.3. It enforces declared tool schemas during generation so tool calls stay valid through long agent sessions.

Teams running agents on open models can get production serving from the same vendor that trains their models. Batch inference and one click deployment of fine tuned models are still on the roadmap.

Deployment / data residency

Prime Intellect made Prime Sandboxes generally available through its CLI and SDK and as part of its reinforcement learning stack. Each sandbox runs a Linux microVM with its own kernel, supporting Docker Compose, background services and custom Docker images. Accounts start with capacity for 1,024 concurrent sandboxes.

Teams training and evaluating agents can use VM isolation while retaining their existing Docker environment definitions. Native Docker and kernel support broaden the workloads they can test without operating the underlying VM fleet.

Agent capability

Prime Intellect announced the general availability of Lab, its training platform for self-improving agents. The platform has officially transitioned out of beta to provide full-stack capabilities for post-training research and agentic reinforcement learning.

Engineering teams can now utilize a production-ready environment to train and continuously improve their own agentic models. This removes the need to manage low-level algorithm details or massive GPU clusters independently.

Deployment / data residency

Prime Intellect released Prime Flash MoE, a set of open-source CUDA kernels optimized for Nvidia Blackwell GPUs to accelerate the feed-forward pass in Mixture-of-Experts (MoE) models. Integrated into the prime-rl framework, these kernels keep intermediate activations on-chip, achieving up to a 2.4x speedup over PyTorch grouped GEMM.

Infrastructure teams and developers running large-scale MoE models can reduce inference latency and hardware overhead on Nvidia B200 GPUs. By accelerating the computational pass and cutting memory traffic, this update lowers the cost of serving complex agentic models in production.

Agent capability

Prime Intellect open-sourced Prime Agent, a self-improving coding and research harness released under the MIT License. The system utilizes a Recursive Language Model framework and a Continual Harness, allowing the agent to manage prompts, sub-agents, skills, and memory as state variables that can be modified during execution.

Engineering teams and AI labs can deploy this harness to build autonomous agents capable of executing complex, multi-hour tasks like overnight refactors or kernel optimization. The open-source architecture and persistent IPython kernel integration provide a highly customizable, token-efficient alternative to proprietary agent frameworks without vendor lock-in.

Integrations

Prime Intellect integrated NVIDIA Vera CPUs, NVIDIA Dynamo inference orchestration, and NeMo Gym open-source reinforcement learning tools into its Lab platform and sandbox infrastructure. This combined hardware and software alignment optimizes continuous reinforcement learning loops for agentic AI models.

Engineering and research teams can execute post-training workflows more efficiently on Prime Intellect infrastructure. The integration enables a reported 30% increase in sandbox throughput per CPU, lowering the overall compute costs required for continuous agent refinement.