Akka releases platform for agentic AI

Akka, provider of a popular framework for building reactive, distributed applications on the JVM, has introduced the Akka Agentic Platform, an integrated suite of offerings for building, operating, and evaluating agentic AI systems.

Announced July 14, Akka Agentic Platform includes capabilities for orchestrating long-running systems, building agents, providing in-memory context to agents, and providing high-performance stream processing. “These integrated offerings deliver 3x the velocity, 1/3rd the compute, and any SLA for every agentic system whether autonomous, adaptive, real-time, transactional or edge,” Akka CEO Tyler Jewel said in the announcement.

In explaining the needs the platform is intended to fill, Jewel said the prospect of uncertainty in agentic AI challenges how IT systems are designed and maintained. Unlike traditional deterministic systems, agentic AI introduces emergent behaviors, non-deterministic decision-making, and context-sensitive reasoning. All of these bring new dimensions of unpredictability into enterprise environments, limiting the ability to deploy these systems for large-scale, business-critical use cases, Jewel stressed.

The Akka Agentic Platform gives IT leaders the certainty to meet operational SLAs for availability and recovery, and behavioral SLAs for safety and accuracy, Akka said. In addition, these new capabilities are comprehensive and unique in that they enable enterprise teams to create any kind of agentic system, whether autonomous, adaptive, real-time, or edge.

The components of the Akka Agentic Platform include:

Akka Orchestration – Control long-running, multi-agent systems even across crashes, delays, or infrastructure failures with sequential, parallel, hierarchical, and human-in-the-loop workflows. Embed a registry for agent, tool, API, and resource governance.

Akka Agents – Create goal-directed agents, MCP tools, and HTTP or gRPC APIs that reason, act, and analyze. Integrate any third-party broker, agent or system.

Akka Memory – Durable, in-memory, and sharded data for agent context, history retention, and personalized behavior. Supports short-term and long-term memory.

Akka Streaming – High-performance stream processing for ambient, adaptive, and real-time AI. Continuous processing, aggregation, and augmentation of live data, metrics, audio, and video.

The Akka Agentic Platform is available now. Alongside the Akka Agentic Platform release, Akka also introduced an AI-assisted developer experience, which leverages the power of LLMs to accelerate the development of Akka systems with agents that create, modify, test, and evaluate Akka services built with the Akka SDK.